CN113537087A - Intelligent traffic information processing method and device and server - Google Patents
Intelligent traffic information processing method and device and server Download PDFInfo
- Publication number
- CN113537087A CN113537087A CN202110819455.6A CN202110819455A CN113537087A CN 113537087 A CN113537087 A CN 113537087A CN 202110819455 A CN202110819455 A CN 202110819455A CN 113537087 A CN113537087 A CN 113537087A
- Authority
- CN
- China
- Prior art keywords
- image
- matched
- transmission image
- information processing
- traffic information
- 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.)
- Withdrawn
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 132
- 238000003672 processing method Methods 0.000 title claims abstract description 33
- 230000005540 biological transmission Effects 0.000 claims abstract description 354
- 238000012545 processing Methods 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 24
- 230000006399 behavior Effects 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 14
- 238000005516 engineering process Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 6
- 239000013598 vector Substances 0.000 description 87
- 230000002452 interceptive effect Effects 0.000 description 30
- 230000004927 fusion Effects 0.000 description 13
- 238000011176 pooling Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000007499 fusion processing Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The application provides an intelligent traffic information processing method, an intelligent traffic information processing device and a server, and relates to the technical field of traffic monitoring. In the method, firstly, an image recognition result between an online transmission image to be matched and a target reference image is obtained, wherein the image recognition result is used for representing whether the online transmission image to be matched is matched with the target reference image or not, and representing that a traffic violation exists in a target traffic area during matching; secondly, determining whether an online transmission image to be matched needs to be sent to a traffic information processing platform or not based on an image identification result; and then, if the on-line transmission image to be matched is determined to be required to be sent to the traffic information processing platform, the on-line transmission image to be matched is sent to the traffic information processing platform for violation processing based on the on-line transmission image to be matched. Based on the method, the problem of poor monitoring effect in the existing traffic monitoring technology can be solved.
Description
Technical Field
The application relates to the technical field of traffic monitoring, in particular to an intelligent traffic information processing method, an intelligent traffic information processing device and a server.
Background
With the popularization of automobiles, the occurrence frequency of traffic accidents is gradually increased. Among them, the occurrence of traffic accidents mainly lies in traffic violations, so that the number of traffic violations is large. Therefore, in order to effectively and timely perform online processing on the traffic violation, the traffic violation needs to be accurately monitored. However, the inventors have found that the conventional traffic monitoring technology has a problem of poor monitoring effect.
Disclosure of Invention
In view of the above, an objective of the present application is to provide an intelligent traffic information processing method, apparatus and server to solve the problem of poor monitoring effect in the existing traffic monitoring technology.
In order to achieve the above purpose, the embodiment of the present application adopts the following technical solutions:
a smart traffic information processing method includes:
acquiring an image recognition result between an online transmission image to be matched and a target reference image, wherein the online transmission image to be matched is obtained based on image acquisition of a target traffic area, and the image recognition result is used for representing whether the online transmission image to be matched is matched with the target reference image or not and representing that traffic violation behaviors exist in the target traffic area during matching;
determining whether the online transmission image to be matched needs to be sent to a traffic information processing platform or not based on the image recognition result, wherein if the image recognition result is that the online transmission image to be matched is matched with the target reference image, the online transmission image to be matched needs to be sent to the traffic information processing platform;
and if the online transmission image to be matched needs to be sent to a traffic information processing platform, sending the online transmission image to be matched to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the online transmission image to be matched.
In a possible embodiment, in the above intelligent traffic information processing method, after the step of sending the online transmission image to be matched to the traffic information processing platform is performed, the intelligent traffic information processing method further includes:
judging whether a violation processing result fed back by the traffic information processing platform based on the online transmission image to be matched is received;
if the violation processing result fed back by the traffic information processing platform is received, executing a preset operation based on the violation processing result, wherein the preset operation comprises the following steps:
if the violation processing result indicates that the traffic violation behavior exists in the target traffic area, the online transmission image to be matched is used as a new target reference image, wherein the step of using the online transmission image to be matched as the new target reference image comprises the following steps of:
replacing the target reference image with the online transmission image to be matched; or
And keeping the target reference image, and simultaneously taking the online transmission image to be matched as the target reference image so as to increase the number of the target reference images.
In a possible embodiment, in the intelligent traffic information processing method, the intelligent traffic information processing method further includes:
if the online transmission image to be matched does not need to be sent to the traffic information processing platform, the online transmission image to be matched is reserved, and the online transmission image to be matched is used as a historical transmission image to be stored;
counting the number of the currently stored historical transmission images to obtain a first number;
judging whether the first quantity is larger than a predetermined target quantity threshold value, wherein the target quantity threshold value is generated based on the threshold value configuration operation of a server executing the intelligent traffic information processing method in response to a corresponding management user;
and if the first number is larger than the target number threshold, sending the currently stored historical transmission images as a historical image set to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the historical transmission images included in the historical image set so as to determine whether traffic violation behaviors exist in each historical transmission image.
In a possible embodiment, in the intelligent traffic information processing method, if the first number is greater than the target number threshold, the step of sending the currently stored historical transmission image as a historical image set to the traffic information processing platform includes:
if the first number is larger than the target number threshold value, screening the currently stored historical transmission image to obtain at least one target historical transmission image;
and sending the at least one target historical transmission image as a historical image set to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the target historical transmission images so as to determine whether traffic violation behaviors exist in each target historical transmission image.
In a possible embodiment, in the intelligent traffic information processing method, if the first number is greater than the target number threshold, the step of performing a filtering process on the currently stored historical transmission image to obtain at least one target historical transmission image includes:
if the first number is larger than the target number threshold value, calculating the similarity between each history transmission image and each other history transmission image in the current saved history transmission images;
and screening the currently stored historical transmission images based on the similarity between the historical transmission images to obtain at least one target historical transmission image.
In a possible embodiment, in the intelligent traffic information processing method, the step of performing a filtering process on the currently stored historical transmission images based on the similarity between the historical transmission images to obtain at least one target historical transmission image includes:
calculating the mean value of the similarity between the historical transmission image and each other historical transmission image aiming at each historical transmission image in the currently stored historical transmission images to obtain the mean value of the similarity corresponding to the historical transmission image;
selecting at least one candidate historical transmission image from the currently stored historical transmission images based on the magnitude relation between the similarity mean values;
based on the similarity between the historical transmission images, taking each candidate historical transmission image as a clustering center, and clustering the currently stored historical transmission images to obtain at least one corresponding historical transmission image cluster;
and selecting at least one historical transmission image from each historical transmission image cluster as a target historical transmission image to obtain at least one target historical transmission image.
In a possible embodiment, in the intelligent traffic information processing method, the step of selecting at least one candidate historical transmission image from currently stored historical transmission images based on a magnitude relation between the similarity averages includes:
calculating an average value among the similarity mean values, and taking each similarity mean value smaller than the average value as a target similarity mean value to obtain at least one target similarity mean value;
and determining at least one historical transmission image corresponding to the at least one target similarity mean value as a candidate historical transmission image.
In a possible embodiment, in the above intelligent traffic information processing method, the step of selecting at least one history transmission image as a target history transmission image in each history transmission image cluster to obtain at least one target history transmission image includes:
determining two history transmission images with the minimum similarity in the history transmission image cluster aiming at each history transmission image cluster with the number of the included history transmission images larger than the second number;
determining two history transmission images with the minimum similarity in each history transmission image cluster as target history transmission images;
and for each history transmission image cluster of which the number of the included history transmission images is less than or equal to the second number, determining the history transmission image with the largest similarity mean value in the history transmission image cluster, and determining the history transmission image as the target history transmission image.
The application also provides an intelligent traffic information processing device, including:
the image identification result acquisition module is used for acquiring an image identification result between an online transmission image to be matched and a target reference image, wherein the online transmission image to be matched is obtained based on image acquisition of a target traffic area, and the image identification result is used for representing whether the online transmission image to be matched is matched with the target reference image or not and representing that traffic violation behaviors exist in the target traffic area during matching;
the image sending determination module is used for determining whether the online transmission image to be matched needs to be sent to a traffic information processing platform or not based on the image identification result, wherein if the image identification result is that the online transmission image to be matched is matched with the target reference image, the online transmission image to be matched needs to be sent to the traffic information processing platform;
and the image sending module is used for sending the online transmission image to be matched to a traffic information processing platform when the online transmission image to be matched is determined to be needed to be sent to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the online transmission image to be matched.
The present application further provides a server configured to:
acquiring an image recognition result between an online transmission image to be matched and a target reference image, wherein the online transmission image to be matched is obtained based on image acquisition of a target traffic area, and the image recognition result is used for representing whether the online transmission image to be matched is matched with the target reference image or not and representing that traffic violation behaviors exist in the target traffic area during matching;
determining whether the online transmission image to be matched needs to be sent to a traffic information processing platform or not based on the image recognition result, wherein if the image recognition result is that the online transmission image to be matched is matched with the target reference image, the online transmission image to be matched needs to be sent to the traffic information processing platform;
and if the online transmission image to be matched needs to be sent to a traffic information processing platform, sending the online transmission image to be matched to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the online transmission image to be matched.
According to the intelligent traffic information processing method, the intelligent traffic information processing device and the intelligent traffic information processing server, before the online transmission image to be matched is sent to the traffic information processing platform for violation processing, whether traffic violation behaviors exist is determined based on the image recognition result between the online transmission image to be matched and the target reference image, and after the traffic violation behaviors exist, the online transmission image to be matched is sent to the traffic information processing platform for violation processing. Based on this, compared with the conventional technical scheme that the online transmission image to be matched is directly sent to the traffic information processing platform, the technical scheme provided by the application can enable the traffic information processing platform to carry out violation processing more accurately and effectively, so that the problem of poor monitoring effect existing in the existing traffic monitoring technology is improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 is a block diagram of a server according to an embodiment of the present disclosure.
Fig. 2 is a flowchart illustrating steps included in the intelligent traffic information processing method according to an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
As shown in fig. 1, an embodiment of the present application provides a server. Wherein the server may include a memory and a processor.
In detail, the memory and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, they may be electrically connected to each other via one or more communication buses or signal lines. The memory can have stored therein at least one software function (computer program) which can be present in the form of software or firmware. The processor may be configured to execute the executable computer program stored in the memory, so as to implement the intelligent traffic information processing method provided in the embodiments (described later) of the present application.
Wherein the server is operable to:
acquiring an image recognition result between an online transmission image to be matched and a target reference image, wherein the online transmission image to be matched is obtained based on image acquisition of a target traffic area, and the image recognition result is used for representing whether the online transmission image to be matched is matched with the target reference image or not and representing that traffic violation behaviors exist in the target traffic area during matching; determining whether the online transmission image to be matched needs to be sent to a traffic information processing platform or not based on the image recognition result, wherein if the image recognition result is that the online transmission image to be matched is matched with the target reference image, the online transmission image to be matched needs to be sent to the traffic information processing platform; and if the online transmission image to be matched needs to be sent to a traffic information processing platform, sending the online transmission image to be matched to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the online transmission image to be matched.
Alternatively, the Memory may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), a System on Chip (SoC), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
Also, the structure shown in fig. 1 is only an illustration, and the server may further include more or less components than those shown in fig. 1, or have a different configuration from that shown in fig. 1, for example, may include a communication unit for information interaction with other devices.
With reference to fig. 2, an embodiment of the present application further provides an intelligent traffic information processing method, which can be applied to the server. The method steps defined by the flow related to the intelligent traffic information processing method can be realized by the server.
The specific process shown in FIG. 2 will be described in detail below.
Step S110, obtaining an image recognition result between the online transmission image to be matched and the target reference image.
In this embodiment, the server may first obtain an image recognition result between the online transmission image to be matched and the target reference image.
The online transmission image to be matched is obtained by carrying out image acquisition on a target traffic area, and the image identification result is used for representing whether the online transmission image to be matched is matched with the target reference image or not and representing that traffic violation behaviors exist in the target traffic area during matching.
And step S120, determining whether the online transmission image to be matched needs to be sent to a traffic information processing platform or not based on the image identification result.
In this embodiment, after the image recognition result is obtained based on step S110, the server may determine whether the online transmission image to be matched needs to be sent to a traffic information processing platform based on the image recognition result.
And if the image recognition result is that the online transmission image to be matched is matched with the target reference image, determining that the online transmission image to be matched needs to be sent to the traffic information processing platform. If it is determined that the online transmission image to be matched needs to be sent to the traffic information processing platform, step S130 is executed.
And step S130, sending the online transmission image to be matched to a traffic information processing platform.
In this embodiment, after determining that the to-be-matched online transmission image needs to be sent to the traffic information processing platform based on step S120, the server may send the to-be-matched online transmission image to the traffic information processing platform. And the traffic information processing platform is used for carrying out violation processing on the basis of the online transmission image to be matched.
Based on the method, before the online transmission image to be matched is sent to the traffic information processing platform for violation processing, whether traffic violation behaviors exist is determined based on the image recognition result between the online transmission image to be matched and the target reference image, and after the traffic violation behaviors are determined to exist, the online transmission image to be matched is sent to the traffic information processing platform for violation processing. Based on this, compared with the conventional technical scheme that the online transmission image to be matched is directly sent to the traffic information processing platform, the technical scheme provided by the application can enable the traffic information processing platform to carry out violation processing more accurately and effectively, so that the problem of poor monitoring effect existing in the existing traffic monitoring technology is improved.
It is understood that, in an alternative example, the image recognition result may be obtained based on the following steps (e.g., step S101, step S102, step S103, and step S104 described later) when step S110 is executed.
And step S101, acquiring an online transmission image to be matched and a target reference image.
In this embodiment, the server may first obtain an online transmission image to be matched, and obtain a predetermined target reference image.
Step S102, respectively extracting the global image feature vector and the local image feature vector of the online transmission image to be matched, the global image feature vector and the local image feature vector of the target reference image, and determining the interactive image feature vector between the online transmission image to be matched and the target reference image based on the global image feature vector of the online transmission image to be matched and the global image feature vector of the target reference image.
In this embodiment, after the online transmission image to be matched and the target reference image are acquired based on step S101, the server may extract a global image feature vector and a local image feature vector of the online transmission image to be matched, and extract a global image feature vector and a local image feature vector of the target reference image. Then, the server may determine an interactive image feature vector between the online transmission image to be matched and the target reference image based on the global image feature vector of the online transmission image to be matched and the global image feature vector of the target reference image.
Step S103, determining the image similarity between the online transmission image to be matched and the target reference image based on the interactive image feature vector between the online transmission image to be matched and the target reference image, the local image feature vector of the online transmission image to be matched and the local image feature vector of the target reference image.
In this embodiment, after obtaining the interactive image feature vector based on step S102, the server may determine the image similarity between the online transmission image to be matched and the target reference image based on the interactive image feature vector between the online transmission image to be matched and the target reference image, the local image feature vector of the online transmission image to be matched, and the local image feature vector of the target reference image.
And step S104, determining the image recognition results of the online transmission image to be matched and the target reference image based on the image similarity.
In this embodiment, after acquiring the image similarity based on step S103, the server may determine the image recognition result of the online transmission image to be matched and the target reference image based on the image similarity.
Based on the method, the online transmission image to be matched, the target reference image and the mutual characteristic information can be captured more accurately through the global image characteristic vector and the local image characteristic vector, and the matching modes with different levels and richness can be obtained, so that the accuracy of image recognition is improved, and the problem of low accuracy of the recognition result in the existing image recognition technology is solved.
It is understood that, in an alternative example, when step S101 is executed, the online transmission image to be matched and the target reference image may be obtained based on the following steps:
firstly, acquiring a multi-frame online transmission image sent by image transmission equipment in communication connection;
next, a frame of online transmission image (such as any one frame, or one frame of an intermediate frame number) is selected from the multiple frames of online transmission images, and is used as an online transmission image to be matched, and a target reference image is obtained from a target database (the target database may be a local database of the server or a remote database of the server).
Based on this, the number of recognized images can be effectively reduced, thereby reducing the amount of calculation.
It is to be understood that in an alternative example, when step S102 is performed, the interactive image feature vector may be determined based on the following steps:
firstly, based on a trained image similarity model (which may be a neural network model obtained based on sample image training, and the type is not specifically limited here), taking the online transmission image to be matched and the target reference image as input, respectively extracting a global image feature vector and a local image feature vector of the online transmission image to be matched, and extracting the global image feature vector and the local image feature vector of the target reference image;
then, based on the global image feature vector of the online transmission image to be matched and the global image feature vector of the target reference image, determining an interactive image feature vector between the online transmission image to be matched and the target reference image.
It will be appreciated that in an alternative example, the interactive image feature vector may be determined by the image similarity model based on the following steps:
firstly, coding all pixels included in the online transmission image to be matched based on a global pixel coding layer of a trained image similarity model, coding all pixels included in the target reference image, and obtaining each pixel feature vector of a fusion pixel value, so that the global image feature vector of the online transmission image to be matched can be obtained, and the global image feature vector of the target reference image can be obtained;
secondly, respectively obtaining a local image feature vector of the online transmission image to be matched and a local image feature vector of the target reference image through a key pixel coding layer of the image similarity model by using each pixel feature vector corresponding to the online transmission image to be matched and each pixel feature vector corresponding to the target reference image, wherein the local image feature vectors are used for representing the features of a foreground image part in a corresponding image;
then, the global image feature vector of the online transmission image to be matched and the global image feature vector of the target reference image are respectively obtained through an attention mechanism layer of the image similarity model, so that the interactive image feature vector of the online transmission image to be matched relative to the target reference image and the interactive image feature vector of the target reference image relative to the online transmission image to be matched are obtained.
It is understood that in an alternative example, when step S103 is executed, the image similarity may be determined based on the following steps:
firstly, based on an interactive modeling layer of a trained image similarity model, carrying out fusion processing on an interactive image feature vector of the online transmission image to be matched and a local image feature vector of the online transmission image to be matched to obtain a fusion interactive image feature vector of the online transmission image to be matched; performing fusion processing on the interactive image feature vector of the target reference image and the local image feature vector of the target reference image based on the interactive modeling layer to obtain a fusion interactive image feature vector of the target reference image;
secondly, obtaining the feature vector of the fusion interactive image of the online transmission image to be matched after the average pooling and maximum pooling operations corresponding to the online transmission image to be matched through the average and maximum pooling layers of the image similarity model; obtaining the fusion interactive image feature vector of the target reference image after the average pooling and maximum pooling operations corresponding to the target reference image through the average and maximum pooling layers of the image similarity model; splicing the interactive image feature vector of the online transmission image to be matched and the corresponding fusion interactive image feature vector after the average pooling and maximum pooling operations to obtain a target reference image feature vector of the online transmission image to be matched; splicing the interactive image feature vector of the target reference image and the fused interactive image feature vector after the corresponding average pooling and maximum pooling operations to obtain the target reference image feature vector of the target reference image;
then, carrying out fusion processing on the target reference image feature vector of the online transmission image to be matched and the target reference image feature vector of the target reference image through a fusion layer of the image similarity model to obtain a fusion image feature vector between the online transmission image to be matched and the target reference image;
and finally, obtaining the image similarity between the online transmission image to be matched and the target reference image through the full connection layer and the activation function layer of the image similarity model by using the fusion image feature vector.
It will be appreciated that in an alternative example, the fused interactive image feature vector may be obtained based on the following steps:
firstly, based on an interactive modeling layer of a trained image similarity model, performing subtraction operation and dot product operation on an interactive image feature vector and a local image feature vector of the online transmission image to be matched, and performing subtraction operation and dot product operation on the interactive image feature vector and the local image feature vector of the target reference image;
secondly, splicing the local image feature vector, the interactive image feature vector, the image feature vector after subtraction and the image feature vector after dot multiplication of the online transmission image to be matched to obtain a fusion interactive image feature vector of the online transmission image to be matched;
and then, splicing the local image feature vector, the interactive image feature vector, the image feature vector after subtraction operation and the image feature vector after dot multiplication operation of the target reference image to obtain a fusion interactive image feature vector of the target reference image.
It will be appreciated that in an alternative example, the fused image feature vector may be obtained based on the following steps:
firstly, performing point multiplication operation on a target reference image feature vector of the online transmission image to be matched and a target reference image feature vector of the target reference image through a fusion layer of the image similarity model, and performing subtraction operation on the target reference image feature vector of the online transmission image to be matched and the target reference image feature vector of the target reference image;
secondly, splicing the target reference image feature vector of the online transmission image to be matched, the target reference image feature vector of the target reference image, the image feature vector after point multiplication operation and the image feature vector after subtraction operation to obtain a fusion image feature vector between the online transmission image to be matched and the target reference image.
It is understood that in an alternative example, when step S104 is executed, the image recognition result may be determined based on the following steps:
firstly, acquiring the magnitude relation between the image similarity and a predetermined similarity threshold, wherein the similarity threshold can be generated based on the configuration operation of a corresponding user according to an actual application scene responded by the server;
secondly, determining an image recognition result of the online transmission image to be matched and the target reference image based on the magnitude relation between the image similarity and the similarity threshold;
if the image similarity is greater than or equal to the similarity threshold, determining that the image identification result is that the online transmission image to be matched is matched with the target reference image; and if the image similarity is smaller than the similarity threshold, determining that the image identification result is that the online transmission image to be matched is not matched with the target reference image.
It is understood that, on the basis of the above example, after the step of sending the online transmission image to be matched to the traffic information processing platform is performed, that is, after the step S130 is performed, the intelligent traffic information processing method further includes the following steps:
step one, judging whether a violation processing result fed back by the traffic information processing platform based on the online transmission image to be matched is received;
and secondly, if a violation processing result fed back by the traffic information processing platform is received, executing preset operation based on the violation processing result, wherein the preset operation comprises the following steps:
and thirdly, if the violation processing result indicates that the traffic violation behavior exists in the target traffic area, taking the online transmission image to be matched as a new target reference image, wherein the step of taking the online transmission image to be matched as the new target reference image comprises the following steps of:
fourthly, replacing the target reference image with the online transmission image to be matched; or, while keeping the target reference image, taking the online transmission image to be matched as the target reference image to increase the number of the target reference images.
It is understood that, on the basis of the above example, if the step S120 is executed to determine that the online transmission image to be matched does not need to be sent to the traffic information processing platform, the intelligent traffic information processing method may further include the following steps:
the method comprises the following steps that firstly, the online transmission image to be matched is reserved, and the online transmission image to be matched is stored as a historical transmission image;
secondly, counting the number of the currently stored historical transmission images to obtain a first number;
thirdly, judging whether the first quantity is larger than a predetermined target quantity threshold value, wherein the target quantity threshold value is generated based on threshold value configuration operation of a server executing the intelligent traffic information processing method responding to a corresponding management user;
and fourthly, if the first number is larger than the target number threshold, sending the currently saved historical transmission images to the traffic information processing platform as a historical image set (and deleting the historical transmission images after sending the historical transmission images to the traffic information processing platform in order to avoid repeated processing on the historical transmission images), wherein the traffic information processing platform is used for carrying out violation processing (such as manual inspection, namely, the inspection is carried out by personnel of a traffic management department) on the basis of the historical transmission images included in the historical image set so as to determine whether traffic violation behaviors exist in each historical transmission image.
It will be appreciated that in an alternative example, the historical transmission image may be sent to the traffic information processing platform based on the following steps:
firstly, if the first quantity is larger than the target quantity threshold value, screening the currently stored historical transmission image to obtain at least one target historical transmission image;
secondly, the at least one target historical transmission image is used as a historical image set and sent to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the target historical transmission images so as to determine whether traffic violation behaviors exist in each target historical transmission image or not.
Based on this, the efficiency of the processing can be improved.
It will be appreciated that in an alternative example, the target historical transmission image may be obtained by performing a screening process based on the following steps:
first, if the first number is greater than the target number threshold, calculating a similarity between each of the currently saved history transmission images and each of the other history transmission images (which may be based on an existing similarity calculation manner or based on a similarity calculation manner included in the foregoing step S110);
and secondly, screening the currently stored historical transmission images based on the similarity between the historical transmission images to obtain at least one target historical transmission image.
It will be appreciated that in an alternative example, the target historically-transmitted images may be filtered based on the similarity between the historically-transmitted images based on the following steps:
the method comprises the steps that firstly, the mean value of the similarity between each historical transmission image and each other historical transmission image in the currently stored historical transmission images is calculated, and the mean value of the similarity corresponding to the historical transmission images is obtained;
secondly, selecting at least one candidate historical transmission image from the currently stored historical transmission images based on the magnitude relation between the similarity mean values;
thirdly, based on the similarity among the historical transmission images, taking each candidate historical transmission image as a clustering center, and clustering the currently stored historical transmission images (for example, the historical transmission images belong to the historical transmission image cluster corresponding to the candidate historical transmission image with the maximum similarity), so as to obtain at least one corresponding historical transmission image cluster;
and fourthly, selecting at least one historical transmission image from each historical transmission image cluster as a target historical transmission image to obtain at least one target historical transmission image.
It will be appreciated that in an alternative example, the at least one candidate historical transmission image may be selected based on the following steps:
firstly, calculating an average value among a plurality of similarity mean values, and taking each similarity mean value smaller than the average value as a target similarity mean value to obtain at least one target similarity mean value;
secondly, determining at least one historical transmission image corresponding to the at least one target similarity mean value as a candidate historical transmission image.
It will be appreciated that in an alternative example, at least one target historical transmission image may be obtained based on the following steps:
the method comprises the steps that firstly, two historical transmission images with the minimum similarity in a historical transmission image cluster are determined for each historical transmission image cluster with the number of the included historical transmission images larger than a second number, wherein the second number can be generated based on threshold value configuration operation of a server responding to a corresponding management user;
determining two history transmission images with the minimum similarity determined in each history transmission image cluster with the number of the included history transmission images larger than the second number as target history transmission images;
and thirdly, determining the historical transmission image with the largest similarity mean value in each historical transmission image cluster with the number of the included historical transmission images smaller than or equal to the second number, and determining the historical transmission image as the target historical transmission image.
The embodiment of the application also provides an intelligent traffic information processing device which can be applied to the server. The intelligent traffic information processing device can comprise an image recognition result acquisition module, an image sending determination module and an image sending module.
In detail, the image recognition result obtaining module is configured to obtain an image recognition result between an online transmission image to be matched and a target reference image, where the online transmission image to be matched is obtained by performing image acquisition on a target traffic area, and the image recognition result is used to represent whether the online transmission image to be matched is matched with the target reference image, and to represent that a traffic violation behavior exists in the target traffic area during matching. The image sending determination module is used for determining whether the online transmission image to be matched needs to be sent to a traffic information processing platform or not based on the image recognition result, wherein if the image recognition result is that the online transmission image to be matched is matched with the target reference image, the online transmission image to be matched needs to be sent to the traffic information processing platform. The image sending module is used for sending the online transmission image to be matched to a traffic information processing platform when it is determined that the online transmission image to be matched needs to be sent to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the online transmission image to be matched.
It is understood that specific functions of the image recognition result obtaining module, the image transmission determining module and the image transmission module can be explained with reference to the foregoing steps S101, S102 and S103.
In summary, before the online transmission image to be matched is sent to the traffic information processing platform for violation processing, whether a traffic violation exists is determined based on an image recognition result between the online transmission image to be matched and a target reference image, and after the traffic violation is determined to exist, the online transmission image to be matched is sent to the traffic information processing platform for violation processing. Based on this, compared with the conventional technical scheme that the online transmission image to be matched is directly sent to the traffic information processing platform, the technical scheme provided by the application can enable the traffic information processing platform to carry out violation processing more accurately and effectively, so that the problem of poor monitoring effect existing in the existing traffic monitoring technology is improved.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method for processing intelligent traffic information is characterized by comprising the following steps:
acquiring an image recognition result between an online transmission image to be matched and a target reference image, wherein the online transmission image to be matched is obtained based on image acquisition of a target traffic area, and the image recognition result is used for representing whether the online transmission image to be matched is matched with the target reference image or not and representing that traffic violation behaviors exist in the target traffic area during matching;
determining whether the online transmission image to be matched needs to be sent to a traffic information processing platform or not based on the image recognition result, wherein if the image recognition result is that the online transmission image to be matched is matched with the target reference image, the online transmission image to be matched needs to be sent to the traffic information processing platform;
and if the online transmission image to be matched needs to be sent to a traffic information processing platform, sending the online transmission image to be matched to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the online transmission image to be matched.
2. The intelligent traffic information processing method according to claim 1, wherein after the step of transmitting the online transmission image to be matched to the traffic information processing platform is performed, the intelligent traffic information processing method further comprises:
judging whether a violation processing result fed back by the traffic information processing platform based on the online transmission image to be matched is received;
if the violation processing result fed back by the traffic information processing platform is received, executing a preset operation based on the violation processing result, wherein the preset operation comprises the following steps:
if the violation processing result indicates that the traffic violation behavior exists in the target traffic area, the online transmission image to be matched is used as a new target reference image, wherein the step of using the online transmission image to be matched as the new target reference image comprises the following steps of:
replacing the target reference image with the online transmission image to be matched; or
And keeping the target reference image, and simultaneously taking the online transmission image to be matched as the target reference image so as to increase the number of the target reference images.
3. The intelligent traffic information processing method according to claim 1 or 2, further comprising:
if the online transmission image to be matched does not need to be sent to the traffic information processing platform, the online transmission image to be matched is reserved, and the online transmission image to be matched is used as a historical transmission image to be stored;
counting the number of the currently stored historical transmission images to obtain a first number;
judging whether the first quantity is larger than a predetermined target quantity threshold value, wherein the target quantity threshold value is generated based on the threshold value configuration operation of a server executing the intelligent traffic information processing method in response to a corresponding management user;
and if the first number is larger than the target number threshold, sending the currently stored historical transmission images as a historical image set to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the historical transmission images included in the historical image set so as to determine whether traffic violation behaviors exist in each historical transmission image.
4. The intelligent traffic information processing method according to claim 3, wherein the step of sending the currently stored historical transmission image as a historical image set to the traffic information processing platform if the first number is greater than the target number threshold comprises:
if the first number is larger than the target number threshold value, screening the currently stored historical transmission image to obtain at least one target historical transmission image;
and sending the at least one target historical transmission image as a historical image set to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the target historical transmission images so as to determine whether traffic violation behaviors exist in each target historical transmission image.
5. The intelligent traffic information processing method according to claim 4, wherein the step of filtering the currently stored historical transmission image to obtain at least one target historical transmission image if the first number is greater than the target number threshold comprises:
if the first number is larger than the target number threshold value, calculating the similarity between each history transmission image and each other history transmission image in the current saved history transmission images;
and screening the currently stored historical transmission images based on the similarity between the historical transmission images to obtain at least one target historical transmission image.
6. The intelligent traffic information processing method according to claim 5, wherein the step of performing a filtering process on the currently stored historical transmission images based on the similarity between the historical transmission images to obtain at least one target historical transmission image comprises:
calculating the mean value of the similarity between the historical transmission image and each other historical transmission image aiming at each historical transmission image in the currently stored historical transmission images to obtain the mean value of the similarity corresponding to the historical transmission image;
selecting at least one candidate historical transmission image from the currently stored historical transmission images based on the magnitude relation between the similarity mean values;
based on the similarity between the historical transmission images, taking each candidate historical transmission image as a clustering center, and clustering the currently stored historical transmission images to obtain at least one corresponding historical transmission image cluster;
and selecting at least one historical transmission image from each historical transmission image cluster as a target historical transmission image to obtain at least one target historical transmission image.
7. The intelligent traffic information processing method according to claim 6, wherein the step of selecting at least one candidate historical transmission image from the currently stored historical transmission images based on the magnitude relationship between the similarity averages includes:
calculating an average value among the similarity mean values, and taking each similarity mean value smaller than the average value as a target similarity mean value to obtain at least one target similarity mean value;
and determining at least one historical transmission image corresponding to the at least one target similarity mean value as a candidate historical transmission image.
8. The intelligent traffic information processing method according to claim 6, wherein the step of selecting at least one historically transmitted image from each historically transmitted image cluster as a target historically transmitted image to obtain at least one target historically transmitted image comprises:
determining two history transmission images with the minimum similarity in the history transmission image cluster aiming at each history transmission image cluster with the number of the included history transmission images larger than the second number;
determining two history transmission images with the minimum similarity in each history transmission image cluster as target history transmission images;
and for each history transmission image cluster of which the number of the included history transmission images is less than or equal to the second number, determining the history transmission image with the largest similarity mean value in the history transmission image cluster, and determining the history transmission image as the target history transmission image.
9. An intelligent traffic information processing device, comprising:
the image identification result acquisition module is used for acquiring an image identification result between an online transmission image to be matched and a target reference image, wherein the online transmission image to be matched is obtained based on image acquisition of a target traffic area, and the image identification result is used for representing whether the online transmission image to be matched is matched with the target reference image or not and representing that traffic violation behaviors exist in the target traffic area during matching;
the image sending determination module is used for determining whether the online transmission image to be matched needs to be sent to a traffic information processing platform or not based on the image identification result, wherein if the image identification result is that the online transmission image to be matched is matched with the target reference image, the online transmission image to be matched needs to be sent to the traffic information processing platform;
and the image sending module is used for sending the online transmission image to be matched to a traffic information processing platform when the online transmission image to be matched is determined to be needed to be sent to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the online transmission image to be matched.
10. A server, wherein the server is configured to:
acquiring an image recognition result between an online transmission image to be matched and a target reference image, wherein the online transmission image to be matched is obtained based on image acquisition of a target traffic area, and the image recognition result is used for representing whether the online transmission image to be matched is matched with the target reference image or not and representing that traffic violation behaviors exist in the target traffic area during matching;
determining whether the online transmission image to be matched needs to be sent to a traffic information processing platform or not based on the image recognition result, wherein if the image recognition result is that the online transmission image to be matched is matched with the target reference image, the online transmission image to be matched needs to be sent to the traffic information processing platform;
and if the online transmission image to be matched needs to be sent to a traffic information processing platform, sending the online transmission image to be matched to the traffic information processing platform, wherein the traffic information processing platform is used for carrying out violation processing on the basis of the online transmission image to be matched.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110819455.6A CN113537087A (en) | 2021-07-20 | 2021-07-20 | Intelligent traffic information processing method and device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110819455.6A CN113537087A (en) | 2021-07-20 | 2021-07-20 | Intelligent traffic information processing method and device and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113537087A true CN113537087A (en) | 2021-10-22 |
Family
ID=78128980
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110819455.6A Withdrawn CN113537087A (en) | 2021-07-20 | 2021-07-20 | Intelligent traffic information processing method and device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113537087A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117270479A (en) * | 2023-11-21 | 2023-12-22 | 清远欧派集成家居有限公司 | Method and system for monitoring multi-working-procedure production line of molding plate |
-
2021
- 2021-07-20 CN CN202110819455.6A patent/CN113537087A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117270479A (en) * | 2023-11-21 | 2023-12-22 | 清远欧派集成家居有限公司 | Method and system for monitoring multi-working-procedure production line of molding plate |
| CN117270479B (en) * | 2023-11-21 | 2024-02-06 | 清远欧派集成家居有限公司 | Method and system for monitoring multi-working-procedure production line of molding plate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109740573B (en) | Video analysis method, device, equipment and server | |
| CN114140713A (en) | Image recognition system and image recognition method | |
| EP4432215A1 (en) | Image processing method and device | |
| CN111639607A (en) | Model training method, image recognition method, model training device, image recognition device, electronic equipment and storage medium | |
| CN111414874A (en) | Driving risk prediction method, device and equipment based on human face and storage medium | |
| CN114140712A (en) | Automatic image recognition and distribution system and method | |
| CN113569965A (en) | User behavior analysis method and system based on Internet of things | |
| CN113537087A (en) | Intelligent traffic information processing method and device and server | |
| CN113674317B (en) | Vehicle tracking method and device for high-level video | |
| CN115439928A (en) | Operation behavior identification method and device | |
| CN113435359A (en) | Image recognition method | |
| CN113902993A (en) | Environmental state analysis method and system based on environmental monitoring | |
| CN113486856A (en) | Driver irregular behavior detection method based on semantic segmentation and convolutional neural network | |
| CN106599865A (en) | Disconnecting link state recognition device and method | |
| CN115375886A (en) | Data acquisition method and system based on cloud computing service | |
| CN114267021A (en) | Object recognition method and device, storage medium and electronic equipment | |
| CN113407750A (en) | Image distributed storage method and system | |
| CN115439692A (en) | Image processing method and device, electronic equipment and medium | |
| CN113609356A (en) | Intelligent building data acquisition method | |
| CN113626647A (en) | Data storage method and system for intelligent cell | |
| CN113516137A (en) | Online image transmission identification method and system | |
| CN113470012A (en) | Marking recognition method, marking recognition device, storage medium and electronic device | |
| CN113626419A (en) | Data screening method and system for intelligent cell | |
| CN113486342A (en) | Information security processing method and system based on user behavior analysis | |
| CN111310652A (en) | Flow identification method and system based on classification regression dual-domain model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211022 |
|
| WW01 | Invention patent application withdrawn after publication |