CN111354121B - Man-car hybrid verification system and method for intelligent inspection station - Google Patents
Man-car hybrid verification system and method for intelligent inspection station Download PDFInfo
- Publication number
- CN111354121B CN111354121B CN202010159007.3A CN202010159007A CN111354121B CN 111354121 B CN111354121 B CN 111354121B CN 202010159007 A CN202010159007 A CN 202010159007A CN 111354121 B CN111354121 B CN 111354121B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- people
- face
- window
- verification
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a man-car hybrid checking method and a man-car hybrid checking system for an intelligent checking station, which relate to the technical field of security check, and have the technical scheme that the system comprises a checking channel, wherein one end of the checking channel is a car inlet end, the other end of the checking channel is a car outlet end, the car outlet end is provided with a signal lamp and a gate machine, a checking area is arranged between the car inlet end and the gate machine, one side of the gate machine is provided with a car snapshot camera, and two sides of the checking area are symmetrically provided with face snapshot camera groups; window body lighting equipment for irradiating the side window of the vehicle to be detected is further arranged on two sides of the verification area; and a falling position detection sensor for detecting the position of the vehicle is arranged on one side of the verification area close to the gate machine. The invention has the beneficial effects that: according to the invention, by means of vehicle acquisition, face acquisition, recognition comparison, multi-device cooperation and the like, under the condition of no participation of workers, drivers and passengers are intelligently guided to autonomously complete human-vehicle verification in the vehicle in various modes such as characters, sound, signal lamps and the like, and are compared and early warned with a specific comparison library.
Description
Technical Field
The invention relates to the technical field of security inspection, in particular to a human-vehicle hybrid inspection system and a human-vehicle hybrid inspection method for an intelligent inspection station.
Background
The public security inspection station is an important component of a social security prevention and control system and is a first defense line for building a safe city firmly. In a traditional working mode, an on-board passenger is required to get off the vehicle for inspection, a large amount of manpower and material resources are required to be consumed, the passing efficiency is greatly reduced, and the effects of a filter screen and a barrier are difficult to be really played.
The commonly used techniques and methods of the existing checkpoint system are introduced:
most of the existing inspection stations rely on manual inspection, and the used auxiliary systems are only devices and systems such as gates, vehicle snapshot machines, face snapshot machines, security inspection channels and the like, and the data acquired by all the systems are independent. When a vehicle runs on a lane of a checking station, all windows are lowered, personnel conditions in the vehicle are observed manually through a checking station worker, and if further checking is deemed necessary, personnel on the vehicle need to get off the vehicle and check through a security check channel.
The core problem that current inspection station security installations exists:
1. the human cost is high, and a lane should be equipped with three groups of shifts, at least two staff of every group at least.
2. The staff just simply sees the personnel in the car, can't discern personnel such as fleing, wanted, often only can play the effect of deterring.
3. The data of the vehicle and the personnel are separated, so that the vehicle is not known to who the vehicle is, and the vehicle cannot be backtracked afterwards when someone is on the vehicle.
4. The passengers on the vehicle need to get off the vehicle and pass through security inspection, and the passing efficiency is low.
Disclosure of Invention
Aiming at the technical problem, the invention provides a man-vehicle hybrid checking system and a man-vehicle hybrid checking method for an intelligent checking station.
The technical scheme includes that the system comprises an inspection channel, wherein one end of the inspection channel is a vehicle inlet end, the other end of the inspection channel is a vehicle outlet end, a signal lamp and a gate machine are arranged at the vehicle outlet end, an inspection area is arranged between the vehicle inlet end and the gate machine, a vehicle snapshot camera is arranged on one side of the gate machine, and a human face snapshot camera group is symmetrically arranged on two sides of the inspection area; window body lighting equipment for irradiating a side window of the vehicle to be detected is further arranged on two sides of the verification area; and a falling position detection sensor for detecting the position of the vehicle is arranged on one side of the verification area close to the gate machine.
Preferably, the face camera of the face camera group is a wide-angle face camera.
Preferably, loudspeakers used as voice guide verification processes are arranged on two sides of the verification area.
Preferably, the window lighting device is a group of LED lights arranged on both sides of the verification area.
Preferably, the window lighting device is a green LED lamp.
Preferably, the inspection channel is divided into a trolley channel, a mixing channel and a cart channel;
the human face camera group of the trolley channel comprises four human face cameras which are opposite in pairs, the lenses of the human face cameras face the middle part of the inspection channel, the height of the human face cameras of the trolley channel is 1.1-1.3 m, the distance between the two human face cameras on the same side is 0.4-0.6 m, namely the human face cameras of the trolley channel shoot towards the side window of the vehicle;
preferably, the axis of the lens of the face camera of the trolley channel is vertical to the vehicle advancing direction of the inspection channel; through the four face cameras, people in the small vehicle can be snapshotted for capturing face information of the people in the small vehicle.
The face camera group of the cart channel comprises four face cameras which are symmetrically arranged in pairs, two face cameras on each side are vertically distributed, the two face cameras on each side are positioned in the oblique front of the corresponding vehicle head of the vehicle verification area, the face cameras of the cart channel are used for collecting images towards the front window direction of the vehicle, and the mounting heights of the two face cameras on each side are 1.7-1.9 meters and 2.3-2.5 meters respectively; because the front window of the large-sized vehicle is generally larger and the light transmittance is better, the human face snapshot camera is arranged in front of the vehicle, and the cameras with two heights are arranged, so that the positions of the windows of the large-sized vehicle with different heights are considered;
the face camera group of the mixing channel comprises four face cameras corresponding to the inspection of the trolley and four face cameras corresponding to the inspection of the cart respectively, and the distance between the face camera group corresponding to the cart and the face camera group corresponding to the trolley is 0.4-0.6 m. The mixed lane is the synthesis of pure dolly and pure cart promptly, because the cart locomotive can be about 0.5 meters short generally relative to the dolly locomotive, uses this kind of mounting means, no matter the car that comes is the cart or the dolly, when the vehicle triggered the position sensor, all just in the coverage of people's face camera.
Preferably, the landing detection sensor is an infrared sensor; a deceleration strip is arranged on the inspection channel corresponding to the falling position sensor;
in order to ensure that the camera has a proper snapshot angle and good snapshot quality for personnel on the vehicle, certain requirements are imposed on the parking position of the vehicle, and the vehicle needs to drive into a waiting area and press a front wheel to a deceleration strip.
The falling position sensor is arranged on the side face of the lane which is flush with the deceleration strip, when a vehicle enters a waiting area, the head of the vehicle can shield the light of the infrared sensor, and the sensor sends a signal through the relay to inform a system that the vehicle reaches a proper position;
for the mixing channel, a cart detection sensor is arranged at a position 2.1-2.4 meters above the deceleration strip, the cart detection sensor is also an infrared sensor, and after the verification task is triggered, if the cart detection sensor is shielded, the sensor sends a signal through a relay to inform a system that the coming cart is a cart, and a cart verification program is required to be operated.
The falling position detection sensor also has the function of judging the leaving state of the vehicle, when the vehicle is checked, the vehicle leaves the lane and does not shield the falling position detection sensor, and the sensor sends a signal to inform the system of leaving the vehicle through the relay.
Preferably, the system further comprises LED screens arranged on two sides of the verification area, corresponding information prompts are provided for the driver through the LED screens, and the driver is helped to perform verification links according to the verification steps.
Based on the inspection method of the intelligent inspection station human-vehicle hybrid inspection system,
s1, capturing the vehicle to enter the verification area by the vehicle capturing camera, and triggering a verification task;
s2, judging the vehicle types respectively, carrying out face snapshot on the persons in the vehicle, and carrying out preliminary counting on the persons in the vehicle according to the face snapshot result;
s3, guiding the vehicle to land according to the result of the vehicle type judgment in the S2, and judging the vehicle land state; after the vehicle with the vehicle type of the cart is judged to be located, the step is shifted to step S8, and after the vehicle with the vehicle type of the dolly is judged to be located, the step is shifted to step S4;
s4, judging the window falling state of the vehicle after the vehicle is in the correct position;
s5, counting the number of people in the vehicle after the vehicle falls into the window;
s6, comparing the preliminary counting of the people in the vehicle and the number of people after falling the window obtained in the step S2, and judging whether the snapshot of all the people in the vehicle is finished;
s7, if the judgment result is S6, all the personnel in the vehicle are captured,
s8, comparing blacklists according to the face snapshot result, and judging vehicle early warning information;
and S9, selecting to perform early warning according to the judgment of the vehicle early warning information of S8, pushing an early warning message, or releasing the vehicle to wait for the detection of the next vehicle.
Preferably, in the step S2, the human face is snapshotted, and the in-vehicle personnel is preliminarily counted according to the result of the face snapshotting, specifically including the steps of face snapshotting, quality filtering, binding of the human face and the vehicle, and face duplication removal which are sequentially performed.
The face and the vehicle are bound, and the captured face and the current vehicle are bound, so that the face information is determined to correspond to the current vehicle.
Preferably, the S4 determines the window falling state of the vehicle after the vehicle falls into the correct position by setting green light belts on both sides of the verification area, irradiating the vehicle side glass through the light belts, counting green reflective points of the window glass in the image collected by the camera, and if the green reflective points exist, it indicates that the window does not fall.
Preferably, in S5, the number of people in the vehicle after the vehicle has fallen into the window is counted after the window falls, specifically, the number of people outside the vehicle body frame is determined and removed according to the position and the motion of the people in the video collected by the camera, and then the actual number of people in the vehicle is calculated by analyzing and removing the weight through the attitude algorithm.
Preferably, in S6, the preliminary in-vehicle person count obtained in S2 is compared with the number of people after falling the window, and whether the snapshot of all the in-vehicle persons is completed is determined; the specific method is that the preliminary counting of the people in the vehicle and the counting of the number of people after the window falling are compared through the S2, and the total acquisition of the face information of the people in the vehicle is realized if the numerical value of the preliminary counting of the people in the vehicle is more than or equal to the numerical value of the counting of the number of people after the window falling.
Because the postures of the people in the vehicle are different, the people cannot be matched well sometimes, the people can not be snapped in the camera, but the people can be counted by the people counting technology at the moment, so that the system can continuously wait for snapping when the snapping number is smaller than the number of people until the snapping number exceeds the number of people. At this time, the process of comparing the subsequent face information with the blacklist can be carried out after the on-board personnel are snapped.
Preferably, in S9, the vehicle warning information determination in S8 is performed, and warning is selected and sent, and multiple warning modes, such as blacklist deployment and control provided by the system itself and pop-up window warning at the PC, may be selected. The captured face and the vehicle photo can be pushed to other public security systems for comparison and early warning in an interface mode, such as a police station and the like. When the early warning is generated, the lane gate closes the closed lane, and meanwhile early warning is performed in the system and a third-party system, so that the working personnel is reminded to perform early warning treatment in time.
Preferably, switching to evacuation mode occurs in case of emergency or heavy congestion:
in order to ensure that the lane can normally pass under extreme conditions, an evacuation mode is set, when the operation mode of the system is switched to the evacuation mode, the system stops checking, the gate long rod is lifted up and does not fall, and the signal lamp continuously lights the green light to ensure that whether the vehicle can pass through without obstacles or not. And after the emergency situation is over or the congestion is relieved, switching back to the normal mode, and then, continuously carrying out the human-vehicle verification by the system according to the verification parameters.
Preferably, a system setting interface is provided, so as to realize templating and free customization of the verification parameters, specifically:
and the parameterization free customization of all links of the verification process of the man-vehicle hybrid verification system of the intelligent inspection station is supported. And the verification parameter template can be pre-customized according to the actual vehicle passing condition, so that the rapid setting of the verification parameters is provided. The verification parameters include: the method comprises the steps of checking the maximum time of a task, checking the snapshot waiting time of a human face, comparing the human face with the waiting time, checking the LED characters of each link of the flow, checking the guide voice of each link of the flow and checking the maximum voice playing times of each link of the flow.
Preferably, fine-grained monitoring of the states of the respective component devices is set:
as the software and hardware of the butt joint are more, and the system needs an efficient means for operation and maintenance, all the butt joint software and hardware are subjected to health check, equipment state monitoring is provided, and monitoring is carried out in the form of a graphical interface, wherein the monitoring comprises human face engine state, vehicle snapshot machine state, number engine state, relay state, window falling engine state, human face camera state, audio server state, audio box state, other butt joint system platform state, left LED screen state, right LED screen state and the like.
Preferably, corresponding to the system and the method, an intelligent guiding state machine is arranged, and the intelligent inspection station man-vehicle hybrid inspection method automatically guides the vehicle driver to autonomously complete the inspection process through the intelligent guiding state machine system without manual participation. The intelligent guiding state machine can interact with the personnel on the vehicle in the modes of sound, characters, signal lamps and the like. The state transition process of the state machine is shown in the intelligent boot state machine of fig. 2:
the state machine comprises 5 state items of a vehicle falling state, a vehicle falling window state, a vehicle number checking state, a vehicle early warning state and a vehicle leaving state. According to the previous checking process, the 5 state items are detected one by one.
After the checking task is triggered, the vehicle is in an unsettled state, the state machine prompts the vehicle to enter the to-be-checked area by using sound and characters, when the vehicle is detected to enter a designated position, the state is converted into a fallen state, the current prompt is interrupted, and the vehicle window falling state detection is carried out; when the vehicle is not in a window falling state, the state machine prompts the vehicle to fall all windows by using sound and characters, and when the vehicle is detected to fall all windows, the state is converted into a window falling state, the current prompt is interrupted, and the checking state detection of the number of people in the vehicle is carried out; when the number of people does not pass the verification, the state machine prompts a driver on the vehicle to take a snapshot of the face of the driver to the left lens and the right lens by using sound and characters, and when the number of the current snapshot faces exceeds the number of people in the vehicle, the state is converted into a number verification passing state, the current prompt is interrupted, and the vehicle early warning state detection is carried out; judging whether blacklist personnel hit or not according to a comparison result of the captured face, if not, converting to a vehicle non-early-warning state, prompting that the vehicle can pass through by using sound and characters by using a state machine, switching a signal lamp to a green lamp, and simultaneously turning on a gate, if so, converting to the vehicle early-warning state, pushing early-warning information to workers by using various modes by using the state machine, simultaneously not turning on the gate, stopping the vehicle in a lane, waiting for the disposal of the workers, and then releasing the vehicle after the disposal is finished; and after the vehicle is released, detecting the leaving state of the vehicle, and switching the signal lamp to a red light after the vehicle is detected to leave, so that the whole state conversion process is completed.
Preferably, the life cycle control of the verification task is configured:
the verification process and the intelligent guide state machine are processing mechanisms under standard conditions, but in the actual human-vehicle hybrid verification process, the condition that vehicles and personnel are not matched according to expected standards inevitably exists, so that the verification process is clamped in a certain link, a set of fault-tolerant mechanism is needed, and under the condition of reducing certain acquisition accuracy rate, actions which are not standard enough are automatically tolerated, so that the verification process can smoothly run. The invention completes fault tolerance by controlling the life cycle of the verification task.
Aiming at 4 key links in the verification process: a falling state detection link, setting the maximum prompting times, wherein each time of prompting has a fixed time interval, and when the maximum prompting times are exceeded, automatically switching to the next link; a window falling detection link, wherein the maximum prompting times are set, each time of prompting has a fixed time interval, and when the maximum prompting times are exceeded, the next link is automatically switched to; the number verification state detection link is set with the maximum prompting times, each time of prompting has a fixed time interval, and when the maximum prompting times are exceeded, the next link is automatically switched to; and in the vehicle early warning state detection link, waiting time is set, and when the waiting time is over and the blacklist is not hit, no early warning is generated.
And setting the maximum verification overtime time aiming at the whole verification process, directly jumping to a vehicle early warning state detection link no matter which link the verification task is in at present after the verification task reaches the overtime time, and then ending the task.
After the life cycle control, the automatic operation of the whole verification process can be ensured under any condition, and the passing efficiency of the inspection station is not greatly reduced. The waiting time, the maximum prompting times and the overtime time are collectively referred to as verification parameters, and the verification parameters allow a user to freely customize according to the actual traffic situation of the inspection station.
The technical scheme provided by the embodiment of the invention has the following beneficial effects: the invention depends on artificial intelligence and mechanical electronic technology, and is matched with equipment such as a face camera, a vehicle snapshot machine, a gate, a sound box, an LED screen, an infrared sensor, a relay and the like, and by means of vehicle acquisition, face acquisition, identification comparison, multi-equipment cooperation and the like, under the condition of no participation of workers, drivers and passengers are intelligently guided to spontaneously complete human and vehicle verification in the vehicle in various modes such as characters, sound, signal lamps and the like, and the vehicle and personnel photos are recorded and compared with a specific comparison library and early warning is carried out. The method has the advantages that the getting-off inspection is omitted, the integral passing efficiency is greatly improved, a large amount of police force is saved, meanwhile, the personnel and the vehicle can be accurately bound, and the later analysis and study are convenient.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the present invention.
Fig. 2 is a flowchart of the operation of a boot-only state machine according to an embodiment of the present invention.
FIG. 3 is a schematic diagram of a cart passage structure according to an embodiment of the present invention.
Fig. 4 is a schematic structural view of a cart passage according to an embodiment of the present invention.
Fig. 5 is a schematic view of a hybrid vehicle tunnel structure according to an embodiment of the present invention.
Wherein the reference numerals are: 1. a signal lamp; 2. a gate machine; 3. a vehicle snapshot camera; 4. capturing a human face; 5. a window illumination device; 6. a drop position detection sensor; 7. a speaker; 8. a speed bump; 9. a cart detection sensor; 10. an LED screen.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. Of course, the specific embodiments described herein are merely illustrative of the invention and are not intended to be limiting.
It should be noted that the embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are used in the orientation or positional relationship indicated in the drawings, which are merely for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be construed as limiting the invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the invention, the meaning of "a plurality" is two or more unless otherwise specified.
In the description of the invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted", "connected" and "connected" are to be construed broadly, e.g. as being fixed or detachable or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the creation of the present invention can be understood by those of ordinary skill in the art through specific situations.
Example 1
Referring to fig. 1 to 5, the invention provides a man-car hybrid checking system of an intelligent checking station, which comprises a checking channel, wherein one end of the checking channel is a car inlet end, the other end of the checking channel is a car outlet end, the car outlet end is provided with a signal lamp (1) and a gate machine (2), a checking area is arranged between the car inlet end and the gate machine (2), one side of the gate machine (2) is provided with a car snapshot camera (3), and two sides of the checking area are symmetrically provided with face snapshot camera groups (4); window body lighting equipment (5) for illuminating a side window of the vehicle to be detected is arranged on two sides of the verification area; and a falling position detection sensor (6) for detecting the position of the vehicle is arranged on one side of the verification area close to the gate machine (2).
The face camera of the face camera group (4) is a wide-angle face camera.
And loudspeakers (7) used as voice guide verification processes are arranged on two sides of the verification area.
