CN106407984A - Target object recognition method and device - Google Patents
Target object recognition method and device Download PDFInfo
- Publication number
- CN106407984A CN106407984A CN201510464842.7A CN201510464842A CN106407984A CN 106407984 A CN106407984 A CN 106407984A CN 201510464842 A CN201510464842 A CN 201510464842A CN 106407984 A CN106407984 A CN 106407984A
- Authority
- CN
- China
- Prior art keywords
- image
- preset value
- corresponding matching
- value
- matching value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/48—Matching video sequences
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a target object recognition method and device and belongs to the technical field of the application of Internet of Things. The method is used in a photographing terminal and comprises the following steps: acquiring n picture frames captured by the photographing terminal; calculating the matching degree of the images of the respective objects contained in the n picture frames with preset image samples to obtain matching values corresponding to the respective objects; sending the images of the objects with the matching values higher than the preset value to a cloud server in order that the cloud server recognizes and the images of the objects with the matching values higher than the preset value to detect whether the objects with the matching values higher than the preset value are the target objects. The method makes simple matching in the photographing terminal to single out the images required to be further identified, and uploads the selected images to the cloud server for further identification to meet a requirement for fast identification, reduce a requirement for network bandwidth and save network traffic.
Description
Technical field
The present invention relates to Internet of Things applied technical field, particularly to a kind of recongnition of objects method and device.
Background technology
With the continuous development of Internet of Things application technology, need under a lot of application scenarios according to the image photographing
Quickly recognize destination object, this is just proposed very high requirement to the speed and the degree of accuracy of identification.
Existing recongnition of objects scheme, generally by means of the powerful operational capability in high in the clouds, camera terminal is clapped
The video taken the photograph or picture are uploaded to cloud server, carry out image procossing and target by cloud server to it
After Object identifying, recognition result is returned to camera terminal.
In the prior art, when carrying out recongnition of objects by cloud server, need to shoot camera terminal
Video or picture be all uploaded to cloud server, this is higher to network bandwidth requirement, also can consume simultaneously
Substantial amounts of flow.
Content of the invention
In order to solve to need in correlation technique the video shooting camera terminal or picture to be all uploaded to high in the clouds clothes
Business device, higher to network bandwidth requirement, also can consume the problem of a large amount of flows, the embodiment of the present invention carries simultaneously
Supply a kind of recongnition of objects method and device.Described technical scheme is as follows：
A kind of first aspect, there is provided recongnition of objects method, in camera terminal, methods described bag
Include：
Obtaining the n image frame that described camera terminal photographs, n >=1, and n is integer；
The image of each object comprising in described n image frame and the image pattern pre-setting are carried out
Degree of joining calculates, and obtains the corresponding matching value of described each object；
By in described each object, corresponding matching value is higher than that the image of the object of preset value is sent to high in the clouds clothes
Business device, the image by described cloud server to described corresponding matching value being higher than the object of preset value carries out figure
As identification, to detect that whether described corresponding matching value is higher than the object of preset value as destination object.
A kind of second aspect, there is provided recongnition of objects method, in cloud server, methods described
Including：
Receive the image that camera terminal sends, described image is that described camera terminal obtains the n picture photographing
Face frame；The image of each object comprising in described n image frame and the image pattern pre-setting are carried out
Matching degree calculates acquisition, and corresponding matching value is higher than the image of the object of preset value, n >=1, and n is whole
Number；
Image recognition is carried out to described image, with detect described corresponding matching value be higher than preset value to as if
No for destination object.
A kind of third aspect, there is provided recongnition of objects device, in camera terminal, described device bag
Include：
Image frame acquisition module, for obtaining the n image frame that described camera terminal photographs, n >=1, and n
For integer；
Matching module, for by the image of each object comprising in described n image frame with pre-set
Image pattern carries out matching degree calculating, obtains the corresponding matching value of described each object；
Image sending module, for by described each object, corresponding matching value is higher than the object of preset value
Image be sent to cloud server, by described cloud server to described corresponding matching value be higher than preset value
The image of object carry out image recognition, with detect described corresponding matching value be higher than the object of preset value whether
For destination object.
A kind of fourth aspect, there is provided recongnition of objects device, in cloud server, described device
Including：
Image receiver module, for receiving the image of camera terminal transmission, described image is described camera terminal
Obtain the n image frame photographing；By the image of each object comprising in described n image frame with advance
The image pattern of setting carries out matching degree and calculates acquisition, and corresponding matching value is higher than the figure of the object of preset value
Picture, n >=1, and n are integer；
Identification module, for carrying out image recognition to described image, to detect that described corresponding matching value is higher than
Whether the object of preset value is destination object.
The beneficial effect that technical scheme provided in an embodiment of the present invention is brought includes：
By obtaining n image frame photographing of camera terminal, by comprise in this n image frame each is right
The image of elephant carries out matching degree calculating with the image pattern pre-setting, and obtains the corresponding coupling of this each object
Value, and by this each object, corresponding matching value is higher than that the image of the object of preset value is sent to high in the clouds clothes
Business device, the image by this cloud server to this corresponding matching value being higher than the object of preset value carries out image knowledge
Not, entered in camera terminal whether as destination object with detecting the object that this corresponding matching value is higher than preset value
Row simple match filters out the image needing to identify further, and the image filtering out is uploaded to cloud service
Device is identified further, and due to the speed of simple match, and the amount of images uploading is also fewer,
Reach while meeting quick identification needs, reduce the requirement to the network bandwidth, save the effect of network traffics
Really.
Brief description
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, below will be to institute in embodiment description
Need use accompanying drawing be briefly described it should be apparent that, drawings in the following description are only the present invention
Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work,
Other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is the implementation environment figure involved by recongnition of objects method that section Example of the present invention provides；
Fig. 2 is the block diagram of the terminal that one embodiment of the invention provides；
Fig. 3 is the structural representation of the server that one embodiment of the invention provides；
Fig. 4 is the flow chart of the recongnition of objects method that one embodiment of the invention provides；
Fig. 5 is the flow chart of the recongnition of objects method that one embodiment of the invention provides；
Fig. 6 is the flow chart of the recongnition of objects method that one embodiment of the invention provides；
Fig. 7 is the structure drawing of device of the recongnition of objects device that one embodiment of the invention provides；
Fig. 8 is the structure drawing of device of the recongnition of objects device that one embodiment of the invention provides；
Fig. 9 is the system construction drawing of the recongnition of objects system that one embodiment of the invention provides.
Specific embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing to the present invention
Embodiment is described in further detail.
Implementation environment
Refer to Fig. 1, it illustrates involved by the recongnition of objects method that section Example of the present invention provides
Implementation environment figure.Implementation environment shown in Fig. 1 includes：Camera terminal 110, cloud server 120；Optional
, this implementation environment can also include mobile terminal 1 30.
Camera terminal 110 can be the equipment with video or picture shooting function, such as fixing or movement
Camera, drive recorder or moving camera etc..
Cloud server 120 can be a server, or or is made up of several servers
Service cluster, an or or cloud computing center.
Mobile terminal 1 30 can be that smart mobile phone, panel computer, E-book reader and intelligence are wearable
Equipment (such as smart mobile phone, intelligent glasses or Intelligent bracelet) etc. is easy to the intelligence that user carries with and is set
Standby.
Wherein, pass through wired or nothing between camera terminal 110, cloud server 120 and mobile terminal 1 30
Gauze network is attached.
Computer architecture
Refer to Fig. 2, it illustrates the block diagram of the terminal that one embodiment of the disclosure provides, the disclosure
Terminal in embodiment can include one or more following parts：For executing computer program instructions
To complete the processor of various flow processs and method, instruct random access memory for information and storage program
(RAM) and read-only storage (ROM), for the memory of data storage and information, I/O equipment, boundary
Face, antenna etc..Specifically：
Terminal 200 can include RF (Radio Frequency, radio frequency) circuit 210, memory 220, defeated
Enter unit 230, display unit 240, sensor 250, voicefrequency circuit 260, WiFi (wireless fidelity,
Wireless Fidelity) part such as module 270, processor 280, power supply 282, camera 290.People in the art
Member, it is appreciated that the restriction of the terminal structure not structure paired terminal shown in Fig. 2, can include than diagram
More or less of part, or combine some parts, or different part arrangements.
With reference to Fig. 2, each component parts of terminal 200 is specifically introduced：
RF circuit 210 can be used for receiving and sending messages or communication process in, the reception of signal and transmission, especially,
After the downlink information of base station is received, process to processor 280；In addition, up data is activation will be designed
To base station.Generally, RF circuit includes but is not limited to antenna, at least one amplifier, transceiver, coupling
Device, LNA (Low Noise Amplifier, low-noise amplifier), duplexer etc..Additionally, RF circuit 210
Can also be communicated with network and other equipment by radio communication.Described radio communication can use arbitrary communication
Standard or agreement, including but not limited to GSM (Global System of Mobile communication, the whole world
Mobile communcations system), GPRS (General Packet Radio Service, general packet radio service),
CDMA (Code Division Multiple Access, CDMA), WCDMA (Wideband Code
Division Multiple Access, WCDMA), LTE (Long Term Evolution, Long Term Evolution),
Email, SMS (Short Messaging Service, Short Message Service) etc..
Memory 220 can be used for storing software program and module, and processor 280 is stored in by operation
The software program of reservoir 220 and module, thus execute at various function application and the data of terminal 200
Reason.Memory 220 can mainly include storing program area and storage data field, and wherein, storing program area can be deposited
Application program (such as sound-playing function, image player work(needed for storage operating system, at least one function
Can etc.) etc.；Storage data field can store according to terminal 200 using data (the such as audio frequency number being created
According to, phone directory etc.) etc..Additionally, memory 220 can include high-speed random access memory, acceptable
Including nonvolatile memory, for example, at least one disk memory, flush memory device or other volatibility
Solid-state memory.
Input block 230 can be used for numeral or the character information of receives input, and produces and terminal 200
User setup and function control relevant key signals input.Specifically, input block 230 may include touch-control
Panel 231 and other input equipments 232.Contact panel 231, also referred to as touch-screen, can collect user and exist
(such as user uses any suitable object such as finger, stylus or annex to exist for touch operation on or near it
Operation on contact panel 231 or near contact panel 231), and phase is driven according to formula set in advance
The attachment means answered.Optionally, contact panel 231 may include touch detecting apparatus and touch controller two
Part.Wherein, touch detecting apparatus detect the touch orientation of user, and detect the signal that touch operation brings,
Transmit a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and will
It is converted into contact coordinate, then gives processor 280, and can the order sent of receiving processor 280 in addition
Execution.Furthermore, it is possible to be realized using polytypes such as resistance-type, condenser type, infrared ray and surface acoustic waves
Contact panel 231.Except contact panel 231, input block 230 can also include other input equipments 232.
Specifically, other input equipments 232 can include but is not limited to physical keyboard, function key (such as volume control
Button processed, switch key etc.), trace ball, mouse, one or more of action bars etc..
Display unit 240 can be used for showing by the information of user input or the information and the terminal that are supplied to user
200 various menus.Display unit 240 may include display floater 241, optionally, can adopt
LCD (Liquid Crystal Display, liquid crystal display), OLED (Organic Light-Emitting Diode,
Organic Light Emitting Diode) etc. form configuring display floater 241.Further, contact panel 231 can cover
Display floater 241, when contact panel 231 detects thereon or after neighbouring touch operation, sends process to
Device 280 to determine the type of touch event, with preprocessor 280 according to the type of touch event in display surface
Corresponding visual output is provided on plate 241.Although in fig. 2, contact panel 231 and display floater 241
It is input and the input function to realize terminal 200 as two independent parts, but in some embodiments
In, can contact panel 231 is integrated with display floater 241 and input and the output work of realizing terminal 200
Energy.
Terminal 200 may also include at least one sensor 250, such as gyro sensor, magnetic induction sensor,
Optical sensor, motion sensor and other sensors.Specifically, optical sensor may include ambient light sensing
Device and proximity transducer, wherein, ambient light sensor can adjust display floater according to the light and shade of ambient light
241 brightness, proximity transducer can when terminal 200 moves in one's ear, close display floater 241 and/or
Backlight.As one kind of motion sensor, acceleration transducer can detect (generally three axles) in all directions
The size of acceleration, can detect that size and the direction of gravity when static, can be used for answering of identification terminal attitude
With (such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as
Pedometer, percussion) etc.；The barometer that can also configure as terminal 200, hygrometer, thermometer, infrared ray
The other sensors such as sensor, will not be described here.
Voicefrequency circuit 260, loudspeaker 261, microphone 262 can provide the audio frequency between user and terminal 200
Interface.Electric signal after the voice data receiving conversion can be transferred to loudspeaker 261 by voicefrequency circuit 260,
Voice signal output is converted to by loudspeaker 261；On the other hand, the voice signal that microphone 262 will be collected
Be converted to electric signal, after being received by voicefrequency circuit 260, be converted to voice data, then by voice data at output
After reason device 280 is processed, through RF circuit 210 being sent to such as another terminal, or voice data is exported
To memory 220 to process further.
WiFi belongs to short range wireless transmission technology, and terminal 200 can help user by WiFi module 270
Send and receive e-mail, browse webpage and access streaming video etc., it has provided the user wireless broadband interconnection
Net accesses.Although Fig. 2 shows WiFi module 270, but it is understood that, it is simultaneously not belonging to terminal
200 must be configured into, can omit completely as needed in the scope not changing disclosed essence.
Processor 280 is the control centre of terminal 200, using various interfaces and the whole terminal of connection
Various pieces, by running or executing software program and/or the module being stored in memory 220, and adjust
With being stored in the data in memory 220, the various functions of execution terminal 200 and processing data, thus right
Terminal carries out integral monitoring.Optionally, processor 280 may include one or more processing units；Preferably,
Processor 280 can integrated application processor and modem processor, wherein, application processor is mainly processed
Operating system, user interface and application program etc., modem processor mainly processes radio communication.Permissible
It is understood by, above-mentioned modem processor can not also be integrated in processor 280.
Terminal 200 also includes the power supply 282 (such as battery) powered to all parts it is preferred that power supply can
With logically contiguous with processor 280 by power-supply management system, thus management is realized by power-supply management system
The functions such as charging, electric discharge and power managed.
Camera 290 general by camera lens, imageing sensor, interface, digital signal processor, CPU, aobvious
Display screen curtain etc. forms.Wherein, camera lens is fixed on the top of imageing sensor, can manually adjust camera lens
To change focusing；Imageing sensor is equivalent to " film " of traditional camera, is the heart of camera collection image；
Interface is used for camera to utilize winding displacement, board to board connector, spring connected mode to be connected with terminal mainboard,
The image of collection is sent to described memory 220；Digital signal processor passes through the figure to collection for the mathematical operation
As being processed, the analog image of collection is converted to digital picture and memory 220 is sent to by interface.
Although not shown, terminal 200 can also include bluetooth module etc., will not be described here.
Terminal 200, except including one or more processor 280, also includes memory, and one or
The multiple module of person, one or more module is stored in memory, and be configured to by one or
Multiple computing devices.
Terminal 200 at least can be implemented as the mobile terminal 1 30 in implementation environment shown in above-mentioned Fig. 1.Work as terminal
When comprising camera 290 in 200, terminal 200 is also implemented as the bat in implementation environment shown in above-mentioned Fig. 1
Take the photograph terminal 110.
Server architecture
Refer to Fig. 3, the structural representation of the server of one embodiment of the invention offer is provided.Described
Server 300 includes CPU (CPU) 301, includes random access memory (RAM) 302
With the system storage 304 of read-only storage (ROM) 303, and connection system memory 304 and central authorities
The system bus 305 of processing unit 301.Described server 300 also includes helping each device in computer
Between transmission information basic input/output (I/O system) 306, and for storage program area 313,
Application program 312 and the mass-memory unit 307 of other program modules 315.
Described basic input/output 306 includes for the display 308 of display information with for user
The input equipment 309 of such as mouse, keyboard etc of input information.Wherein said display 308 and input set
Standby 309 are all connected to CPU by being connected to the IOC 310 of system bus 305
301.Described basic input/output 306 can also include IOC 310 for receive and
Process the input from multiple other equipments such as keyboard, mouse or electronic touch pens.Similarly, input is defeated
Go out controller 310 and also provide output to display screen, printer or other kinds of output equipment.
Described mass-memory unit 307 is by the bulk memory controller that is connected to system bus 305 (not
Illustrate) it is connected to CPU 301.Described mass-memory unit 307 and its associated computer
Computer-readable recording medium provides non-volatile memories for server 300.That is, described mass-memory unit 307
The computer-readable medium (not shown) of such as hard disk or CD-ROM drive etc can be included.
Without loss of generality, described computer-readable medium can include computer-readable storage medium and communication media.
Computer-readable storage medium include for storage such as computer-readable instruction, data structure, program module or
Volatibility that any method or technique of the information such as other data is realized and non-volatile, removable and not removable
Dynamic medium.Computer-readable storage medium include RAM, ROM, EPROM, EEPROM, flash memory or other
Its technology of solid-state storage, CD-ROM, DVD or other optical storage, cassette, tape, disk storage
Or other magnetic storage apparatus.Certainly, skilled person will appreciate that described computer-readable storage medium does not limit to
In above-mentioned several.Above-mentioned system storage 304 and mass-memory unit 307 may be collectively referred to as memory.
According to various embodiments of the present invention, described server 300 can also pass through the networks such as internet
The remote computer being connected on network runs.Namely server 300 can be total by being connected to described system
NIU 311 on line 305 is connected to network 312, in other words, it is possible to use network interface list
Unit 311 is being connected to other kinds of network or remote computer system (not shown).
Described memory also includes one or more than one program, one or more than one program
It is stored in memory.
Server 300 can be implemented as the cloud server 120 in implementation environment shown in above-mentioned Fig. 1.
Refer to Fig. 4, the flow process of the recongnition of objects method of one embodiment of the invention offer is provided
Figure.This recongnition of objects method can apply in the camera terminal 110 shown in Fig. 1.This destination object
Recognition methods can include several steps as follows：
Step 401, obtaining the n image frame that camera terminal photographs, n >=1, and n is integer.
Step 402, by the image of each object comprising in this n image frame and the image pattern pre-setting
Carry out matching degree calculating, obtain the corresponding matching value of this each object.
Step 403, by this each object, corresponding matching value is higher than that the image of the object of preset value is sent to
Cloud server, is carried out higher than the image of the object of preset value to this corresponding matching value by this cloud server
Image recognition, to detect that whether this corresponding matching value is higher than the object of preset value as destination object.
In sum, recongnition of objects method provided in an embodiment of the present invention, is clapped by obtaining camera terminal
The n image frame taken the photograph, by the image of each object comprising in this n image frame and the figure pre-setting
Decent carries out matching degree calculating, obtains the corresponding matching value of this each object, and by this each object,
Corresponding matching value is higher than that the image of the object of preset value is sent to cloud server, by this cloud server pair
This corresponding matching value is higher than that the image of the object of preset value carries out image recognition, to detect this corresponding coupling
Value be higher than preset value object whether be destination object, camera terminal carry out simple match filter out need into
The image of one step identification, and the image filtering out is uploaded to cloud server is identified further, due to
The speed of simple match, and the amount of images uploading is also fewer, reaches and is meeting quick identification needs
While, reduce the requirement to the network bandwidth, save the effect of network traffics.
Refer to Fig. 5, the flow process of the recongnition of objects method of one embodiment of the invention offer is provided
Figure.This recongnition of objects method can apply in the cloud server 120 shown in Fig. 1.This target pair
As recognition methods can include several steps as follows：
Step 501, receives the image that camera terminal sends, and this image is the n that the acquisition of this camera terminal photographs
Individual image frame；The image of each object comprising in this n image frame and the image pattern pre-setting are entered
Row matching degree calculates acquisition, and corresponding matching value is higher than the image of the object of preset value；N >=1, and n is
Integer.
Step 502, carries out image recognition to this image, to detect that this corresponding matching value is higher than the right of preset value
As if no for destination object.
In sum, recongnition of objects method provided in an embodiment of the present invention, is obtained by receiving camera terminal
Take the n image frame photographing, and by the image of each object comprising in this n image frame with set in advance
The image pattern put carries out matching degree and calculates acquisition, and corresponding matching value is higher than the image of the object of preset value,
Image recognition is carried out to this image, to detect that whether this corresponding matching value is higher than the object of preset value as target
Object, carry out simple match in camera terminal and filter out the image needing to identify further, and will filter out
Image is uploaded to cloud server and is identified further, due to the speed of simple match, and upload
Amount of images is also fewer, reaches while meeting quick identification needs, reduces the requirement to the network bandwidth,
Save the effect of network traffics.
Refer to Fig. 6, the flow process of the recongnition of objects method of one embodiment of the invention offer is provided
Figure.This recongnition of objects method can apply in the implementation environment shown in Fig. 1.This recongnition of objects
Method can include several steps as follows：
Step 601, the n image frame that camera terminal acquisition photographs, n >=1, and n is integer.
Camera terminal obtains the interior shooting of at the appointed time section, comprises the video segment of at least n frame picture, and
Extract n continuous image frame in this video segment, such as, the front n in this video segment can be extracted
Individual continuous image frame, or extract rear n continuous image frame in this video segment, or extraction should
N in an intermediate position continuous image frame etc. in video segment.
Wherein, camera terminal can obtain, according to the time period, the image frame photographing.Such as, camera terminal is every
Minute obtains an image frame, when the moment point of acquisition image frame reaches every time, bat in the previous minute of acquisition
Front n image frame in the video taken the photograph；Or, shoot in the previous minute that camera terminal can also obtain
To video in last n image frame；Or, shoot in the previous minute that camera terminal can also obtain
To video in be in n image frame of middle part.Optionally, this n image frame may also mean that and determine
Discontinuous image frame in the video segment shooting in time period, such as, camera terminal can at random or press
According to predetermined sample frequency from previous minute in extract n image frame the video that photographs.
Step 602, camera terminal by the image of each object comprising in this n image frame with pre-set
Image pattern carries out matching degree calculating, obtains the corresponding matching value of this each object.
Camera terminal can obtain the characteristics of image of this each object, and this characteristics of image includes profile and profile
Interior COLOR COMPOSITION THROUGH DISTRIBUTION；The characteristics of image calculating this each image is respectively and the characteristics of image of this image pattern between
Matching value.
Wherein, this image pattern can be the corresponding image pattern of destination object, and this image pattern can only have
One sample, it is possibility to have multiple different samples.When this image pattern has multiple different sample, will
The sample that the image of each object is different from several carries out matching degree calculating respectively, and takes maximum of which
Join value as effective matching value.
Camera terminal can by the image segmentation of each object in this n image frame out, and will be partitioned into
Each image and image pattern carry out matching degree calculating respectively.In order to reduce the amount of calculation of camera terminal side,
Improve matching speed, be partitioned into the object in each image frame, after camera terminal obtains n image frame,
The COLOR COMPOSITION THROUGH DISTRIBUTION that can only extract in the profile of each object and profile is as characteristics of image and each is right
COLOR COMPOSITION THROUGH DISTRIBUTION in the profile of the COLOR COMPOSITION THROUGH DISTRIBUTION in the profile of elephant and profile and image pattern and profile is carried out
Matching degree calculates, and the matching value of acquisition is higher, illustrates that corresponding object and image pattern are more similar.
Step 603, when there is not the matching value higher than preset value in result of calculation, camera terminal continues to obtain
Next organizes n image frame.
Above-mentioned preset value can be the matching threshold being arranged by developer in advance, when an object
Join value and be more than this preset value, then illustrate that this object is likely to be destination object, can subsequently be identified, no
Then illustrate it is not necessary to identify further, this object can confirm that it is not target with destination object gap is larger
Object.Therefore, if there is not the matching value higher than preset value in the result of calculation of above-mentioned steps 602, say
Suspected target object in the video of interior shooting for the previous period in bright camera terminal, can continue to obtain
Take off one group of image frame.
Step 604, when there is the matching value higher than preset value in result of calculation, camera terminal by this each right
As in, corresponding matching value is higher than that the image of object of preset value is sent to cloud server.
When there is the matching value higher than preset value in the result of calculation of step 602, illustrate camera terminal front
It has been likely to occur destination object in the video shooting in a period of time, needed possible object is carried out further
Identification.
To cloud server send image when, can by each be higher than preset value matching value object according to
Matching value order from high to low is arranged, and corresponding matching value highest, the figure of most m objects
As being sent to cloud server.Wherein, m >=1, and n is integer.Above-mentioned preset value can be in advance by opening
One matching threshold of the personnel of sending out setting, the matching value of certain object is more than this preset value, then this object is described
It is likely to be destination object, can subsequently be identified.
Additionally, in order to control the quantity sending image, threshold value m can also be arranged, when identifying every time,
The most multidirectional cloud server sends the image of m object.When the number of objects of the matching value higher than preset value is big
When m, the image of matching value highest m object is sent to cloud server；When higher than preset value
When the number of objects of matching value is less than m, then it corresponding matching value is higher than the image of all objects of preset value
All it is sent to cloud server.
Step 605, cloud server is higher than that the image of the object of preset value carries out image to this corresponding matching value
Identification, to detect that whether this corresponding matching value is higher than the object of preset value as destination object.
Cloud server receives camera terminal transmission, and corresponding matching value is higher than each object of preset value
Image after, these images are accurately identified, such as, identify material in the image of these objects,
Whether the features such as pattern, text, judge this object as destination object.
When optional camera terminal is to cloud server transmission image, directly can also will include corresponding
The whole image frame joining the object that value is higher than preset value is sent to cloud server, by cloud server in this picture
Carry out image segmentation and accurate identification in the frame of face.
Step 606, recognition result is returned to camera terminal by cloud server.
Step 607, when this recognition result be this corresponding matching value be higher than preset value to as if destination object
When, camera terminal passes through MSN and sends reminder message to mobile terminal, and this reminder message is used for carrying
Waking up has destination object to be photographed by this camera terminal.
Cloud server returns to recognition result after camera terminal, if this recognition result shoots for camera terminal
To video or picture in comprise destination object, then can be carried with to user by MSN
Mobile terminal send reminder message, after mobile terminal receives this reminder message, issue the user with prompting.
Wherein, can be provided with the mobile terminal of camera terminal and user with a MSN, use
Family logs in this MSN by identical or different accounts in camera terminal with mobile terminal, with
When, the recipient that user arranges reminder message also in camera terminal is mobile terminal.Such as, when user exists
When passing through identical account log-in instant communication software in camera terminal and mobile terminal, can arrange reception should
The device type of reminder message is the type of mobile terminal；When user passes through in camera terminal and mobile terminal
During different account log-in instant communication software, can arrange and receive the account of this reminder message is that user is moving
The account logging in dynamic terminal.
When including target in the video that the recognition result of cloud server photographs for camera terminal or picture
During object, camera terminal sends reminder message to the server of this MSN, indicates that this carries simultaneously
The receiving device of awake message is mobile terminal, is transmitted to this reminder message by the server of MSN
Mobile terminal.
Optionally, destination object includes the destination object of two or more types, by instant messaging
Before software sends reminder message to mobile terminal, can also obtain and carry in this recognition result, this correspondence
Matching value be higher than preset value object type, and according to this corresponding matching value be higher than preset value object
Type generate this reminder message.
In embodiments of the present invention, multiple different types of destination objects can be set simultaneously, each type
Destination object can correspond to the different reminder message of generation.Camera terminal receives cloud server return
Recognition result, and recognition result be corresponding matching value be higher than preset value to as if during destination object, this knowledge
The type of the destination object identifying also can be carried in other result, that is, corresponding matching value is higher than preset value
Object type, camera terminal can generate corresponding reminder message according to the type of this object and send.
Optionally, when the recognition result that this image is carried out with image recognition is this corresponding matching value higher than default
Value to as if during destination object, cloud server sends this reminder message to mobile terminal.
Wherein, cloud server can be whole to moving by modes such as MSN, note or multimedia messages
End sends reminder message.
Such as, it is previously stored between the mark of camera terminal and the mark of mobile terminal in cloud server
Binding relationship, this mark can be account, device address and/or telephone number etc..Camera terminal in advance will be from
Oneself identification notification is higher than preset value to cloud server, cloud server identifying corresponding matching value
The mark of this binding relationship enquiry mobile terminal during to liking destination object, can be passed through, and according to this movement
The mark of terminal sends reminder message to mobile terminal, such as, when mobile terminal to be designated instant messaging soft
During the account of part, the instant communication information comprising this reminder message is sent to this account by MSN,
Or, when mobile terminal is when being designated phone number, send to this phone number and comprise this reminder message
Note or multimedia message.
This destination object includes the destination object of two or more types, carries sending to mobile terminal
Before awake message, it may also be determined that this corresponding matching value is higher than the type of the object of preset value, right according to this
The matching value answered is higher than that the type of the object of preset value generates this reminder message.
In the disclosed embodiments, this reminder message directly can also be sent to mobile terminal by cloud server,
Such as, it is previously stored with the binding relationship between camera terminal and mobile terminal in cloud server, work as detection
Go out in the image of camera terminal transmission to as if destination object after, directly determine that this corresponding matching value is higher than
The type of the object of preset value, generates corresponding reminder message according to the type and is sent to mobile terminal.
Optionally, can also be comprised this in the reminder message of above-mentioned camera terminal or cloud server transmission right
The matching value answered is higher than the image of the object of preset value, or comprises this corresponding matching value higher than preset value
The whole image frame that object is located, so that whether user's manual confirmation really photographs destination object.
A kind of possible in the disclosure is realized in scene, and above-mentioned camera terminal can be drive recorder.By
Relatively limited in the parking stall of current public place, a lot of drivers forbid having to for vehicle to be parked in roadside etc.
On the position stopped, because of no one in vehicle, penalty note is pasted by traffic police sometimes, lead to driver's damage economically
Lose.In order to avoid this situation, the image of various traffic police and police car can be prestored in drive recorder
Sample.Driving note when vehicle is parked in non-parking stall and leaves the vehicle a bit of time by driver, in vehicle
Record instrument can shoot the video of vehicle periphery；Every 1 minute, in the previous minute that parking recorder just extracts
Front n image frame in the video shooting, splits to the image of each object in this n image frame,
And the matching degree calculating between the image of this each object and image pattern (can only calculate the whole of object herein
The matching degree between COLOR COMPOSITION THROUGH DISTRIBUTION in body profile and profile), obtain matching value, when some object
Join that value is higher, illustrate this to as if dressing humanoid subject similar with traffic police it may be possible to a traffic police,
Or, this to as if application Vehicle Object similar with police car it may be possible to a police car.Now, OK
The image of this object is sent to cloud server by car recorder, and cloud server is carried out to the image of this object
Accurately identify, believed in detail by identifying the text in the material in the image of this object, pattern and pattern etc.
Cease and to determine whether this object is traffic police or police car, and return recognition result to drive recorder.Work as driving
Recorder receive this to as if the recognition result of traffic police or police car after, the type according to object generates corresponding
Reminder message, and send this reminder message to the smart mobile phone of driver, to remind user to have traffic police or police car to connect
Closely.Wherein, the message that this reminder message can be transmitted by instant communication software.
Alternatively possible in the disclosure is realized in scene, and above-mentioned camera terminal can be fixing camera,
Such scheme can be used for chasing lawless person by fixing camera.Such as, when some lawless person's quilt
During wanted circular, the image that fixing camera receives this lawless person as image pattern and stores, fixing shooting
When shooting monitor video, every 1 minute, shoot in the previous minute that fixing camera just extracts regarded head
Front n image frame in frequency, splits to the image of each object in this n image frame, and calculates
Matching degree between the image of this each object and image pattern (can only calculate the overall profile of object herein
And the matching degree between the COLOR COMPOSITION THROUGH DISTRIBUTION in profile), obtain matching value, when some object matching value relatively
Height, illustrates that the dressing of this object is similar with lawless person it may be possible to the lawless person that ordering to arrest, now,
The image of this object is sent to cloud server by fixing camera, and cloud server enters to the image of this object
Row accurately identifies, determines whether this object is lawless person by identifying the face feature of this object, works as knowledge
When not going out this to liking lawless person, send reminder message to the police nearest apart from this camera,
There is lawless person to haunt to remind, also provide the monitoring position of this fixing camera, so that police simultaneously
Carry out evacuating personnel in time and arrest.
Additionally, the camera terminal in scheme shown in the embodiment of the present invention can also be other has video or picture
The dollying head installed on the equipment of shoot function, such as aerial photography device, or moving camera etc., the present invention
Embodiment pair is not limited with the particular type of camera terminal.
In sum, recongnition of objects method provided in an embodiment of the present invention, camera terminal is clapped by acquisition
The n image frame taken the photograph, by the image of each object comprising in this n image frame and the figure pre-setting
Decent carries out matching degree calculating, obtains the corresponding matching value of this each object, and by this each object,
Corresponding matching value is higher than that the image of the object of preset value is sent to cloud server, by this cloud server pair
This corresponding matching value is higher than that the image of the object of preset value carries out image recognition, to detect this corresponding coupling
Value be higher than preset value object whether be destination object, camera terminal carry out simple match filter out need into
The image of one step identification, and the image filtering out is uploaded to cloud server is identified further, due to
The speed of simple match, and the amount of images uploading is also fewer, reaches and is meeting quick identification needs
While, reduce the requirement to the network bandwidth, save the effect of network traffics.
Following for apparatus of the present invention embodiment, can be used for executing the inventive method embodiment.For the present invention
The details not disclosed in device embodiment, refer to the inventive method embodiment.
Refer to Fig. 7, the device knot of the recongnition of objects device of one embodiment of the invention offer is provided
Composition.This recongnition of objects device can be implemented as the camera terminal 110 in implementation environment shown in Fig. 1
In whole or in part.This recongnition of objects device 700 can include：
Image frame acquisition module 701, for obtaining the n image frame that described camera terminal photographs, n >=1,
And n is integer；
Matching module 702, for by the image of each object comprising in described n image frame with pre-set
Image pattern carry out matching degree calculating, obtain the corresponding matching value of described each object；
Image sending module 703, for by described each object, corresponding matching value is higher than the right of preset value
The image of elephant is sent to cloud server, by described cloud server to described corresponding matching value higher than default
The image of the object of value carries out image recognition, with detect described corresponding matching value be higher than preset value to as if
No for destination object.
In sum, recongnition of objects device provided in an embodiment of the present invention, by obtaining the n photographing
Individual image frame, the image of each object comprising in this n image frame and the image pattern pre-setting are entered
Row matching degree calculates, and obtains the corresponding matching value of this each object, and by this each object, corresponding
The image joining the object that value is higher than preset value is sent to cloud server, corresponding to this by this cloud server
Matching value is higher than that the image of the object of preset value carries out image recognition, to detect that this corresponding matching value is higher than pre-
If whether the object of value is destination object, carry out simple match and filter out needing to identify further in camera terminal
Image, and the image filtering out be uploaded to cloud server identified further, due to simple match
Speed, and the amount of images uploading is also fewer, reach meet quick identify needs while,
Reduce the requirement to the network bandwidth, save the effect of network traffics.
Refer to Fig. 8, the device knot of the recongnition of objects device of one embodiment of the invention offer is provided
Composition.This recongnition of objects device can be implemented as the cloud server 120 in implementation environment shown in Fig. 1
All or part of.This recongnition of objects device 800 can include：
Image receiver module 801, for receiving the image of camera terminal transmission, described image is described shooting eventually
End obtains the n image frame photographing；By the image of each object comprising in described n image frame and in advance
The image pattern first arranging carries out matching degree and calculates acquisition, and corresponding matching value is higher than the object of preset value
Image, n >=1, and n are integer；
Identification module 802 is for carrying out image recognition to described image, high to detect described corresponding matching value
Whether it is destination object in the object of preset value.
In sum, recongnition of objects device provided in an embodiment of the present invention, is obtained by receiving camera terminal
Take the n image frame photographing, and by the image of each object comprising in this n image frame with set in advance
The image pattern put carries out matching degree and calculates acquisition, and corresponding matching value is higher than the image of the object of preset value,
Image recognition is carried out to this image, to detect that whether this corresponding matching value is higher than the object of preset value as target
Object, carry out simple match in camera terminal and filter out the image needing to identify further, and will filter out
Image is uploaded to cloud server and is identified further, due to the speed of simple match, and upload
Amount of images is also fewer, reaches while meeting quick identification needs, reduces the requirement to the network bandwidth,
Save the effect of network traffics.
Refer to Fig. 9, the system knot of the recongnition of objects system of one embodiment of the invention offer is provided
Composition.This recongnition of objects system can include camera terminal 110 and cloud in implementation environment shown in Fig. 1
Hold all or part of of server 120.This recongnition of objects system can include：Comprise destination object
The camera terminal of identifying device 700 and the cloud server comprising recongnition of objects device 800；
Wherein, recongnition of objects device 700 includes：
Image frame acquisition module 701, for obtaining the n image frame that described camera terminal photographs, n >=1,
And n is integer；
Matching module 702, for by the image of each object comprising in described n image frame with pre-set
Image pattern carry out matching degree calculating, obtain the corresponding matching value of described each object；
Image sending module 703, for by described each object, corresponding matching value is higher than the right of preset value
The image of elephant is sent to cloud server, by described cloud server to described corresponding matching value higher than default
The image of the object of value carries out image recognition, with detect described corresponding matching value be higher than preset value to as if
No for destination object.
Optionally, described matching module 702, including：
Feature acquiring unit 702a, for obtaining the characteristics of image of described each object, described image feature bag
Include the COLOR COMPOSITION THROUGH DISTRIBUTION in profile and profile；
Computing unit 702b, for calculate the characteristics of image of each image described respectively with described image sample
Matching value between characteristics of image.
Optionally, described image frame acquisition module 701, for obtaining described camera terminal at the appointed time in section
Shoot, comprise the video segment of at least n frame picture, front n extracted in described video segment continuous
Image frame or rear n continuous image frame.
Optionally, described device also includes：
Recognition result receiver module 704, for receiving the recognition result that described cloud server sends；
First prompting module 705, for being described corresponding matching value higher than preset value when described recognition result
During to liking destination object, reminder message is sent to mobile terminal by MSN, described prompting disappears
Cease and have destination object to be arrived by described terminal taking for reminding.
Optionally, described destination object includes the destination object of two or more types, described target
Object recognition equipment 700 also includes：
Type acquisition module 706, for passing through MSN to movement in described first prompting module 705
Before terminal sends reminder message, carry in the described recognition result of acquisition, described corresponding matching value is higher than
The type of the object of preset value；
First generation module 707, for giving birth to higher than the type of the object of preset value according to described corresponding matching value
Become described reminder message.
Wherein, recongnition of objects device 800 includes：
Image receiver module 801, for receiving the image of camera terminal transmission, described image is described shooting eventually
End obtains the n image frame photographing；By the image of each object comprising in described n image frame and in advance
The image pattern first arranging carries out matching degree and calculates acquisition, and corresponding matching value is higher than the object of preset value
Image, n >=1, and n are integer；
Identification module 802 is for carrying out image recognition to described image, high to detect described corresponding matching value
Whether it is destination object in the object of preset value.
Optionally, described device also includes：
Recognition result returns module 803, for returning to the recognition result that described image is carried out with image recognition
Described camera terminal；
Second prompting module 804, for being described correspondence when the recognition result that described image is carried out with image recognition
Matching value be higher than preset value to as if during destination object, send reminder message to mobile terminal, described carry
Awake message has destination object to be arrived by described terminal taking for prompting.
Optionally, described destination object includes the destination object of two or more types, described target
Object recognition equipment 800 also includes：
Determination type module 805, for sending reminder message in described second prompting module 804 to mobile terminal
Before, determine that described corresponding matching value is higher than the type of the object of preset value；
Second generation module 806, for giving birth to higher than the type of the object of preset value according to described corresponding matching value
Become described reminder message
In sum, recongnition of objects system provided in an embodiment of the present invention, camera terminal is clapped by acquisition
The n image frame taken the photograph, by the image of each object comprising in this n image frame and the figure pre-setting
Decent carries out matching degree calculating, obtains the corresponding matching value of this each object, and by this each object,
Corresponding matching value is higher than that the image of the object of preset value is sent to cloud server, by this cloud server pair
This corresponding matching value is higher than that the image of the object of preset value carries out image recognition, to detect this corresponding coupling
Value be higher than preset value object whether be destination object, camera terminal carry out simple match filter out need into
The image of one step identification, and the image filtering out is uploaded to cloud server is identified further, due to
The speed of simple match, and the amount of images uploading is also fewer, reaches and is meeting quick identification needs
While, reduce the requirement to the network bandwidth, save the effect of network traffics.
It should be noted that：The recongnition of objects device that above-described embodiment provides is carrying out recongnition of objects
When, only it is illustrated with the division of above-mentioned each functional module, in practical application, can be as desired
Above-mentioned functions distribution is completed by different functional modules, the internal structure of device will be divided into different work(
Energy module, to complete all or part of function described above.In addition, the target that above-described embodiment provides
Object recognition equipment and recongnition of objects embodiment of the method belong to same design, and it implements process and refers to
Embodiment of the method, repeats no more here.
It should be appreciated that it is used in the present context, unless exception, odd number clearly supported in context
Form " one " (" a ", " an ", " the ") is intended to also include plural form.It is to be further understood that at this
Used in literary composition "and/or" refer to one or project that more than one is listed in association arbitrarily and institute
It is possible to combine.
The embodiments of the present invention are for illustration only, do not represent the quality of embodiment.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can be passed through
Hardware come to complete it is also possible to instructed by program correlation hardware complete, described program can be stored in
In a kind of computer-readable recording medium, storage medium mentioned above can be read-only storage, disk or
CD etc..
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all the present invention's
Within spirit and principle, any modification, equivalent substitution and improvement made etc., should be included in the present invention's
Within protection domain.
Claims (18)
1. a kind of recongnition of objects method is it is characterised in that be used in camera terminal, methods described includes：
Obtaining the n image frame that described camera terminal photographs, n >=1, and n is integer；
The image of each object comprising in described n image frame and the image pattern pre-setting are carried out
Degree of joining calculates, and obtains the corresponding matching value of described each object；
By in described each object, corresponding matching value is higher than that the image of the object of preset value is sent to high in the clouds clothes
Business device, the image by described cloud server to described corresponding matching value being higher than the object of preset value carries out figure
As identification, to detect that whether described corresponding matching value is higher than the object of preset value as destination object.
2. method according to claim 1 is it is characterised in that described will wrap in described n image frame
The image of each object containing carries out matching degree calculating with the image pattern pre-setting, including：
Obtain the characteristics of image of described each object, described image feature includes the color in profile and profile
Distribution；
Calculate characteristics of image the mating between the characteristics of image of described image sample respectively of each image described
Value.
3. method according to claim 1 is it is characterised in that the described camera terminal of described acquisition shoots
The n image frame arriving, including：
Obtain what described camera terminal at the appointed time shot in section, comprise the video segment of at least n frame picture,
Extract front n continuous image frame in described video segment or rear n continuous image frame.
4. according to the arbitrary described method of claims 1 to 3 it is characterised in that methods described also includes：
Receive the recognition result that described cloud server sends；
When described recognition result be described corresponding matching value be higher than preset value to as if during destination object, lead to
Cross MSN and send reminder message to mobile terminal, described reminder message has destination object for prompting
Arrived by described terminal taking.
5. method according to claim 4 it is characterised in that described destination object include two or
The destination object of two or more type, described by MSN to mobile terminal send reminder message it
Before, also include：
Obtain and carry in described recognition result, described corresponding matching value is higher than the type of the object of preset value；
The type according to described corresponding matching value being higher than the object of preset value generates described reminder message.
6. a kind of recongnition of objects method is it is characterised in that be used in cloud server, methods described bag
Include：
Receive the image that camera terminal sends, described image is that described camera terminal obtains the n picture photographing
Face frame；The image of each object comprising in described n image frame and the image pattern pre-setting are carried out
Matching degree calculates acquisition, and corresponding matching value is higher than the image of the object of preset value, n >=1, and n is whole
Number；
Image recognition is carried out to described image, with detect described corresponding matching value be higher than preset value to as if
No for destination object.
7. method according to claim 6 is it is characterised in that methods described also includes：
The recognition result that described image is carried out with image recognition is returned to described camera terminal.
8. method according to claim 6 is it is characterised in that methods described also includes：
When the recognition result that described image is carried out with image recognition is described corresponding matching value higher than preset value
During to liking destination object, send reminder message to mobile terminal, described reminder message is used for reminding described shifting
The corresponding user of dynamic terminal has destination object to be arrived by described terminal taking.
9. method according to claim 8 it is characterised in that described destination object include two or
The destination object of two or more type, before the described transmission reminder message to mobile terminal, also includes：
Determine that described corresponding matching value is higher than the type of the object of preset value；
The type according to described corresponding matching value being higher than the object of preset value generates described reminder message.
10. a kind of recongnition of objects device is it is characterised in that be used in camera terminal, described device bag
Include：
Image frame acquisition module, for obtaining the n image frame that described camera terminal photographs, n >=1, and n
For integer；
Matching module, for by the image of each object comprising in described n image frame with pre-set
Image pattern carries out matching degree calculating, obtains the corresponding matching value of described each object；
Image sending module, for by described each object, corresponding matching value is higher than the object of preset value
Image be sent to cloud server, by described cloud server to described corresponding matching value be higher than preset value
The image of object carry out image recognition, with detect described corresponding matching value be higher than the object of preset value whether
For destination object.
11. devices according to claim 10 it is characterised in that described matching module, including：
Feature acquiring unit, for obtaining the characteristics of image of described each object, described image feature includes taking turns
COLOR COMPOSITION THROUGH DISTRIBUTION in exterior feature and profile；
Computing unit, for calculating the characteristics of image image with described image sample respectively of each image described
Matching value between feature.
12. devices according to claim 10, it is characterised in that described image frame acquisition module, are used
Shoot in the described camera terminal of acquisition at the appointed time section, comprise the video segment of at least n frame picture,
Extract front n continuous image frame in described video segment or rear n continuous image frame.
13. according to the arbitrary described device of claim 10 to 12 it is characterised in that described device is also wrapped
Include：
Recognition result receiver module, for receiving the recognition result that described cloud server sends；
First prompting module, for being that described corresponding matching value is right higher than preset value when described recognition result
As if during destination object, reminder message, described reminder message are sent to mobile terminal by MSN
Destination object is had to be arrived by described terminal taking for reminding.
14. devices according to claim 13 it is characterised in that described destination object include two or
The destination object of person's two or more type, described device also includes：
Type acquisition module, for being sent out to mobile terminal by MSN in described first prompting module
Before sending reminder message, carry in the described recognition result of acquisition, described corresponding matching value is higher than preset value
Object type；
First generation module, for generating higher than the type of the object of preset value according to described corresponding matching value
Described reminder message.
A kind of 15. recongnition of objects devices are it is characterised in that be used in cloud server, described device
Including：
Image receiver module, for receiving the image of camera terminal transmission, described image is described camera terminal
Obtain the n image frame photographing；By the image of each object comprising in described n image frame with advance
The image pattern of setting carries out matching degree and calculates acquisition, and corresponding matching value is higher than the figure of the object of preset value
Picture, n >=1, and n are integer；
Identification module, for carrying out image recognition to described image, to detect that described corresponding matching value is higher than
Whether the object of preset value is destination object.
16. devices according to claim 15 are it is characterised in that described device also includes：
Recognition result returns module, for the recognition result that described image is carried out with image recognition is returned to institute
State camera terminal.
17. devices according to claim 15 are it is characterised in that described device also includes：
Second prompting module, for being described corresponding when the recognition result that described image is carried out with image recognition
Matching value be higher than preset value to as if during destination object, send reminder message, described prompting to mobile terminal
Message has destination object to be arrived by described terminal taking for prompting.
18. devices according to claim 17 it is characterised in that described destination object include two or
The destination object of person's two or more type, described device also includes：
Determination type module, before sending reminder message in described second prompting module to mobile terminal,
Determine that described corresponding matching value is higher than the type of the object of preset value；
Second generation module, for generating higher than the type of the object of preset value according to described corresponding matching value
Described reminder message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510464842.7A CN106407984B (en) | 2015-07-31 | 2015-07-31 | Target object identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510464842.7A CN106407984B (en) | 2015-07-31 | 2015-07-31 | Target object identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106407984A true CN106407984A (en) | 2017-02-15 |
| CN106407984B CN106407984B (en) | 2020-09-11 |
Family
ID=58007288
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510464842.7A Active CN106407984B (en) | 2015-07-31 | 2015-07-31 | Target object identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106407984B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107135254A (en) * | 2017-04-25 | 2017-09-05 | 成都凌点科技有限公司 | Utilize drive recorder safety defense monitoring system |
| CN107566654A (en) * | 2017-09-27 | 2018-01-09 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN107832799A (en) * | 2017-11-20 | 2018-03-23 | 北京奇虎科技有限公司 | Object identifying method and device, computing device based on camera scene |
| CN107991712A (en) * | 2017-10-25 | 2018-05-04 | 深圳市日联科技有限公司 | A kind of people based on Internet of Things, car, the separated nanometer wave detecting system of cabinet |
| CN109376660A (en) * | 2018-10-26 | 2019-02-22 | 天宇经纬（北京）科技有限公司 | A kind of target monitoring method, apparatus and system |
| CN109685088A (en) * | 2017-10-18 | 2019-04-26 | 上海仪电（集团）有限公司中央研究院 | Narrow band communication intelligent image analysis system based on cloud separation convolutional neural networks |
| CN110149551A (en) * | 2018-11-06 | 2019-08-20 | 腾讯科技（深圳）有限公司 | Media file playing method and device, storage medium and electronic device |
| CN110427824A (en) * | 2019-06-28 | 2019-11-08 | 特斯联（北京）科技有限公司 | A kind of the security protection automatic test approach and system of artificial intelligence virtual scene |
| CN110849855A (en) * | 2019-12-02 | 2020-02-28 | 杭州特隆基因技术有限公司 | Artificial intelligence-based living bacterium quantitative detection method |
| WO2020042637A1 (en) * | 2018-08-27 | 2020-03-05 | 深圳前海达闼云端智能科技有限公司 | Supervision method, apparatus and system, cloud server and storage medium |
| CN110933362A (en) * | 2018-09-20 | 2020-03-27 | 中移物联网有限公司 | Picture processing method and device and computer readable storage medium |
| CN111914692A (en) * | 2017-04-28 | 2020-11-10 | 创新先进技术有限公司 | Vehicle loss assessment image acquisition method and device |
| CN112101304A (en) * | 2020-11-06 | 2020-12-18 | 腾讯科技（深圳）有限公司 | Data processing method, device, storage medium and equipment |
| CN112422601A (en) * | 2019-08-23 | 2021-02-26 | 阿里巴巴集团控股有限公司 | Data processing method and device and electronic equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101375608A (en) * | 2006-02-07 | 2009-02-25 | 高通股份有限公司 | Intra-mode region-of-interest video object segmentation |
| CN102360421A (en) * | 2011-10-19 | 2012-02-22 | 苏州大学 | Face identification method and system based on video streaming |
| CN103369049A (en) * | 2013-07-22 | 2013-10-23 | 王雁林 | Mobile terminal and server interactive method and system thereof |
| CN103577802A (en) * | 2012-07-19 | 2014-02-12 | 松下电器产业株式会社 | Image transmission device, image transmission method, image transmission program, image recognition and authentication system, and image reception device |
| CN103632132A (en) * | 2012-12-11 | 2014-03-12 | 广西工学院 | Face detection and recognition method based on skin color segmentation and template matching |
| US20140099028A1 (en) * | 2012-10-09 | 2014-04-10 | Samsung Electronics Co., Ltd. | System and method for video recognition based on visual image matching |
| CN104050450A (en) * | 2014-06-16 | 2014-09-17 | 西安通瑞新材料开发有限公司 | Vehicle license plate recognition method based on video |
| CN104066009A (en) * | 2013-10-31 | 2014-09-24 | 腾讯科技（深圳）有限公司 | Method, device, terminal, server and system for program identification |
| WO2015005728A1 (en) * | 2013-07-12 | 2015-01-15 | 삼성전자 주식회사 | Image display method and device |
-
2015
- 2015-07-31 CN CN201510464842.7A patent/CN106407984B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101375608A (en) * | 2006-02-07 | 2009-02-25 | 高通股份有限公司 | Intra-mode region-of-interest video object segmentation |
| CN102360421A (en) * | 2011-10-19 | 2012-02-22 | 苏州大学 | Face identification method and system based on video streaming |
| CN103577802A (en) * | 2012-07-19 | 2014-02-12 | 松下电器产业株式会社 | Image transmission device, image transmission method, image transmission program, image recognition and authentication system, and image reception device |
| US20140099028A1 (en) * | 2012-10-09 | 2014-04-10 | Samsung Electronics Co., Ltd. | System and method for video recognition based on visual image matching |
| CN103632132A (en) * | 2012-12-11 | 2014-03-12 | 广西工学院 | Face detection and recognition method based on skin color segmentation and template matching |
| WO2015005728A1 (en) * | 2013-07-12 | 2015-01-15 | 삼성전자 주식회사 | Image display method and device |
| CN103369049A (en) * | 2013-07-22 | 2013-10-23 | 王雁林 | Mobile terminal and server interactive method and system thereof |
| CN104066009A (en) * | 2013-10-31 | 2014-09-24 | 腾讯科技（深圳）有限公司 | Method, device, terminal, server and system for program identification |
| CN104050450A (en) * | 2014-06-16 | 2014-09-17 | 西安通瑞新材料开发有限公司 | Vehicle license plate recognition method based on video |
Non-Patent Citations (2)
| Title |
|---|
| TAO CHEN ET AL.: "Context-Aware Discriminative Vocabulary Learning for Mobile Landmark Recognition", 《 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 》 * |
| 刘秀朋: "轮廓曲线的形状描述与匹配算法研究", 《万方学位论文数据库》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107135254A (en) * | 2017-04-25 | 2017-09-05 | 成都凌点科技有限公司 | Utilize drive recorder safety defense monitoring system |
| CN111914692B (en) * | 2017-04-28 | 2023-07-14 | 创新先进技术有限公司 | Method and device for acquiring damage assessment image of vehicle |
| CN111914692A (en) * | 2017-04-28 | 2020-11-10 | 创新先进技术有限公司 | Vehicle loss assessment image acquisition method and device |
| CN107566654A (en) * | 2017-09-27 | 2018-01-09 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN107566654B (en) * | 2017-09-27 | 2020-03-17 | Oppo广东移动通信有限公司 | Unlocking control method and related product |
| CN109685088A (en) * | 2017-10-18 | 2019-04-26 | 上海仪电（集团）有限公司中央研究院 | Narrow band communication intelligent image analysis system based on cloud separation convolutional neural networks |
| CN107991712A (en) * | 2017-10-25 | 2018-05-04 | 深圳市日联科技有限公司 | A kind of people based on Internet of Things, car, the separated nanometer wave detecting system of cabinet |
| CN107991712B (en) * | 2017-10-25 | 2024-03-19 | 深圳市日联科技有限公司 | Nanometer wave detecting system based on separation of people, vehicles and cabinets of Internet of things |
| CN107832799A (en) * | 2017-11-20 | 2018-03-23 | 北京奇虎科技有限公司 | Object identifying method and device, computing device based on camera scene |
| WO2020042637A1 (en) * | 2018-08-27 | 2020-03-05 | 深圳前海达闼云端智能科技有限公司 | Supervision method, apparatus and system, cloud server and storage medium |
| CN110933362A (en) * | 2018-09-20 | 2020-03-27 | 中移物联网有限公司 | Picture processing method and device and computer readable storage medium |
| CN109376660A (en) * | 2018-10-26 | 2019-02-22 | 天宇经纬（北京）科技有限公司 | A kind of target monitoring method, apparatus and system |
| CN110149551B (en) * | 2018-11-06 | 2022-02-22 | 腾讯科技（深圳）有限公司 | Media file playing method and device, storage medium and electronic device |
| CN110149551A (en) * | 2018-11-06 | 2019-08-20 | 腾讯科技（深圳）有限公司 | Media file playing method and device, storage medium and electronic device |
| CN110427824A (en) * | 2019-06-28 | 2019-11-08 | 特斯联（北京）科技有限公司 | A kind of the security protection automatic test approach and system of artificial intelligence virtual scene |
| CN112422601A (en) * | 2019-08-23 | 2021-02-26 | 阿里巴巴集团控股有限公司 | Data processing method and device and electronic equipment |
| CN112422601B (en) * | 2019-08-23 | 2022-06-10 | 阿里巴巴集团控股有限公司 | Data processing method and device and electronic equipment |
| CN110849855A (en) * | 2019-12-02 | 2020-02-28 | 杭州特隆基因技术有限公司 | Artificial intelligence-based living bacterium quantitative detection method |
| CN112101304A (en) * | 2020-11-06 | 2020-12-18 | 腾讯科技（深圳）有限公司 | Data processing method, device, storage medium and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106407984B (en) | 2020-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106407984A (en) | Target object recognition method and device | |
| WO2021115007A1 (en) | Network switching method and electronic device | |
| CN106937039B (en) | Imaging method based on double cameras, mobile terminal and storage medium | |
| CN110381282A (en) | A kind of display methods and relevant apparatus of the video calling applied to electronic equipment | |
| CN106412681A (en) | Bullet screen video live broadcasting method and device | |
| CN109863742A (en) | Image processing method and terminal device | |
| CN107659758A (en) | Periscopic filming apparatus and mobile terminal | |
| CN110401767B (en) | Information processing method and apparatus | |
| WO2019129020A1 (en) | Automatic focusing method of camera, storage device and mobile terminal | |
| WO2018228241A1 (en) | Image selection method and related product | |
| CN108307106B (en) | Image processing method and device and mobile terminal | |
| CN114710585A (en) | Photographing method and terminal | |
| CN107959795A (en) | A kind of information collecting method, equipment and computer-readable recording medium | |
| CN109947248A (en) | Vibration control method, mobile terminal and computer readable storage medium | |
| CN107357500A (en) | A kind of picture-adjusting method, terminal and storage medium | |
| CN108184051A (en) | A kind of main body image pickup method, equipment and computer readable storage medium | |
| US11997158B2 (en) | Data sharing method, apparatus, and system, and electronic device | |
| CN109889695A (en) | A kind of image-region determines method, terminal and computer readable storage medium | |
| CN108076213A (en) | A kind of terminal based reminding method, terminal and computer readable storage medium | |
| CN105120158B (en) | The image pickup method and device of mobile terminal | |
| CN109075856A (en) | flight path configuration method and device | |
| WO2022100219A1 (en) | Data transfer method and related device | |
| CN108243489B (en) | Photographing control method and mobile terminal | |
| CN110163036B (en) | Image recognition method and device | |
| CN109510941A (en) | A kind of shooting processing method, equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |