Vehicle detection method and related device thereof

Abstract

The application provides a vehicle detection method and a related device thereof, relates to the technical field of communication, and is applied to a vehicle detection system comprising a position detection device and a shooting device. A plurality of identification areas are divided along the road width direction in a detection area comprising a plurality of lanes, and the number of the identification areas is greater than the number of the lanes. The vehicle detection method comprises the following steps: when a vehicle enters the detection area, acquiring the position information of the vehicle in real time through the position detection device; determining the identification area where the vehicle currently locates as a target identification area according to the position information of the vehicle; and sending a shooting signal to the shooting device so that the shooting device shoots the vehicle in the target identification area. The application utilizes the fine division of the identification areas, so that the vehicle in the driving lane is consistent with the vehicle shot by the shooting device, thereby achieving the purpose of improving the vehicle identification rate.

Description

Technical Field

[0001] This application belongs to the field of communication technology, and in particular relates to a vehicle detection method and related equipment. Background Technology

[0002] Currently, utilizing information technology to combat overloading has become a major approach in my country's efforts to manage freight overloading. Among these methods, non-stop dynamic weighing and detection systems on highways are an indispensable component.

[0003] When a vehicle passes through the weighing device in the non-stop dynamic weighing detection system on the highway, the weighing device can automatically detect information such as the vehicle's speed, axle load, number of axles, wheelbase, total vehicle weight, and passage time. It can also automatically separate the vehicle and form a complete vehicle weighing information. Then, it is matched with image evidence information such as images captured by the capture equipment of the front, body, and rear of the vehicle, as well as short videos obtained during the detection process, to realize the detection and screening of overloaded freight vehicles. Subsequently, according to law enforcement needs, overloaded vehicles can be dealt with in accordance with the law.

[0004] However, in the current method, only one capture is performed when a vehicle is detected in the area. If there are two vehicles running parallel in the lane and both of their valid license plates are within the recognition area, the camera will randomly output a license plate. This may result in a mismatch between the output license plate and the weighing data, leading to incorrect evidence collection. Summary of the Invention

[0005] This application provides a vehicle detection method and system. By finely dividing a detection area including multiple lanes into a number of identification areas along the lane width direction that is greater than the number of lanes, the capture device can capture images more accurately, thereby ensuring that the vehicles in the driving lanes match the vehicles in the identification areas, thus improving the vehicle recognition rate.

[0006] To achieve the above objectives, this application adopts the following technical solution:

[0007] Firstly, a vehicle detection method is provided, applied to a vehicle detection system including a position detection device and a camera; and a detection area containing multiple lanes is divided into multiple recognition areas along the road width direction, wherein the number of recognition areas is greater than the number of lanes; the vehicle detection method includes:

[0008] When a vehicle enters the detection area, the vehicle's location information is acquired in real time through the location detection device; based on the vehicle's location information, the current identification area of ​​the vehicle is determined and used as the target identification area; a capture signal is sent to the shooting device so that the shooting device can capture images of the vehicle within the target identification area.

[0009] The vehicle detection method provided in the first aspect can make more accurate judgment on the position of a vehicle based on existing sensor structure and signal characteristics without adding hardware devices, finely divide a plurality of identification areas along the width direction of a lane in a detection area including a plurality of lanes, so that each identification area corresponds to a snapshot device that can only recognize one license plate and cannot recognize multiple license plates at the same time, and thus the vehicle in a driving lane is consistent with the vehicle captured by the snapshot device, achieving the purpose of improving vehicle recognition rate.

[0010] In a possible implementation manner of the first aspect, each two adjacent identification areas partially overlap.

[0011] In a possible implementation manner of the first aspect, the vehicle position information is obtained by a weighing device.

[0012] The weighing device includes M columnar sensors arranged in each lane; each N continuous columnar sensors correspond to one identification area, M > N ≥ 2, and M and N are integers.

[0013] In this implementation manner, since the identification areas are finely divided, the determined target identification area where the vehicle currently locates is more accurate, and thus the vehicle captured by the snapshot device corresponding to the target identification area is more consistent with the vehicle driving.

[0014] In a possible implementation manner of the first aspect, determining the identification area where the vehicle currently locates according to the vehicle position information includes:

[0015] Determining the license plate position of the vehicle according to the vehicle position information.

[0016] Determining the identification area where the vehicle currently locates according to the determined license plate position of the vehicle.

[0017] In this implementation manner, the vehicle and the identification area can be associated by the position detection device.

[0018] In a possible implementation manner of the first aspect, determining the license plate position of the vehicle according to the vehicle position information includes:

[0019] Determining the left wheel position and the right wheel position of the first axis of the vehicle according to the vehicle position information.

[0020] Determining the license plate position according to the left wheel position and the right wheel position of the first axis.

[0021] In the implementation, the first axle refers to a first axle at the front side of the vehicle, and since the first axle is closest to the license plate at the front side of the vehicle, the position of the two wheels of the first axle of the vehicle can be determined by analyzing the position information triggered by the vehicle, and the position of the license plate can be further determined according to the middle position of the two wheels corresponding to the first axle.

[0022] In a possible implementation of the first aspect, the identification area currently occupied by the vehicle is determined according to the determined position of the license plate of the vehicle, including:

[0023] determining the distance between the center of each identification area and the position of the license plate;

[0024] determining the minimum value in the plurality of distances, and taking the identification area corresponding to the minimum value as the identification area currently occupied by the vehicle.

[0025] In the implementation, the identification area closest to the license plate can be selected as the target identification area by determining the distance between the center of the identification area and the position of the license plate, so that the identification area currently occupied by the vehicle can be determined, and the identification accuracy of the target identification area is improved.

[0026] In a possible implementation of the first aspect, the photographing device includes a plurality of snapshot devices, and the snapshot devices are arranged correspondingly to the identification areas; the snapshot device according to the snapshot signal to the vehicle in the target identification area, including:

[0027] After the photographing device receives the snapshot signal, the photographing device determines the snapshot device corresponding to the target identification area, and instructs the determined snapshot device to perform snapshot and generate a target image; wherein the target image carries a mark corresponding to the target identification area.

[0028] In the implementation, the target identification area can be accurately snapped by the snapshot device corresponding to the target identification area, so that the license plate image corresponding to the vehicle can be accurately obtained.

[0029] In a possible implementation of the first aspect, the method further includes:

[0030] When the vehicle passes through the position detection device, the position detection device collects and updates the vehicle information of the vehicle, and the vehicle information includes at least one of the mark corresponding to the target identification area, the number of axles of the vehicle, the wheelbase, and the axle load.

[0031] In a possible implementation of the first aspect, the width of the identification area is greater than a preset width.

[0032] In the implementation, over-fine division of the identification area can be avoided, and the calculation amount is saved while ensuring accurate identification of the license plate.

[0033] In a second aspect, a vehicle detection system is provided, which divides a plurality of identification areas along a road width direction in a detection area including a plurality of lanes, and the number of the identification areas is greater than the number of the lanes; the vehicle detection system comprises:

[0034] A position detection device is configured to acquire real-time vehicle position information when the vehicle enters the detection area;

[0035] A data processing device is configured to determine the identification area in which the vehicle currently locates as a target identification area according to the vehicle position information, and generate and send a snapshot signal to a shooting device;

[0036] The shooting device is configured to receive the shooting signal, and perform snapshot on the vehicle in the target identification area according to the shooting signal.

[0037] In a third aspect, a vehicle detection device is provided, which comprises a memory and a processor, the memory stores a computer program, and the processor is configured to execute the vehicle detection method in the first aspect or any possible implementation of the first aspect.

[0038] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program or instructions, and when the computer reads and executes the computer program or instructions, the computer executes the vehicle detection method in the first aspect or any possible implementation of the first aspect.

[0039] The embodiments of the present application provide a vehicle detection method and system, which finely divides a plurality of identification areas along a lane width direction in a detection area including a plurality of lanes, and the number of the identification areas is greater than the number of the lanes, so as to avoid the case that two vehicles are in the same identification area, and make the corresponding snapshot device of each identification area not recognize multiple license plates at the same time, and further make the vehicle in the driving lane consistent with the vehicle captured by the snapshot device, and achieve the purpose of improving the vehicle recognition rate. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 FIG. 1 is a schematic diagram of an application scenario;

[0041] Figure 2 FIG. 2 is a schematic diagram of division of an identification area provided by the prior art;

[0042] Figure 3 FIG. 3 is a schematic diagram of a structure of a sensor provided by the embodiments of the present application;

[0043] Figure 4 is a flowchart of a vehicle detection method provided by an embodiment of the present application;

[0044] Figure 5 is a division schematic diagram of an identification area provided by an embodiment of the present application;

[0045] Figure 6 is another division schematic diagram of an identification area provided by an embodiment of the present application.

[0046] Reference signs:

[0047] 1-vehicle detection system; 2-position detection device; 10-weighing device; 11-sensor assembly; 12-stripe sensor; 13-data processing device; 20-shooting device; 21-snapping device; 30-evidence collection device. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0049] First, the application scenario is briefly introduced. Figure 1 A schematic diagram of an application scenario is shown.

[0050] As shown in Figure 1 , a weighing device 10 is arranged in the middle of the road, and a shooting device 20 including a plurality of snapping devices 21 and an evidence collection device 30 are also arranged correspondingly, wherein the evidence collection device 30 can be a camera or one of the snapping devices 21 in the shooting device 20. Among them, the weighing device 10, the shooting device 20 and the evidence collection device 30 can be communicatively connected.

[0051] When the vehicle travels and passes through the weighing device 10, the weighing device 10 is triggered and generates a snapping signal to instruct the snapping device 21 in the shooting device 20 to snap the vehicle head and identify the license plate. In addition, the snapping device 21 can also snap the vehicle body and tail, and take screenshots of the short video shot when the vehicle passes through. Then, the weighing device 10 sends the collected weighing information and the shooting device 20 sends a series of related information to the evidence collection device 30 for detection. The evidence collection device 30 matches the license plate, image, video information with the weighing information, and finally the road management or law enforcement personnel realizes accurate law enforcement and evidence collection on overloaded and oversized vehicles.

[0052] It can be understood that whether the license plate recognition is correct is a key factor for evidence collection, and if the recognition is wrong, it will bring great difficulty to evidence collection, and an important influencing factor causing the recognition error is the division of the recognition area in the detection area. The detection area is the area where the weighing device 10 is laid on the lane.

[0053] In the prior art, the division of the license plate recognition area is divided according to the number of actual lanes included in the detection area, that is, one lane in the detection area is usually divided into one recognition area. In this way, if multiple vehicles pass through the detection area, there are two vehicles in parallel in the same lane, and the license plates are in the recognition area corresponding to the lane, the snapshot image of the recognition area taken by the snapshot device 21 will include the images corresponding to the two license plates, and the license plate recognized by the snapshot device 21 may not match the vehicle corresponding to the weighing information obtained by the weighing device 10, causing information confusion and resulting in errors in subsequent evidence collection.

[0054] Figure 2 A schematic diagram of a recognition area in the related art is shown.

[0055] For example, as shown in Figure 2 , there are actually 3 lanes on the road, assuming from left to right are lane 1, lane 2 and lane 3, and the area indicated by b is the current detection area where the weighing device 10 is laid. Then, according to the number of lanes, each lane in the detection area can be divided into a recognition area along the road width direction (i.e. x direction). From left to right, they are recognition area a1, recognition area a2 and recognition area a3. Among them, recognition area a1 corresponds to lane 1, recognition area a2 corresponds to lane 2, and recognition area a3 corresponds to lane 3. Here, the width of each recognition area can be slightly wider than the width of the lane.

[0056] When the snapshot device 21 takes a snapshot, if there are two vehicles in parallel in the left lane 1, and both license plates are within the scope of the recognition area a1, the snapshot device 21 will only randomly give one license plate, so the license plate recognition result may not match the vehicle corresponding to the weighing information, resulting in errors in subsequent evidence collection. As can be seen, there is a certain uncertainty in relying too much on the license plate recognition of the snapshot device 21 and the weighing device 10 for evidence collection.

[0057] Therefore, the embodiments of the present application provide a vehicle detection method, which finely divides a number of recognition areas greater than the number of lanes along the lane width direction in a detection area including a plurality of lanes, so that each recognition area corresponding to the snapshot device will not recognize multiple license plates at the same time, and only one license plate can be recognized, thereby making the vehicle in the driving lane consistent with the vehicle captured by the snapshot device, and achieving the purpose of improving the vehicle recognition rate.

[0058] The vehicle detection system and the vehicle detection method provided by the embodiments of the present application will be described in detail below with reference to the drawings. First, the vehicle detection system 1 provided by the embodiments of the present application is described in detail.

[0059] The embodiments of the present application provide a vehicle detection system 1, comprising a position detection device 2 and a shooting device 20. The vehicle detection system 1 is suitable for Figure 1 the application scenarios.

[0060] Optionally, the position detection device 2 can be a weighing device 10, or can be a laser radar scanning device, etc. The weighing device 10 can collect the position information of the vehicle through a strip sensor 12, and the laser radar scanning device can track the position information of the vehicle through a laser radar. Of course, the position detection device 2 can also be other devices, which can be set as needed, and the embodiments of the present application do not make any limitation in this regard.

[0061] As shown in Figures 3-6 Without increasing hardware devices, the embodiments can make more accurate judgments on the position of the vehicle based on the existing weighing device and signal characteristics. When the position detection device 2 is the weighing device 10, the weighing device 10 can include M columns of arrayed strip sensors 12 arranged in each lane, wherein each continuous N columns of strip sensors 12 correspond to an identification area, M>N≥2, and M and N are integers. In the embodiments, the detection area includes 3 lanes, and each lane has 2 columns of strip sensors, and the adjacent two columns of strip sensors are arranged in parallel and staggered along the extension direction of the lane.

[0062] It should be understood that the column direction y is consistent with the extension direction of the lane, and the row direction x is consistent with the width direction of the lane. Based on the row direction x and the column direction y, the M columns of strip sensors 12 arranged in each lane means that there are M columns of strip sensors 12 arranged along the row direction x, and the adjacent two columns of strip sensors 12 can be arranged in a spaced manner, a staggered manner or an adjacent manner along the row direction x.

[0063] Among them, the spaced arrangement along the row direction x means that there is a certain distance between the adjacent two columns of strip sensors 12 in the row direction x; the adjacent arrangement along the row direction x means that there is no gap between the adjacent two columns of strip sensors 12 in the row direction x; the staggered arrangement along the row direction x means that whether there is a certain distance between the adjacent two columns of strip sensors in the row direction x, the two columns of strip sensors are not arranged along a straight line parallel to the x direction. Of course, the M columns of strip sensors 12 can also be arranged in other manners, which can be set and modified as needed, and the embodiments of the present application do not make any limitation in this regard.

[0064] It should be understood that each column of strip sensors includes a plurality of strip sensors 12 arranged at intervals in the column direction y. Arranged at intervals in the column direction y means that there is a certain distance between two adjacent strip sensors 12 in the column direction y. The number and interval distance of the strip sensors 12 arranged at intervals in the column direction y can be set as needed, and the embodiments of the present application do not make any limitation in this regard.

[0065] Figure 3 A structural schematic diagram of a strip sensor 12 is shown. As shown, each strip sensor 12 includes four trigger paths, i.e., includes four weighing units. From left to right, they are path 1, path 2, path 3, and path 4. Figure 3

[0066] It should be understood that the strip sensor 12 is used to detect the pressure of the vehicle on the strip sensor 12 and output the weight information. Since the number of trigger paths in each strip sensor 12 has corresponding position information, by collecting the weight information output by the strip sensor 12, the corresponding trigger path of the weight information can be determined, and the vehicle position information can be determined. Wherein, the long side of each strip sensor 12 is parallel to the x direction.

[0067] On this basis, each continuous N column of strip sensors 12 corresponds to an identification area, which means that the N columns of strip sensors 12 continuous in the row direction x can be divided into an identification area.

[0068] When the number of N is the same as the number of columns of strip sensors included in the lane, the width of the identification area can be equal to or less than the actual width of the lane. When the number of N is less than the number of columns of strip sensors 12 included in the lane, the width of the identification area is less than the actual width of the lane. In this way, each lane corresponds to more than one identification area, and the number of identification areas divided along the road width direction of the entire detection area will be greater than the number of lanes.

[0069] It should be understood that the identification areas can be adjacent and non-overlapping, or can have partial overlap. When two identification areas overlap, the two identification areas include the same strip sensors 12. The number of columns of strip sensors 12 included in each identification area can be the same or different, and can be set as needed, and the embodiments of the present application do not make any limitation in this regard.

[0070] Optionally, the vehicle detection system 1 can further include a data processing device 13. The data processing device 13 is used to receive and process the vehicle position information triggered by the strip sensor 12.

[0071] It should be understood that each strip sensor 12 is in communication connection with the data processing device 13, and the strip sensor 12 can transmit the collected vehicle position information to the data processing device 13.

[0072] ​Optionally, the photographing device 20 in the vehicle detection system 1 provided by the embodiment of the present application can include a plurality of snapshot devices 21, and the snapshot device 21 can be in one-to-one correspondence with the identification area, that is, each snapshot device 21 corresponds to an identification area, and the snapshot device 21 only takes a snapshot of the corresponding identification area.

[0073] Optionally, the snapshot device 21 can also be in a many-to-one correspondence with the identification area, or in a one-to-many correspondence, or in a one-to-one correspondence. That is, a plurality of snapshot devices 21 can correspond to one identification area, and the plurality of snapshot devices 21 simultaneously take a snapshot of the identification area; or each snapshot device 21 can correspond to a plurality of identification areas, and each identification area in the plurality of identification areas can be taken by the snapshot device 21, but the snapshot order is generally based on the order of the received snapshot signals. In the embodiment, the identification area is in one-to-one correspondence with the snapshot area, so as to further improve the identification accuracy.

[0074] The snapshot device 21 obtains an image through an image processor, and the image sensor can be, for example, a charge-coupled device (CCD), a complementary metal oxide semiconductor (CMOS), etc. The embodiment of the present application does not make any limitation in this regard.

[0075] In combination with the vehicle detection system 1 described above, the vehicle detection method provided by the embodiment of the present application is described in detail. Figure 4 A flowchart of the vehicle detection method provided by the embodiment of the present application is shown.

[0076] As shown in Figure 4 The method includes the following S100 to S300.

[0077] S100, when the vehicle enters the detection area, the position detection device 2 obtains the vehicle position information in real time. The following takes the weighing device 10 as an example for description.

[0078] It should be understood that real time means that when the vehicle passes through the detection area, the vehicle position information is collected by the strip sensor 12 as soon as the vehicle presses the strip sensor 12, and the time delay can be ignored.

[0079] It should be understood that the position information of the vehicle can be used to indicate the position represented by the triggered trigger number in the triggered strip sensor 12.

[0080] It should be understood that the vehicle includes a plurality of wheels, each of which travels at a different position, so that during the vehicle travels, when the vehicle passes through the weighing device 10, each wheel will roll over a plurality of strip sensors 12, triggering one or more trigger paths of each strip sensor 12, thereby obtaining the position information of the vehicle in real time.

[0081] S200, the data processing device 13 determines the identification area where the vehicle is currently located according to the vehicle position information, and takes it as the target identification area.

[0082] Optionally, the above S200 can include the following S210 and S240.

[0083] S210, determining the left wheel position and the right wheel position of the first axle of the vehicle according to the vehicle position information.

[0084] It should be understood that by analyzing a plurality of position information, the position information of each wheel in the vehicle and the motion trajectory of each wheel can be determined. In the embodiment, after the first axle of the vehicle sequentially presses the strip sensor array, the position of the axle and the speed of the vehicle can be calculated through the sensor matching logic, and the position of the vehicle head can be deduced according to the position of the first axle of the vehicle. Thereafter, according to the vehicle speed, the position of the vehicle head at each moment can be calculated.

[0085] It should be understood that the first axle refers to the first axle of the vehicle driving into the detection area,

[0086] Wherein, the left wheel position and the right wheel position are only used to distinguish the information of the two wheels on both sides of the first axle, and the "left" and "right" can be changed according to the different directions.

[0087] S220, determining the license plate position according to the left wheel position and the right wheel position of the first axle.

[0088] Here, the license plate position refers to the license plate on the front side of the vehicle, which is generally located on the center line of the front side of the vehicle, so that the middle position between the left wheel position and the right wheel position can be determined by determining the left wheel position and the right wheel position of the vehicle. Then, the middle position can be taken as the corresponding license plate position.

[0089] For example, when the vehicle normally drives into the detection area, since the axle is closest to the license plate on the front side of the vehicle, the position of the two wheels connected by the first axle can be determined by analyzing the position information triggered by the vehicle, and then the license plate position can be further determined according to the middle position of the two wheels corresponding to the first axle.

[0090] On this basis, since the license plate is usually some distance away from the first axle, the accuracy of the license plate position can be further improved by combining other data. For example, after determining the middle position C1 of the two wheels corresponding to the first axle, the vertical distance D of the front edge of the vehicle body to the middle position of the left and right wheels is determined, so that the position with a distance D from the middle position C1 and close to the front side of the vehicle body on the median line of the first axle can be determined as the license plate position.

[0091] S230, determine the distance between the center of each identification area and the license plate position.

[0092] S240, determine the minimum value in the plurality of distances, and determine the identification area corresponding to the minimum value as the identification area where the vehicle is currently located, i.e., the target identification area.

[0093] Exemplary one, Figure 5 An identification area division schematic diagram provided by an embodiment of the application is shown.

[0094] As Figure 5 shown, it is assumed that there are actually 3 lanes on the road, lane 1, lane 2 and lane 3 from left to right, and each lane has four columns of strip sensors 12 distributed along the row direction x, and the four columns of strip sensors 12 are divided into two column sensor assemblies 11, which are arranged staggered. Among them, each column sensor assembly 11 contains 3 sensor assemblies 11 along the column direction y, and each sensor assembly 11 includes two strip sensors 12 arranged adjacent along the row direction x, and each strip sensor 12 includes 4 trigger paths arranged along the row direction x.

[0095] Two consecutive column sensor assemblies 11 are divided into one identification area, that is, four consecutive strip sensors 12 are divided into one identification area, so that the six column sensor assemblies (12 strip sensors 12) arranged in the three lanes can be divided into five identification areas. For example, from left to right, the first column sensor assembly 11 and the second column sensor assembly 11 correspond to the identification area b1, the second column sensor assembly 11 and the third column sensor assembly 11 correspond to the identification area b2, and so on, the fifth column sensor assembly 11 and the sixth column sensor assembly 11 correspond to the identification area b5. It should be understood that adjacent identification areas contain some same strip sensors 12, which means that adjacent identification areas overlap.

[0096] Based on this division method, when a vehicle passes through the weighing device 10, according to the received position information, the license plate position of the vehicle can be determined (as Figure 5As shown in w1), the distance between the center of each recognition region and the license plate position is calculated. That is, the distances between the center of recognition region b1 and the center of recognition region b5 and the license plate position w1 are calculated respectively. Then, the five calculated distances are sorted, and the minimum value among the five distances is determined. Assuming that the recognition region corresponding to the minimum value among the five distances is b2, it means that the license plate position is closest to the recognition region b2. Therefore, the recognition region b2 can be regarded as the recognition region where the vehicle is currently located, that is, the target recognition region.

[0097] Example 2, Figure 6 This illustration shows another schematic diagram of the division of the identification region provided in an embodiment of this application.

[0098] like Figure 6 As shown, assuming there are actually three lanes on the road, from left to right: lane 1, lane 2, and lane 3, each lane has four rows of strip sensors 12 distributed along the x-direction. The four rows of strip sensors 12 are paired up to form two rows of sensor assemblies 11, which are staggered. Each row of sensor assemblies 11 contains three sensor assemblies 11 along the y-direction, and each sensor assembly 11 includes two adjacent strip sensors 12 arranged along the x-direction. Each strip sensor 12 includes four trigger paths arranged along the x-direction.

[0099] From left to right, the first to third columns of strip sensors 12 are divided into one recognition area c1, the fourth and fifth columns of strip sensors 12 are divided into one recognition area c2, the sixth and seventh columns of strip sensors 12 are divided into one recognition area c3, the eighth and ninth columns of strip sensors 12 are divided into one recognition area c4, and the tenth to twelfth columns of strip sensors 12 are divided into one recognition area c5. It should be understood that adjacent recognition areas contain a different number of columns of strip sensors 12 and do not overlap.

[0100] Based on this classification method, when a vehicle passes through the weighing device 10, the location of the vehicle's license plate can be determined based on the received location information (e.g., ...). Figure 6 As shown in w2), the distance between the center of each recognition area and the license plate position is calculated. That is, the distances from the center of recognition area c1 to the center of recognition area c5 to the vehicle position w2 are calculated respectively. The five calculated distances are sorted, and the minimum value among the five distances is determined. Assuming that the recognition area corresponding to the minimum value among the five distances is c4, it means that the license plate position is closest to recognition area c4. Therefore, recognition area c4 can be regarded as the recognition area where the vehicle is currently located, that is, the target recognition area.

[0101] The above is only an example of division of two identification areas, and does not constitute any limitation on the embodiments of the present application. Of course, other division manners can also be used, and the embodiments of the present application do not limit this.

[0102] Here, if the determined minimum distance corresponds to two identification areas, it indicates that the license plate position is just at the boundary of the two identification areas. At this time, for example, the driving direction of the vehicle can be predicted according to the running track of the license plate position of the vehicle, and one of the two identification areas is determined as the identification area currently occupied by the vehicle in combination with the driving direction.

[0103] Optionally, the width of the identification area is greater than a preset width, for example, the preset width is the width of the vehicle.

[0104] It should be understood that too many identification areas will increase the calculation amount. Therefore, in combination with the cost, when the width of the lane is 3 meters, the width of the identification area can be set to 1-1.5 meters. In the embodiment, the width of the identification area is set to 1 m.

[0105] S300, the data processing device 13 sends a snapshot signal to the shooting device 20, so that the shooting device 20 captures the vehicle in the target identification area.

[0106] Optionally, the shooting device 20 includes a plurality of snapshot devices 21.

[0107] If the snapshot device 21 is one-to-one corresponding to the identification area, after the shooting device 20 receives the snapshot signal, the snapshot device 21 corresponding to the target identification area can be determined as the target snapshot device, and the target snapshot device 21 is instructed to capture the license plate position in the target identification area to generate a target image.

[0108] The snapshot signal is used to indicate the license plate position and the target identification area. The target image carries a mark corresponding to the target identification area, so as to match the image with other information of the vehicle subsequently. For example, the specific position of the vehicle in the detection area (i.e., the position of the identification area) at the snapshot moment can be determined according to the mark corresponding to the identification area, and then the weight information and the image information are matched according to the position of the identification area and the position of the vehicle obtained by the weighing device.

[0109] Example I: It is assumed that the shooting device 20 includes five snapshot devices 21, and each snapshot device 21 corresponds to one identification area in the detection area. Figure 5 When the weighing device 10 determines that the target identification area currently occupied by the license plate is b2, the data processing device 13 sends a snapshot signal to the shooting device 20, instructing the snapshot device 21 corresponding to the target identification area b2 to capture the license plate position in b2 to generate a target image, and the target image carries a mark corresponding to the target identification area b2.

[0110] Example two, assuming the shooting device 20 includes 5 snapshot devices 21, each snapshot device 21 corresponds to one identification area in the c1-c4. Figure 6 When the weighing device 10 determines that the target identification area where the license plate is currently located is c4, the data processing device 13 sends a snapshot signal to the shooting device 20, instructing the snapshot device 21 corresponding to the target identification area c4 to shoot the position of the license plate in c4, and generate a target image carrying the mark corresponding to the target identification area c4.

[0111] The vehicle detection method provided by the embodiment of the application can make more accurate judgment on the position of the vehicle based on the existing sensor structure and signal characteristics without increasing hardware devices, finely divide the identification areas in the detection area including multiple lanes along the lane width direction, so that the snapshot device corresponding to each identification area cannot identify multiple license plates at the same time, and only one license plate can be identified, so that the vehicle in the driving lane is consistent with the vehicle snapped by the snapshot device, and the purpose of improving the vehicle identification rate is achieved.

[0112] Optionally, as a realizable way, when the vehicle passes through the weighing device 10, the weighing device 10 can also collect and update the vehicle information of the vehicle, and the vehicle information includes at least one of the following: the mark corresponding to the target identification area, the number of axles of the license plate, the wheelbase, and the axle load.

[0113] It can be understood that when the vehicle information includes the number of axles of the license plate, the wheelbase, the axle load, the number of axles, etc., the weighing device can automatically detect the speed, the axle load, the number of axles, the wheelbase, the whole vehicle weight, and the passing time, etc. of the vehicle, and can also automatically separate the vehicle and form a complete vehicle weighing information, and then match the image evidence information such as the image of the snapshot of the front, body and tail of the vehicle by the snapshot device and the short video obtained in the detection process, to realize the detection and screening of the overloading and overlength of the freight motor vehicle, and then the subsequent management of the overloading and overlength vehicle according to the law enforcement demand. In addition, when the vehicle information includes the mark corresponding to the target identification area, the corresponding picture information of the vehicle can be quickly obtained during the evidence collection.

[0114] Of course, the vehicle information can also include other contents, which can be set and changed as needed, and the embodiment of the application does not make any limitation on this.

[0115] Optionally, as a realizable way, the vehicle detection system 1 provided by the embodiment of the application can also include: an evidence collection device 30, which is in communication connection with the weighing device 10 and the shooting device 20.

[0116] Based on this, the above method further includes:

[0117] The weighing device 10 sends the vehicle information to the evidence collection device 30.

[0118] The shooting device 20 sends the target image to the evidence collection device 30.

[0119] The evidence collection device 30 matches the received vehicle information and target image with the same mark, and outputs the evidence collection result.

[0120] Since the identification area provided by the embodiment of the application is more fine, one lane includes more than one identification area, that is, some identification areas cross lanes, so that even if two vehicles are in parallel in one lane, the target identification areas determined according to the positions of the license plates of the vehicles are not the same, and therefore, in the vehicle detection method provided by the embodiment of the application, there is no case that two vehicles to be identified are in one identification area, and the problem of multi-license plate identification error in the identification area is fundamentally solved.

[0121] The embodiment of the application further provides a detection device, which includes a memory and a processor, the memory stores a computer program, and the processor is configured to execute the vehicle detection method described above by using the computer program.

[0122] The detection device provided by the embodiment of the application has the same beneficial effects as the vehicle detection method described above, and details are not repeated here.

[0123] The embodiment of the application further provides a computer readable storage medium, which stores a computer program or instructions, and when the computer reads and executes the computer program or instructions, the computer executes the vehicle detection method described above.

[0124] The computer readable storage medium provided by the embodiment of the application has the same beneficial effects as the vehicle detection method described above, and details are not repeated here.

[0125] The embodiment of the application further provides a computer program product, which includes a computer program, and when the computer program product runs on a device, the device executes the vehicle detection method described in the method embodiment.

[0126] The above-described embodiments are only used to illustrate the technical solutions of the application, rather than limit them; although the application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent ones; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application, and should be included in the protection scope of the application.

Claims

1. A vehicle inspection method, characterized in that, An application is made to a vehicle detection system that includes a position detection device and a shooting device; and in a detection area containing multiple lanes, multiple recognition areas are divided along the road width direction, the number of recognition areas being greater than the number of lanes; wherein, the shooting device includes multiple capture devices, and the capture devices are set up one-to-one with the recognition areas; The vehicle detection method includes: Once the vehicle enters the detection area, the vehicle's location information is acquired in real time through the location detection device. Based on the vehicle location information, the current identification area of ​​the vehicle is determined and used as the target identification area; A capture signal is sent to the shooting device. After receiving the capture signal, the shooting device determines the capture device corresponding to the target recognition area and instructs the determined capture device to capture the target and generate a target image; wherein the target image carries a marker corresponding to the target recognition area.

2. The vehicle detection method according to claim 1, characterized in that, Each pair of adjacent identification regions partially overlaps.

3. The vehicle inspection method according to claim 1, characterized in that, Vehicle location information is obtained through a weighing device; The weighing device includes M rows of strip sensors installed in each lane; wherein each consecutive N rows of strip sensors corresponds to a recognition area, M > N ≥ 2, and M and N are both integers.

4. The vehicle detection method according to claim 1, characterized in that, Determining the current identification area of ​​the vehicle based on its location information includes: Based on the vehicle location information, determine the location of the vehicle's license plate; Based on the determined location of the vehicle's license plate, the current identification area of ​​the vehicle is determined.

5. The vehicle inspection method according to claim 4, characterized in that, Determining the location of the vehicle's license plate based on the vehicle location information includes: Based on the vehicle position information, determine the positions of the left and right wheels of the vehicle's front axle; The license plate position is determined based on the positions of the left and right wheels of the first axle.

6. The vehicle detection method according to claim 5, characterized in that, Based on the determined location of the vehicle's license plate, the current recognition area of ​​the vehicle is determined, including: Determine the distance between the center of each of the recognition areas and the location of the license plate; The minimum value among the multiple distances is determined, and the recognition area corresponding to the minimum value is taken as the recognition area where the vehicle is currently located.

7. The vehicle inspection method according to claim 1, characterized in that, The method further includes: When the vehicle passes the position detection device, the position detection device collects and updates the vehicle information of the vehicle, which includes at least one of the following: a marker corresponding to the target recognition area, the number of axles of the vehicle, wheelbase, and axle load.

8. The vehicle inspection method according to any one of claims 1-7, characterized in that, The width of the recognition area is greater than the preset width.

9. A vehicle detection system, characterized in that, In a detection area containing multiple lanes, multiple recognition areas are divided along the road width direction, and the number of recognition areas is greater than the number of lanes; The vehicle detection system includes: A location detection device is used to acquire the vehicle's location information in real time after the vehicle enters the detection area; A data processing device is used to determine the current identification area of ​​the vehicle based on the vehicle's location information, and use it as the target identification area; and to generate and send a capture signal to the shooting device; wherein the shooting device includes multiple capture devices, and the capture devices are set up one-to-one with the identification area; The shooting device is used to receive the capture signal and capture images of vehicles within the target recognition area based on the capture signal. The shooting device is further configured to, upon receiving the capture signal, determine the capture device corresponding to the target recognition area, and instruct the determined capture device to capture and generate a target image; wherein the target image carries a marker corresponding to the target recognition area.

Images