The window lighting equipment (5) is an LED lamp group arranged on two sides of the verification area.
The window lighting equipment (5) is a green LED lamp.
The inspection channel is divided into a trolley channel, a mixing channel and a cart channel;
the face camera group (4) of the trolley channel comprises four face cameras which are opposite in pairs, the lenses of the face cameras face the middle part of the inspection channel, the height of the face cameras of the trolley channel is 1.2 meters, the distance between the two face cameras on the same side is 0.5 meter, and the face cameras of the trolley channel shoot towards the side window of the vehicle;
the axis of a lens of a face camera of the trolley channel is vertical to the vehicle advancing direction of the inspection channel; through the four face cameras, people in the small vehicle can be snapshotted for capturing face information of the people in the small vehicle.
The face camera group (4) of the cart channel comprises four face cameras which are arranged in a pairwise symmetrical manner, two face snapshot cameras on each side are distributed up and down in the vertical direction, the two face snapshot cameras on each side are positioned in the oblique front of the corresponding vehicle head of the vehicle verification area, the face snapshot cameras of the cart channel conduct image acquisition towards the direction of the front window of the vehicle, and the mounting heights of the two face snapshot cameras on each side are 1.8 m and 2.4 m respectively; because the front window of the large-sized vehicle is generally larger and the light transmittance is better, the human face snapshot camera is arranged in front of the vehicle, and the cameras with two heights are arranged, so that the positions of the windows of the large-sized vehicle with different heights are considered;
the face camera group (4) of the mixing channel respectively comprises four face cameras corresponding to the inspection of the trolley and four face cameras corresponding to the inspection of the cart, and the distance between the face camera group corresponding to the cart and the face camera group corresponding to the trolley is 0.5 m. The mixed lane is the synthesis of pure dolly and pure cart promptly, because the cart locomotive can be about 0.5 meters short generally relative to the dolly locomotive, uses this kind of mounting means, no matter the car that comes is the cart or the dolly, when the vehicle triggered the position sensor, all just in the coverage of people's face camera.
The falling position detection sensor (6) is an infrared sensor; a deceleration strip (8) is arranged on the inspection channel corresponding to the falling position sensor (6);
in order to ensure that the camera has a proper snapshot angle and good snapshot quality for personnel on the vehicle, certain requirements are required for the parking position of the vehicle, and the vehicle needs to drive into a waiting area and press a front wheel to a deceleration strip (8).
The falling position sensor (6) is arranged on the side face of the lane which is level with the deceleration strip (8), when the vehicle enters a waiting area, the vehicle head can shield the light of the infrared sensor, and the sensor sends a signal through a relay to inform a system that the vehicle reaches a proper position;
for a mixing channel, a cart detection sensor (9) is arranged at a position 2.2 meters above a deceleration strip (8), the cart detection sensor (9) is also an infrared sensor, and after an inspection task is triggered, if the cart detection sensor (9) is shielded, the sensor sends a signal through a relay to inform a system that an incoming cart is a cart, and a cart inspection program is required to be operated.
The falling position detection sensor (6) also has the function of judging the leaving state of the vehicle, when the vehicle is checked, the vehicle leaves the lane and does not shield the falling position detection sensor (6), and the sensor sends a signal to inform the system of leaving the vehicle through a relay.
The driver verification system further comprises LED screens 10 arranged on two sides of the verification area, corresponding information prompts are provided for the driver through the LED screens 10, and the driver is helped to perform verification links according to the verification steps.
The device also comprises an upper computer which is communicated with the components, and all parts are combined into a whole through the upper computer to form a control and feedback loop for all parts.
This device during operation, through full-automatic intelligent verification flow, this verification flow need not artificial intervention, combines together through sensor, artificial intelligence technique, accomplishes the mixed verification of people's car automatically, as figure 1 intelligent inspection station people's car mixes the verification flow chart and shows:
after a vehicle is captured and a verification task is triggered, on one hand, face capturing, quality filtering, face and vehicle binding, face duplication removal and comparison are carried out; on the other hand, the method comprises the steps of firstly judging the type of a large car according to the height of the car, then continuously detecting the falling state of the car according to the stopping position of the car, then continuously detecting the falling state of a car window by using a falling window identification technology, then continuously detecting the number of people in the car, namely counting the number of people in the car, comparing the number of the face snapshots with the number of people in the car, judging whether the snapshots of all the people in the car are finished, and finally detecting the early warning state of the car, namely releasing the car if the blacklist is not hit according to the comparison result of the faces, otherwise, not releasing the car and pushing an early warning message, and simultaneously finishing the checking task.
Example 2
On the basis of the embodiment 1, the inspection method of the intelligent inspection station-based human-vehicle hybrid inspection system,
s1, the vehicle snapshot camera 3 shoots that the vehicle is about to enter the verification area, and a verification task is triggered;
s2, judging the vehicle types respectively, carrying out face snapshot on the persons in the vehicle, and carrying out preliminary counting on the persons in the vehicle according to the face snapshot result;
s3, guiding the vehicle to land according to the result of the vehicle type judgment in the S2, and judging the vehicle land state; after the vehicle with the vehicle type of the cart is judged to be located, the step is shifted to step S8, and after the vehicle with the vehicle type of the dolly is judged to be located, the step is shifted to step S4;
s4, judging the window falling state of the vehicle after the vehicle is in the correct position;
s5, counting the number of people in the vehicle after the vehicle falls into the window;
s6, comparing the preliminary counting of the people in the vehicle and the number of people after falling the window obtained in the step S2, and judging whether the snapshot of all the people in the vehicle is finished;
s7, if the judgment result is S6, all the personnel in the vehicle are captured,
s8, comparing blacklists according to the face snapshot result, and judging vehicle early warning information;
and S9, selecting to perform early warning according to the judgment of the vehicle early warning information of S8, pushing an early warning message, or releasing the vehicle to wait for the detection of the next vehicle.
And S2, performing face snapshot on the person, and performing in-vehicle personnel preliminary counting according to the face snapshot result, wherein the method specifically comprises the steps of face snapshot, quality filtering, face and vehicle binding and face duplicate removal which are sequentially performed.
The face and the vehicle are bound, and the captured face and the current vehicle are bound, so that the face information is determined to correspond to the current vehicle.
S4, judging the window falling state of the vehicle after the vehicle falls into the position correctly, wherein the judging method comprises the steps of arranging green lamp belts on two sides of a checking area, irradiating the side glass of the vehicle through the lamp belts, counting green reflective points of the window glass in an image collected through a camera, and if the green reflective points exist, indicating that the window does not fall.
And S5, counting the number of people in the vehicle after the vehicle falls into the window, specifically, counting according to the position and action of the people in the video collected by the camera, firstly judging and removing the people outside the vehicle body frame, and then calculating the actual number of people in the vehicle through attitude algorithm analysis and de-weighting.
In S6, comparing the preliminary count of the people in the vehicle and the number of people after falling the window, which are obtained in S2, and judging whether the snapshot of all the people in the vehicle is finished; the specific method is that the preliminary counting of the people in the vehicle and the counting of the number of people after the window falling are compared through the S2, and the total acquisition of the face information of the people in the vehicle is realized if the numerical value of the preliminary counting of the people in the vehicle is more than or equal to the numerical value of the counting of the number of people after the window falling.
Because the postures of the people in the vehicle are different, the people cannot be matched well sometimes, the people can not be snapped in the camera, but the people can be counted by the people counting technology at the moment, so that the system can continuously wait for snapping when the snapping number is smaller than the number of people until the snapping number exceeds the number of people. At this time, the process of comparing the subsequent face information with the blacklist can be carried out after the on-board personnel are snapped.
In S9, according to the judgment of the vehicle early warning information in S8, early warning is selected, early warning information is pushed, and various early warning modes can be selected, such as blacklist deployment and control provided by the system and popup window early warning at a PC (personal computer) end. The captured face and the vehicle photo can be pushed to other public security systems for comparison and early warning in an interface mode, such as a police station and the like. When the early warning is generated, the lane gate closes the closed lane, and meanwhile early warning is performed in the system and a third-party system, so that the working personnel is reminded to perform early warning treatment in time.
Switching to evacuation mode in the event of an emergency or severe congestion:
in order to ensure that the lane can normally pass under extreme conditions, an evacuation mode is set, when the operation mode of the system is switched to the evacuation mode, the system stops checking, the gate long rod is lifted up and does not fall, and the signal lamp continuously lights the green light to ensure that whether the vehicle can pass through without obstacles or not. And after the emergency situation is over or the congestion is relieved, switching back to the normal mode, and then, continuously carrying out the human-vehicle verification by the system according to the verification parameters.
the state machine comprises 5 state items of a vehicle falling state, a vehicle falling window state, a vehicle number checking state, a vehicle early warning state and a vehicle leaving state. According to the previous checking process, the 5 state items are detected one by one.
After the checking task is triggered, the vehicle is in an unsettled state, the state machine prompts the vehicle to enter the to-be-checked area by using sound and characters, when the vehicle is detected to enter a designated position, the state is converted into a fallen state, the current prompt is interrupted, and the vehicle window falling state detection is carried out; when the vehicle is not in a window falling state, the state machine prompts the vehicle to fall all windows by using sound and characters, and when the vehicle is detected to fall all windows, the state is converted into a window falling state, the current prompt is interrupted, and the checking state detection of the number of people in the vehicle is carried out; when the number of people does not pass the verification, the state machine prompts a driver on the vehicle to take a snapshot of the face of the driver to the left lens and the right lens by using sound and characters, and when the number of the current snapshot faces exceeds the number of people in the vehicle, the state is converted into a number verification passing state, the current prompt is interrupted, and the vehicle early warning state detection is carried out; judging whether blacklist personnel hit or not according to a comparison result of the captured face, if not, converting to a vehicle non-early-warning state, prompting that the vehicle can pass through by using sound and characters by using a state machine, switching a signal lamp to a green lamp, and simultaneously turning on a gate, if so, converting to the vehicle early-warning state, pushing early-warning information to workers by using various modes by using the state machine, simultaneously not turning on the gate, stopping the vehicle in a lane, waiting for the disposal of the workers, and then releasing the vehicle after the disposal is finished; and after the vehicle is released, detecting the leaving state of the vehicle, and switching the signal lamp to a red light after the vehicle is detected to leave, so that the whole state conversion process is completed.
Example 4
On the basis of embodiment 3, the life cycle control of the verification task is configured:
the verification process and the intelligent guiding state machine are processing mechanisms under standard conditions, but in the actual human-vehicle hybrid verification process, the condition that vehicles and personnel are not matched according to expected standards inevitably exists, so that the verification process is blocked in a certain link, a set of fault-tolerant mechanism is needed, and under the condition that certain acquisition accuracy is reduced, the actions which are not standard enough are automatically tolerated, so that the verification process can smoothly run. The invention completes fault tolerance by controlling the life cycle of the verification task.
Aiming at 4 key links in the verification process: a falling state detection link, setting the maximum prompting times, wherein each time of prompting has a fixed time interval, and when the maximum prompting times are exceeded, automatically switching to the next link; a window falling detection link, wherein the maximum prompting times are set, each time of prompting has a fixed time interval, and when the maximum prompting times are exceeded, the next link is automatically switched to; the number verification state detection link is set with the maximum prompting times, each time of prompting has a fixed time interval, and when the maximum prompting times are exceeded, the next link is automatically switched to; and in the vehicle early warning state detection link, waiting time is set, and when the waiting time is over and the blacklist is not hit, no early warning is generated.
And setting the maximum verification overtime time aiming at the whole verification process, directly jumping to a vehicle early warning state detection link no matter which link the verification task is in at present after the verification task reaches the overtime time, and then ending the task.
After the life cycle control, the automatic operation of the whole verification process can be ensured under any condition, and the passing efficiency of the inspection station is not greatly reduced. The waiting time, the maximum prompting times and the overtime time are collectively referred to as verification parameters, and the verification parameters allow a user to freely customize according to the actual traffic situation of the inspection station.
Example 5
On the basis of the above embodiment, a system setting interface is provided to realize templating and free customization of verification parameters, specifically:
and the parameterization free customization of all links of the verification process of the man-vehicle hybrid verification system of the intelligent inspection station is supported. And the verification parameter template can be pre-customized according to the actual vehicle passing condition, so that the rapid setting of the verification parameters is provided. The verification parameters include: the method comprises the steps of checking the maximum time of a task, checking the snapshot waiting time of a human face, comparing the human face with the waiting time, checking the LED characters of each link of the flow, checking the guide voice of each link of the flow and checking the maximum voice playing times of each link of the flow.
Example 6
On the basis of the above embodiment, fine-grained monitoring of the states of each component device is set:
as the software and hardware of the butt joint are more, and the system needs an efficient means for operation and maintenance, all the butt joint software and hardware are subjected to health check, equipment state monitoring is provided, and monitoring is carried out in the form of a graphical interface, wherein the monitoring comprises human face engine state, vehicle snapshot machine state, number engine state, relay state, window falling engine state, human face camera state, audio server state, audio box state, other butt joint system platform state, left LED screen state, right LED screen state and the like.
Example 7
The present invention will be described in further detail below with reference to the accompanying drawings, which are implemented by way of example according to actual scenarios.
Taking the implementation of a trolley lane as an example:
the method comprises the following steps: as shown in the installation and deployment schematic diagram of the trolley lane in fig. 3:
and planning a lane range and a check waiting area according to the standard lane width. A gate machine 2 is arranged right ahead a lane, and a vehicle snapshot camera 3 and a signal lamp 1 are arranged beside the gate machine 2. A group of box bodies are respectively arranged on two sides of the lane verification area, and window lighting equipment 5, an LED screen 10 and a loudspeaker 7 are arranged in the box bodies. A deceleration strip 8 is arranged at a position about 1 meter in front of the gate machine 2, and a drop position detection sensor 6 is arranged at a position parallel to the deceleration strip 8. Face snapshot camera group 4 that 4 individual faces snapshot cameras are constituteed is installed on the box equally, according to the relative position with the vehicle, is left front, left back, right front, right back camera respectively, and each equipment effect is as follows:
1) vehicle snapshot camera 3: and (5) snapping a picture of the vehicle and analyzing the license plate.
2) Face snapshot camera: and synchronously acquiring the video of the driver and the personnel on the vehicle.
3) The landing detection sensor 6: and judging whether the vehicle drives into a proper position in the waiting area.
4) The gate machine 2: and after the verification is finished, the lifting rod is released, and the vehicle passes through the rear rod falling.
5) LED screen 10: and providing a text mode to guide the user to cooperate with the verification.
6) The loudspeaker 7: and providing a voice mode to guide the user to cooperate with the verification.
7) Signal lamp 1: the default is red light, the green light passing mark is changed after the verification is finished, and the vehicle returns to the red light to stop after passing.
Step two: deploying the backend system. The backend system comprises: the system comprises a face recognition engine, an in-vehicle personnel counting engine, a window falling recognition engine and a man-vehicle hybrid verification system, wherein the system has the following functions:
1) a face recognition engine: face snapshot, picture quality filtering, face duplication removal and face comparison.
2) The in-vehicle people counting engine: for counting persons in vehicles
3) A window falling identification engine: for identifying whether each window is lowered
4) The man-vehicle hybrid verification system is applied as follows: the method comprises the following steps of man-vehicle binding, verification flow control, intelligent guide control, life cycle control of verification tasks, early warning, verification template management, equipment state monitoring and the like.
Step three: and configuring a verification template. According to the trial experience, 3 sets of relatively suitable verification parameter templates are explored, wherein the relatively suitable verification parameter templates comprise a common verification mode, a rapid verification mode and a peak verification mode.
A. The common verification mode is as follows:
maximum duration of check task is 30 seconds
The waiting time of snap shot of the check mark face is 3 seconds
The maximum prompt is 4 times in the drop position detection link, and the prompt voice and the prompt characters are that 'please drive forward into the area to be detected'
The method has the steps of detecting the drop window, prompting for 4 times at most, and prompting that voice and characters are 'please drop all windows'
Checking the number of people, prompting for 2 times at most, and prompting voice and characters that please see left passenger to left and right passenger to right "
In the detection link of the early warning state, the waiting time for face comparison is 2 seconds
The check shows that the check is finished and the pass is called as the prompt voice and the text for 1 time at most "
Under the common verification mode, the average verification time of the vehicle is estimated to be about 22-23 seconds.
B. In the fast check mode:
maximum duration of check task is 15 seconds
The waiting time of snap shot of the check mark face is 3 seconds
The maximum prompt is 2 times in the drop position detection link, and the prompt voice and the prompt characters are that 'please drive forward into the area to be detected'
The method has the steps of detecting the drop window, prompting for 2 times at most, and prompting that voice and characters are 'please drop all windows'
Checking the number of people, prompting for 1 time at most, and prompting voice and characters that please see left passenger to left and right passenger to right "
In the detection link of the early warning state, the waiting time for face comparison is 2 seconds
The check shows that the check is finished and the pass is called as the prompt voice and the text for 1 time at most "
Under the rapid verification mode, the average vehicle verification time is measured and calculated to be about 13-14 seconds
C. In peak check mode:
maximum duration of check task is 10 seconds
The waiting time of snap shot of the check mark face is 2 seconds
The maximum prompt is 1 time in the drop position detection link, and the prompt voice and the prompt characters are that 'please drive forward into the area to be detected'
In the detection link of drop window, maximum prompt is 1 time, and prompt voice and characters are 'please drop all windows'
Checking the number of people, prompting for 1 time at most, and prompting voice and characters that please see left passenger to left and right passenger to right "
In the detection link of the early warning state, the waiting time for face comparison is 1 second
The check shows that the check is finished and the pass is called as the prompt voice and the text for 1 time at most "
Under the peak period checking mode, the average checking time of the vehicle is about 10 seconds after being measured and calculated
After the above steps are completed, the specific verification process is described as follows: when the vehicle starts to drive into the verification area, the vehicle snapshot camera 3 shoots the vehicle information and sends the vehicle information to the system to trigger the verification task; the system starts to detect the position, controls a loudspeaker 7 to repeatedly prompt that the driver wants to drive forward into the area to be detected, and controls an LED screen 10 to prompt that the driver wants to drive forward into the area to be detected until the vehicle position or the maximum prompting times are reached, and then enters the next link; the system carries out window falling detection, controls a loudspeaker 7 to repeatedly prompt that all windows are required to fall through voice, and controls an LED screen 10 to prompt that all windows are required to fall through characters until all windows fall or the maximum prompting times are reached, and then enters the next link; the system checks the number of people, controls the loudspeaker 7 to repeatedly prompt the left passenger to see the lens leftwards and the right passenger to see the lens rightwards in a voice way, prompts the left LED screen 10 to prompt the left passenger to see leftwards, prompts the right LED screen 10 to prompt the right passenger to see rightwards, and enters the next link until the number of people is checked or the maximum prompting times is reached; when the links are carried out, the face recognition engine can capture the face through video streaming, quality filtering, duplication removal and face comparison are carried out, and the face photos are stored by the system and are associated with people and vehicles; after the number verification link is finished, the system carries out an early warning state detection link, judges whether early warning exists according to the comparison result of the face recognition engine, controls a signal lamp to light green if no early warning exists, controls the gate machine 2 to lift the rod to release, controls a loudspeaker 7 to carry out voice prompt on 'verification is finished and the person is ready to pass', and simultaneously displays 'verification is finished and the person is ready to pass' on an LED screen 10 in a text mode; if the early warning is generated, the door lock 2 is kept closed, the vehicle is stopped, and staff are reminded to handle the vehicle through various modes such as a system popup window and PAD pushing; after the vehicle passes through, the gate machine 2 automatically drops the rod, and the signal lamp lights the red light, thereby completing the whole checking task.
Therefore, the problems existing in the security inspection mode of the traditional inspection station are solved to a great extent:
1. the manpower is saved, no matter how many lanes, only a group of personnel need to be equipped, and the treatment is carried out when early warning occurs.
2. Specific personnel such as escape, wanted and wanted can carry out blacklist cloth accuse, and when personnel appeared, the early warning was triggered automatically, reminded staff key inspection and processing.
3. Personnel and vehicles are bound, and people can be found through vehicles or vehicles can be found through people.
The passengers on the vehicle do not need to get off the vehicle for inspection, and the passing efficiency is greatly improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (3)
1. The human-vehicle hybrid checking method for the intelligent checking station is characterized by comprising the following steps of:
s1, the vehicle snapshot camera (3) shoots that the vehicle is about to enter the verification area, and a verification task is triggered;
s2, judging the vehicle types respectively, carrying out face snapshot on the persons in the vehicle, and carrying out preliminary counting on the persons in the vehicle according to the face snapshot result;
s3, guiding the vehicle to land according to the result of the vehicle type judgment in the S2, and judging the vehicle land state; after the vehicle with the vehicle type of the cart is judged to be located, the step is shifted to step S8, and after the vehicle with the vehicle type of the dolly is judged to be located, the step is shifted to step S4;
s4, judging the window falling state of the vehicle after the vehicle is in the correct position;
s5, counting the number of people in the vehicle after the vehicle falls into the window;
s6, comparing the preliminary count of the people in the vehicle and the number of people after falling the window, which are obtained in the step S2, and judging whether the snapshot of all the people in the vehicle is finished;
s7, if the judgment result is S6, all the people in the vehicle are taken a snapshot;
s8, comparing blacklists according to the face snapshot result, and judging vehicle early warning information;
s9, selecting to carry out early warning according to the judgment of the vehicle early warning information of S8, pushing early warning information, or releasing the vehicle and waiting for the detection of the next vehicle;
in the step S2, performing face snapshot on the person, and performing in-vehicle person preliminary counting according to the face snapshot result, specifically including the steps of face snapshot, quality filtering, face-vehicle binding, and face deduplication which are performed in sequence;
in the step S6, comparing the preliminary count of the people in the vehicle obtained in the step S2 with the count of the number of people after falling into the window, and judging whether the snapshot of all the people in the vehicle is finished; the specific method is that the preliminary counting of the people in the vehicle and the counting of the number of people after the window falling are compared through the S2, and the total acquisition of the face information of the people in the vehicle is realized if the numerical value of the preliminary counting of the people in the vehicle is more than or equal to the numerical value of the counting of the number of people after the window falling.
2. The method according to claim 1, wherein the step S4 is to determine the window falling state of the vehicle after the vehicle is in the correct position by arranging green light strips on two sides of the verification area, irradiating the side glass of the vehicle through the light strips, counting green reflective points of the window glass in the image collected by the camera, and if the green reflective points exist, indicating that the window is not lowered.
3. The method according to claim 1, wherein in the step S5, the number of people in the vehicle after the window of the vehicle is counted after the window is dropped, specifically, the number is counted according to the position and the action of the people in the video collected by the camera, the people outside the vehicle body frame are firstly judged and removed, and then the actual number of people in the vehicle is calculated through attitude algorithm analysis and de-weighting.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010159007.3A CN111354121B (en) | 2020-03-09 | 2020-03-09 | Man-car hybrid verification system and method for intelligent inspection station |
| CN202111467060.0A CN114333126A (en) | 2020-03-09 | 2020-03-09 | Intelligent human-vehicle checking system and method for inspection station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010159007.3A CN111354121B (en) | 2020-03-09 | 2020-03-09 | Man-car hybrid verification system and method for intelligent inspection station |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111467060.0A Division CN114333126A (en) | 2020-03-09 | 2020-03-09 | Intelligent human-vehicle checking system and method for inspection station |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111354121A CN111354121A (en) | 2020-06-30 |
| CN111354121B true CN111354121B (en) | 2022-02-01 |
Family
ID=71197321
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010159007.3A Active CN111354121B (en) | 2020-03-09 | 2020-03-09 | Man-car hybrid verification system and method for intelligent inspection station |
| CN202111467060.0A Pending CN114333126A (en) | 2020-03-09 | 2020-03-09 | Intelligent human-vehicle checking system and method for inspection station |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111467060.0A Pending CN114333126A (en) | 2020-03-09 | 2020-03-09 | Intelligent human-vehicle checking system and method for inspection station |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN111354121B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111354121B (en) * | 2020-03-09 | 2022-02-01 | 中通服公众信息产业股份有限公司 | Man-car hybrid verification system and method for intelligent inspection station |
| CN112215234A (en) * | 2020-10-16 | 2021-01-12 | 神思电子技术股份有限公司 | Method for checking information of vehicle personnel at road interface |
| CN114383593B (en) * | 2020-10-22 | 2024-05-31 | 同方威视技术股份有限公司 | Vehicle inspection guiding method and system |
| CN112395966A (en) * | 2020-11-10 | 2021-02-23 | 中国科学院上海光学精密机械研究所 | Double-side visual intelligent detection device for monitoring vehicle passengers |
| CN112634626B (en) * | 2020-12-16 | 2022-02-01 | 智道网联科技(北京)有限公司 | Vehicle inspection method and system, electronic device and readable storage medium |
| CN112712012B (en) * | 2020-12-29 | 2024-09-13 | 中通服公众信息产业股份有限公司 | Road gate vehicle position detection method |
| CN112863192A (en) * | 2021-01-05 | 2021-05-28 | 航天信息股份有限公司 | System and method for acquiring human body biological information of traffic lane |
| CN113487047B (en) * | 2021-07-01 | 2022-11-08 | 石家庄华燕交通科技有限公司 | Intelligent guiding system for motor vehicle inspection business |
| CN113763610A (en) * | 2021-08-02 | 2021-12-07 | 河北远东通信系统工程有限公司 | Security check method supporting multiple check modes |
| CN113668910A (en) * | 2021-08-14 | 2021-11-19 | 刘薇 | Mobile security inspection device, system and method |
| CN113822165B (en) * | 2021-08-25 | 2024-09-10 | 中通服公众信息产业股份有限公司 | Method for detecting state of vehicle window of road gate and counting personnel in vehicle |
| CN114373303A (en) * | 2022-01-10 | 2022-04-19 | 潘学德 | Mobile modularized public security intelligent inspection station system |
| CN115187170B (en) * | 2022-07-12 | 2023-04-07 | 深圳市泰洲科技有限公司 | Seamless clearance system and use method thereof |
| CN118038423B (en) * | 2024-04-15 | 2024-07-30 | 盛视科技股份有限公司 | In-vehicle checking method and system based on intelligent vision |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203780480U (en) * | 2014-04-25 | 2014-08-20 | 沈清权 | Multifunctional anti-theft device for automobile |
| CN107948477A (en) * | 2017-12-05 | 2018-04-20 | 张家港奥尼斯信息科技有限公司 | Vehicle identification camera |
| CN108615365A (en) * | 2018-05-09 | 2018-10-02 | 扬州大学 | A kind of statistical method of traffic flow based on vehicle detection and tracking |
| CN110070733A (en) * | 2019-05-30 | 2019-07-30 | 上海海事大学 | A kind of time headway modeling method and a kind of minimum green time calculation method |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN205193907U (en) * | 2015-11-04 | 2016-04-27 | 杭州朗米科技有限公司 | Dual verification floodgate of people's car machine system |
| CN205302432U (en) * | 2015-12-25 | 2016-06-08 | 深圳市万睿智能科技有限公司 | Prevent following intelligence door system |
| CN107452104A (en) * | 2017-07-26 | 2017-12-08 | 北京声迅电子股份有限公司 | A kind of control method for vehicle and system of the vehicle bayonet socket based on intelligent monitoring |
| KR20200124263A (en) * | 2018-02-23 | 2020-11-02 | 크라운 이큅먼트 코포레이션 | System and method for indoor vehicle navigation based on optical target |
| KR20190143748A (en) * | 2018-06-21 | 2019-12-31 | 문병국 | Pole type road facility for leasing and supplying smart power using internet of things, system and method for leasing and supplying smart power using the same |
| CN110164014A (en) * | 2019-06-03 | 2019-08-23 | 深圳市万睿智能科技有限公司 | A kind of intelligent access control system |
| CN110189450A (en) * | 2019-06-05 | 2019-08-30 | 厦门浩邈科技有限公司 | A kind of trailing analysis method based on recognition of face and demographics |
| CN110689725A (en) * | 2019-09-03 | 2020-01-14 | 北京理工大学 | Security robot system for crossing comprehensive inspection and processing method thereof |
| CN110867004A (en) * | 2019-11-25 | 2020-03-06 | 交通运输部公路科学研究所 | Automatic checking and releasing system for road freight vehicles |
| CN111354121B (en) * | 2020-03-09 | 2022-02-01 | 中通服公众信息产业股份有限公司 | Man-car hybrid verification system and method for intelligent inspection station |
-
2020
- 2020-03-09 CN CN202010159007.3A patent/CN111354121B/en active Active
- 2020-03-09 CN CN202111467060.0A patent/CN114333126A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203780480U (en) * | 2014-04-25 | 2014-08-20 | 沈清权 | Multifunctional anti-theft device for automobile |
| CN107948477A (en) * | 2017-12-05 | 2018-04-20 | 张家港奥尼斯信息科技有限公司 | Vehicle identification camera |
| CN108615365A (en) * | 2018-05-09 | 2018-10-02 | 扬州大学 | A kind of statistical method of traffic flow based on vehicle detection and tracking |
| CN110070733A (en) * | 2019-05-30 | 2019-07-30 | 上海海事大学 | A kind of time headway modeling method and a kind of minimum green time calculation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111354121A (en) | 2020-06-30 |
| CN114333126A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111354121B (en) | Man-car hybrid verification system and method for intelligent inspection station | |
| CN106652551B (en) | Parking space detection method and equipment | |
| WO2020124950A1 (en) | Parking lot traffic accident tracing system and method based on high precision indoor positioning technology | |
| CN105741560A (en) | Vehicle identification method used for gas station | |
| CN107016852B (en) | Intelligent parking access control system and method with stress prevention function | |
| CN109146914B (en) | Drunk driving behavior early warning method for expressway based on video analysis | |
| CN209388480U (en) | Freeway tunnel safe operation monitors system | |
| CN103730009A (en) | Method and system for detecting vehicle with one number plate missing | |
| KR20200035536A (en) | Enforcement system of vehicle violating exclusive bus lain using infrared camera and infrared lighting, and method for the same | |
| CN106683413A (en) | Rapid rescue system based on emergency lane | |
| CN107911488A (en) | A kind of scenic spot integrates security-protection management system | |
| JP5506537B2 (en) | A vehicle side light detection method provided in a traveling body, and a movable fence control device that opens and closes a door provided in the movable fence using the detection method. | |
| CN108550218A (en) | A kind of bicycle capacity integrated control system and its management-control method | |
| CN110809137A (en) | Campus safety trampling prevention monitoring system and method | |
| CN204155453U (en) | A kind of high-definition electronic police capturing retrograde vehicle | |
| CN114333120A (en) | Bus passenger flow detection method and system | |
| CN110310400B (en) | Intelligent gate system for lane special for bicycle and control method thereof | |
| CN115527377A (en) | Security robot system and method for comprehensive inspection of people and vehicles at public security inspection station | |
| CN111206525A (en) | Street crossing control method, system and device | |
| KR100573727B1 (en) | Safety accident preventing system for railroad platform | |
| KR101050452B1 (en) | Taxi enforcement system, method using the same and recording medium thereof | |
| KR20060102889A (en) | System and method for regulating violation of exclusive auto road | |
| CN106251638A (en) | Channelizing line violation snap-shooting system | |
| CN114373303A (en) | Mobile modularized public security intelligent inspection station system | |
| KR102428881B1 (en) | Elevator smart recording and monitoring system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |