CN115641724B - Inspection identification method, system and computer medium for managing berths in roads - Google Patents
Inspection identification method, system and computer medium for managing berths in roads Download PDFInfo
- Publication number
- CN115641724B CN115641724B CN202211119839.8A CN202211119839A CN115641724B CN 115641724 B CN115641724 B CN 115641724B CN 202211119839 A CN202211119839 A CN 202211119839A CN 115641724 B CN115641724 B CN 115641724B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- license plate
- parking space
- information
- personal computer
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims description 44
- 238000001514 detection method Methods 0.000 claims description 40
- 238000001914 filtration Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 238000007726 management method Methods 0.000 description 12
- 238000003384 imaging method Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The application provides a patrol identification method, a system and a computer medium for managing berths in roads, wherein the method comprises the following steps: the industrial personal computer of the patrol car acquires positioning information of the patrol car through the integrated navigation equipment, and associates the patrol car with a target parking space according to the positioning information; the industrial personal computer simultaneously acquires images shot by the front-view camera and the license plate camera; judging whether the vehicle is parked in the parking space according to the image shot by the front-view camera, when the vehicle is parked in the target parking space, identifying the license plate position of the vehicle, generating an identification result, when the vehicle is not parked, acquiring three-dimensional point cloud image information generated by the laser radar by the industrial personal computer, and secondarily judging whether the vehicle is parked in the parking space according to the three-dimensional point cloud image information; the inspection cloud platform receives the identification result and manages the vehicles on the parking spaces according to the identification result; the application reduces the complexity of license plate recognition and improves the efficiency of berth management.
Description
Technical Field
The application relates to the technical field of wireless sensor information acquisition, in particular to a method, a system and a computer medium for inspecting and identifying management of berths in roads.
Background
At present, with the rapid increase of the quantity of motor vehicles to be kept, the demand for parking is increasing. For the management of berths in roads, in order to reduce the time cost of manual participation and improve the efficiency of road surface inspection, a plurality of intelligent road surface inspection vehicles appear on the market. And collecting parking conditions of parking in the road by using the inspection vehicle, and shooting and evidence obtaining the vehicle on the berth.
Shooting and evidence obtaining are carried out on vehicles on berths, and the environmental information of the berths and the information of the vehicles on the berths and the license plates of the vehicles on the berths are required to be collected simultaneously. For the acquisition of the panoramic information of the berth environment, a wider visual field range is required, and a camera with a smaller focal length is required to shoot and obtain evidence. However, for the camera with smaller focal length, the license plate information shot by the camera is displayed in the image less, and often is displayed unclear, so that the license plate recognition algorithm is inaccurate in recognition, and a background customer service person is required to correct, or a road surface worker is required to perform supplementary shooting and evidence obtaining. This adds virtually to the cost of labor involved.
The parking evidence obtaining and license plate recognition in the prior art are completed by adopting the image shot by the same camera, and the problems are that: scene pictures shot by the evidence obtaining images should be relatively wide, so that not only the complete vehicle and the surrounding environment of the parking space where the vehicle is located are required to be shot, but also the berth numbers can be seen clearly in the photos; meanwhile, the traditional detection technology is easy to carry out false detection on vehicles in the left road of the berth and vehicles on the right road of the berth, so that false charge is caused.
Disclosure of Invention
The application mainly aims to provide a patrol identification method, a system and a computer medium for in-road berth management, which are used for reducing the complexity of license plate identification, improving the speed and the accuracy of license plate identification and improving the efficiency of berth management.
In order to solve the technical problems, the application has the following technical scheme:
in a first aspect, the application provides a patrol identification system for managing berths in roads, which comprises a patrol vehicle and a patrol cloud platform; the inspection vehicle comprises:
the camera acquisition module is used for acquiring a parking space image and a license plate image;
the integrated navigation module is used for acquiring positioning information of the inspection vehicle through integrated navigation equipment and sending the positioning information to the industrial personal computer;
the laser radar module is used for collecting three-dimensional point cloud image information of the vehicle and assisting in judging whether the vehicle is parked on the berth or not;
the industrial personal computer is used for judging whether the vehicle is parked in the parking space according to the parking space image shot by the front-view camera, when the vehicle is parked in the target parking space, identifying the license plate position of the vehicle, generating an identification result aiming at the target parking space, and sending the identification result to the inspection cloud platform; when judging that the vehicle is not parked, the industrial personal computer acquires three-dimensional point cloud image information generated by the laser radar, and judges whether the vehicle is parked on the parking space for the second time according to the three-dimensional point cloud image information;
the POE switch is used for respectively transmitting the parking space image and the license plate image acquired by the camera acquisition module to the industrial personal computer and the ARM computing unit;
the ARM computing unit is provided with a GPU coprocessor and is used for convolution operation of a laser radar three-dimensional target detection algorithm and a license plate recognition algorithm;
the 4G router is used for connecting the industrial personal computer, receiving the identification result sent by the industrial personal computer and transmitting the identification result to the routing inspection cloud platform;
and the inspection platform receives the identification result and manages the vehicles on the parking spaces according to the identification result. Optionally, the camera acquisition module includes: a front view camera, a middle view camera, a license plate camera and a rear view camera; the cameras are configured in the same local area network, and data are forwarded to the ARM computing unit and the industrial personal computer through the switch.
Optionally, different transmission network segments are set for external data transmission for the camera acquisition module, the laser radar module and the integrated navigation module, so that data among the modules are isolated.
Optionally, the network segment where the external data transmitted by the camera acquisition module is located is 192.168.3.X; the laser radar module transmits the external data in the network segment 192.168.1.X; the integrated navigation module transmits the external data to the network segment 192.168.2.X.
Optionally, the industrial personal computer acquires the three-dimensional point cloud image information, and is used for performing secondary judgment on whether the vehicle is parked on the parking space or not, and specifically includes: starting a point cloud analysis algorithm to acquire a current latest point cloud frame; performing point cloud filtering according to a preset range, only reserving point cloud data of a target area, filtering out ground points by utilizing laser radar height information and a plane estimation algorithm, performing target segmentation according to point cloud clustering, and classifying by using a support vector machine model; judging whether a vehicle point cloud target occupies a current parking space area according to the positions of the vehicle and the pre-collected parking space, if the vehicle point cloud target is classified as a vehicle, judging that the parking space is on, and if the vehicle point cloud target is not present, judging that the parking space is off.
Optionally, the identifying the license plate according to the photographed image specifically includes: the industrial personal computer takes license plate image information at the same moment after reaching a parking space from a license plate camera image queue; and analyzing whether license plates exist in the corresponding image sensing areas, and if so, identifying license plate numbers.
Optionally, the industrial personal computer identifies the license plate position of the vehicle through an identification algorithm, judges whether shielding exists, and identifies license plate information if the license plate position is identified and the license plate position is not shielded; the industrial personal computer is used for calling the picture information acquired by the cameras of three recent license plates, synchronously identifying the license plate information of the picture, and selecting one picture with the highest license plate information identification confidence as a license plate identification result.
In a second aspect, the application provides a patrol identification method for managing berths in a road, which is applied to a patrol vehicle, and the method comprises the following steps:
step 101, an industrial personal computer of the patrol car acquires positioning information of the patrol car through integrated navigation equipment, and associates the patrol car with a target parking space according to the positioning information;
step 102, when the patrol vehicle runs to a target parking space, the industrial personal computer simultaneously acquires images shot by the front-view camera and the license plate camera;
step 103, judging whether the vehicle is parked in the parking space according to the image shot by the front-view camera, when judging that the vehicle is parked in the target parking space, identifying the license plate position of the vehicle, generating an identification result aiming at the target parking space, and sending the identification result to a patrol cloud platform; when judging that the vehicle is not parked, the industrial personal computer acquires three-dimensional point cloud image information generated by the laser radar, and judges whether the vehicle is parked on the parking space for the second time according to the three-dimensional point cloud image information;
and 104, receiving the identification result by the inspection cloud platform, and managing the vehicles on the parking spaces according to the identification result.
Optionally, pre-calibrating berth calibration information, wherein the berth calibration information comprises longitude and latitude and inspection course angle information; in the process of inspecting the inspection vehicle, the industrial personal computer receives the positioning information output by the integrated navigation equipment in real time, compares the positioning information with the pre-calibrated berth calibration information, judges whether the inspection vehicle enters a specified berth acquisition area, establishes a one-to-one correspondence between the photographed evidence obtaining pictures and the berths, and is used for completing the association between the inspection vehicle and a target parking space.
Optionally, the industrial personal computer judges that the inspection vehicle enters a specified berth acquisition area, and simultaneously acquires images shot by the front-view camera and the license plate camera; the images shot by the front-view camera are the latest front-view images taken out of the front-view camera image queue, namely the parking space image information at the same moment after the parking space is reached; and analyzing the parking space state according to the parking space image shot by the front-view camera, wherein the analysis comprises the step of judging whether the vehicle is parked or not by using a deep learning target classification recognition algorithm.
Optionally, if the target parking space is judged to be parked with the vehicle, the industrial personal computer identifies the license plate position of the vehicle through an identification algorithm, judges whether shielding exists, and if the license plate position is identified and the license plate information is not shielded, the industrial personal computer identifies the license plate information; meanwhile, the industrial personal computer invokes the picture information acquired by the three recent license plate cameras, synchronously carries out license plate information identification on the picture, selects one picture with the highest confidence coefficient of a license plate information identification algorithm as a license plate identification result of the picture shot by the license plate camera, carries out similarity comparison on the license plate identification information of the picture shot by the front-view camera and the license plate camera, takes the license plate identification information of the picture shot by the license plate camera as a parking vehicle license plate identification result of the parking place if the comparison result is similar, and takes the license plate identification information of the picture shot by the front-view camera as the parking vehicle license plate identification result of the parking place if the comparison result is not similar.
Optionally, if the license plate position cannot be identified or the license plate is judged to be blocked, the industrial personal computer controls the middle camera and the rearview camera to perform supplementary shooting on the vehicle on the parking space along with the advance of the inspection vehicle, and positions the license plate; if the license plate position can be positioned, license plate recognition is carried out, and the license plate information recognition algorithm with higher confidence coefficient is taken as a recognition result.
Optionally, when it is determined that the vehicle is not parked, the industrial personal computer acquires the three-dimensional point cloud image information, and the method for performing secondary determination on whether the vehicle is parked on the parking space specifically includes: starting a point cloud analysis algorithm to acquire a current latest point cloud frame; performing point cloud filtering according to a preset range, only reserving point cloud data of a target area, filtering out ground points by utilizing laser radar height information and a plane estimation algorithm, performing target segmentation according to point cloud clustering, and classifying by using a support vector machine model; judging whether a vehicle point cloud target occupies a current parking space area according to the positions of the vehicle and the pre-collected parking space, if the vehicle point cloud target is classified as a vehicle, judging that the parking space is on, and if the vehicle point cloud target is not present, judging that the parking space is off.
In a third aspect, embodiments of the present application provide a computer medium having a computer program stored thereon, which when executed by a processor implements an inspection method for in-way berth management as described in the previous embodiments
Drawings
Fig. 1 is a schematic diagram of an inspection system for managing berths in a road according to an embodiment of the present application;
fig. 2 is a flow chart of an inspection method for managing berths in a road according to an embodiment of the application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by one of ordinary skill in the art without creative efforts, are within the scope of the present application based on the embodiments of the present application.
The embodiment of the application provides a patrol identification system for managing berths in roads, which is shown in fig. 1, and comprises a patrol vehicle and a patrol cloud platform; the inspection vehicle comprises:
the camera acquisition module is used for acquiring a parking space image and a license plate image;
optionally, the camera acquisition module includes: a front view camera, a middle view camera, a license plate camera and a rear view camera; the cameras are configured in the same local area network, and data are forwarded to the ARM computing unit and the industrial personal computer through the switch.
Optionally, the front view camera adopts a focal length of 4mm, the license plate camera adopts a focal length of 12mm, the middle view camera adopts a focal length of 2.8mm, and the rear view camera is the same as the front view camera and also has a focal length of 4 mm; the license plate adopts a large-focal-length camera to amplify the license plate of the vehicle in the imaging of the picture.
Optionally, the camera installation principle is, along the vehicle inspection advancing direction, can shoot the berth information that needs to gather, and leading panorama camera and license plate camera shoot the direction unanimous, and license plate camera can shoot the complete license plate information of berth parked vehicle.
Optionally, the camera acquisition module is connected to the POE switch through a 192.168.3.X network segment, and transmits the photographed image to the POE switch through an RTSP multicast mode.
Optionally, the front view camera uses a camera with a smaller focal length to capture environmental panoramic information including berthing vehicles for evidence collection.
The integrated navigation module is used for acquiring positioning information of the inspection vehicle through integrated navigation equipment and sending the positioning information to the industrial personal computer;
optionally, the integrated navigation module outputs the positioning information of the inspection vehicle to the industrial personal computer through the network port at the frequency of 100HZ; the integrated navigation module is connected to a designated network port of the industrial personal computer through a 192.168.2.X network segment.
The laser radar module is used for collecting three-dimensional point cloud image information of the vehicle and assisting in judging whether the vehicle is parked on the berth or not;
optionally, the laser radar module sends the three-dimensional point cloud image information to a designated network port of the ARM computing unit through a 192.168.1.X network segment.
The industrial personal computer is used for judging whether the vehicle is parked in the parking space according to the parking space image shot by the front-view camera, when the vehicle is parked in the target parking space, identifying the license plate position of the vehicle, generating an identification result aiming at the target parking space, and sending the identification result to the inspection cloud platform; when judging that the vehicle is not parked, the industrial personal computer acquires three-dimensional point cloud image information generated by the laser radar, and judges whether the vehicle is parked on the parking space or not secondarily according to the three-dimensional point cloud image information.
Optionally, pre-calibrating berth calibration information, wherein the berth calibration information comprises longitude and latitude and inspection course angle information; in the process of inspecting the inspection vehicle, the industrial personal computer receives the positioning information output by the integrated navigation module in real time, compares the positioning information with the pre-calibrated berth calibration information, judges whether the inspection vehicle enters a specified berth acquisition area, and establishes a one-to-one correspondence between the photographed evidence-taking pictures and the berths.
Optionally, the industrial personal computer judges that the inspection vehicle enters a specified berth acquisition area, and simultaneously acquires images shot by the front-view camera and the license plate camera; the images shot by the front-view camera are the latest front-view images taken out of the front-view camera image queue, namely the parking space image information at the same moment after the parking space is reached; and analyzing the parking space state according to the parking space image shot by the front-view camera, wherein the analysis comprises the step of judging whether the vehicle is parked or not by using a deep learning target classification recognition algorithm.
Optionally, if the target parking space is judged to be parked with the vehicle, the industrial personal computer identifies the license plate position of the vehicle through an identification algorithm, judges whether shielding exists, and if the license plate position is identified and the license plate information is not shielded, the industrial personal computer identifies the license plate information; meanwhile, the industrial personal computer invokes the picture information acquired by the three recent license plate cameras, synchronously carries out license plate information identification on the picture, selects one picture with the highest confidence coefficient of a license plate information identification algorithm as a license plate identification result of the picture shot by the license plate camera, carries out similarity comparison on the license plate identification information of the picture shot by the front-view camera and the license plate camera, takes the license plate identification information of the picture shot by the license plate camera as a parking vehicle license plate identification result of the parking place if the comparison result is similar, and takes the license plate identification information of the picture shot by the front-view camera as the parking vehicle license plate identification result of the parking place if the comparison result is not similar.
Optionally, if the license plate position cannot be identified or the license plate is judged to be blocked, the industrial personal computer controls the middle camera and the rearview camera to perform supplementary shooting on the vehicle on the parking space along with the advance of the inspection vehicle, and positions the license plate; if the license plate position can be positioned, license plate recognition is carried out, and the license plate information recognition algorithm with higher confidence coefficient is taken as a recognition result.
Optionally, if the industrial personal computer determines that the vehicle is parked at the parking space, the industrial personal computer classifies the identified vehicle, and the classification specifically includes: the identified vehicles are classified into vehicles containing license plate information such as cars, trucks and the like, are used for carrying out berth management charging, and are used for filtering vehicles such as tricycles, bicycles, carts and the like which cannot carry out charging management.
Optionally, before analyzing the parking space state according to the parking space image shot by the front-view camera, performing association between the front-view camera and the license plate camera, where the association specifically includes: and (3) comparing the similarity between the license plate image shot by the front-view camera and the license plate image shot by the license plate camera, wherein the threshold value of the similarity is set to be 60%, namely, comparing each character in the two license plate images, and if the characters are more than 60%, the correlation of the parking space parking vehicle information shot by the two cameras is completed, and finally taking the license plate identification information of the pictures shot by the license plate cameras as a license plate identification result.
Optionally, in the comparison of license plate recognition information of the pictures shot by the front-view camera and the license plate camera, if the license plate recognition result of the license plate camera has different license plate lengths, the position of each character of the license plate recognition result of the license plate camera can be compared with the corresponding position of the license plate recognition result of the front-view camera and the front-back position characters thereof, and if one position is consistent, the recognized characters are judged to be identical.
Optionally, if the comparison similarity of license plate identification information of the pictures shot by the front-view camera and the license plate camera is lower than a set threshold, the vehicle color and license plate color information of the pictures shot by the front-view camera and the license plate camera can be further identified and compared, if the vehicle color and the license plate color information are consistent, the correlation of the parking space parking vehicle information shot by the two cameras is completed, and the license plate identification information of the pictures shot by the license plate camera is selected as an identification result.
Optionally, under the condition of failure of association, images shot by the three license plate cameras can be acquired again to carry out license plate recognition and are compared with the front panoramic camera in similarity, so that the success rate of association is improved.
Optionally, when it is determined that the vehicle is not parked, the industrial personal computer acquires the three-dimensional point cloud image information, and the method for performing secondary determination on whether the vehicle is parked on the parking space specifically includes: starting a point cloud analysis algorithm to acquire a current latest point cloud frame; performing point cloud filtering according to a preset range, only reserving point cloud data of a target area, filtering out ground points by utilizing laser radar height information and a plane estimation algorithm, performing target segmentation according to point cloud clustering, and classifying by using a support vector machine model; judging whether a vehicle point cloud target occupies a current parking space area according to the positions of the vehicle and the pre-collected parking space, if the vehicle point cloud target is classified as a vehicle, judging that the parking space is on, and if the vehicle point cloud target is not present, judging that the parking space is off.
Optionally, preset limiting conditions, and judging whether a vehicle exists on the parking space for multiple times and acquiring license plate information according to the limiting conditions; the limiting conditions comprise whether the detection area of the parking space is exceeded or not, and the size of the detection area is set and adjusted according to the range from the detection starting position to the detection ending position, the length of the parking space and the running speed of the vehicle. And synthesizing the detection information of multiple rounds, and sequencing the detection results according to the confidence level.
Optionally, the industrial personal computer gathers the parking space state, license plate number and corresponding confidence coefficient of the current parking space obtained by multiple times of detection, and verifies the parking space state, license plate number and corresponding confidence coefficient, and the verification specifically comprises: and acquiring the collected multiple detection results and the confidence coefficient thereof, and starting the verification of the vehicle type when the confidence coefficient of the detection results is 0, wherein the fact that the vehicle is not a normal passenger vehicle and cannot charge, such as delivery of express tricycles, is indicated by the fact that no vehicle license plate is detected or identified. When the confidence coefficient of the detection result is lower than 90, the reliability of the license plate recognition result is insufficient, and a secondary confirmation is needed by using different recognition algorithms, if the secondary recognition result is consistent with the given result, the confidence coefficient of the first recognition of the license plate is not high, but the correct probability is high, and the confidence coefficient of the license plate recognition is corrected. If the confidence is lower than a certain threshold, parking space line detection is needed, and whether the vehicle is far away from the parking space line or not is analyzed, which may be false detection of the vehicle on the road, because the imaging range of the license plate is smaller and the imaging effect of the license plate is poor in the common situation. The position relation between the vehicle detection area and the parking space line needs to be judged, if no intersection of the vehicle detection area and the parking space line exists, the result is misdetection, and correction is needed.
Optionally, identifying the license plate according to the photographed image, and generating an identification result for the target parking space specifically includes: the industrial personal computer encapsulates the corrected identification result and sends the encapsulated identification result to a 4G router, and the detection result is sent to a patrol cloud platform through the 4G router; the identification result comprises license plate identification information and evidence obtaining pictures shot by all cameras.
Optionally, the industrial personal computer is specifically designed by adopting an X86 platform, and at least has 3 network ports, 3 network segments, and 192.168.0.X network segments are external network segments connected with the 4G router, and upload data to the inspection cloud platform; the 192.168.2.X network segment is a network port connected with the integrated navigation module, and the data transmission frequency is 100HZ; the 192.168.3.X network segment is a network port connected with the POE switch, and acquires the data of the front-view cameras, the middle-view cameras and the rear-view cameras, and meanwhile, the industrial personal computer is connected with the ARM computing unit.
And the POE switch is used for forwarding the parking space image and the license plate image acquired by the camera acquisition module to the industrial personal computer and the ARM computing unit.
Specifically, the camera acquisition module forwards the acquired image data of the front-view cameras, the middle-view cameras and the rear-view cameras to a POE switch, and the POE switch sends the image data to a designated network port of an industrial personal computer through a 192.168.3.X network segment; and forwarding the license plate image acquired by the license plate camera to an ARM computing unit through the POE switch.
The ARM computing unit is provided with a GPU coprocessor and is used for convolution operation of a laser radar three-dimensional target detection algorithm and a license plate recognition algorithm;
alternatively, the laser radar three-dimensional target detection algorithm and the license plate recognition algorithm both involve a large number of convolution operations and data parallel processing, so that the GPU with a coprocessor is adopted for calculation.
Optionally, the ARM computing unit is provided with at least 2 network ports, and the network segments are 192.168.3.X and 192.168.1.X respectively; 192.168.3.X is used for obtaining license plate camera data, and 192.168.1.X is used for obtaining laser radar data.
The 4G router is used for being connected with the industrial personal computer, receiving the identification result sent by the industrial personal computer and transmitting the identification result to the routing inspection cloud platform.
And the inspection cloud platform receives the identification result and manages the vehicles on the parking spaces according to the identification result. Optionally, the managing specifically includes: the inspection cloud platform receives identification results containing license plate identification information and evidence obtaining pictures shot by all cameras, and the identification results are used as a basis for parking space management charging and are used for managing vehicles on a parking space.
The embodiment of the application provides a patrol identification method for in-road berth management, which is applied to a patrol vehicle, wherein the patrol vehicle comprises an industrial personal computer; as shown in fig. 2, the method includes:
and 101, acquiring positioning information of the patrol car by the industrial personal computer of the patrol car through integrated navigation equipment, and associating the patrol car with a target parking space according to the positioning information.
Optionally, after the integrated navigation equipment acquires the positioning information of the inspection vehicle, outputting the positioning information of the inspection vehicle to the industrial personal computer through the network port at the frequency of 100HZ; the integrated navigation module is connected to a designated network port of the industrial personal computer through a 192.168.2.X network segment.
Optionally, the inspection vehicle inspects along the inspection track at a speed of 20-25 km/h, and the inspection vehicle can be provided with combined navigation equipment and pre-marks berth calibration information, wherein the berth calibration information comprises longitude and latitude and inspection course angle information; in the process of inspecting the inspection vehicle, the industrial personal computer receives the positioning information output by the integrated navigation module in real time, compares the positioning information with the pre-calibrated berth calibration information, judges whether the inspection vehicle enters a specified berth acquisition area, establishes a one-to-one correspondence between the photographed evidence obtaining pictures and the berths, and is used for completing the association between the inspection vehicle and a target parking space.
And 102, when the patrol vehicle runs to the target parking space, the industrial personal computer simultaneously acquires images shot by the front-view camera and the license plate camera.
Optionally, when the inspection vehicle is about to travel to a position with a distance of about 2.5 meters from a position to be photographed, the industrial personal computer simultaneously collects images photographed by the front-view camera and the license plate camera.
Step 103, judging whether the vehicle is parked in the parking space according to the image shot by the front-view camera, when judging that the vehicle is parked in the target parking space, identifying the license plate position of the vehicle, generating an identification result aiming at the target parking space, and sending the identification result to a patrol cloud platform; when judging that the vehicle is not parked, the industrial personal computer acquires three-dimensional point cloud image information generated by the laser radar, and judges whether the vehicle is parked on the parking space or not secondarily according to the three-dimensional point cloud image information.
Optionally, the industrial personal computer judges that the inspection vehicle enters a specified berth acquisition area, and simultaneously acquires images shot by the front-view camera and the license plate camera; the images shot by the front-view camera are the latest front-view images taken out of the front-view camera image queue, namely the parking space image information at the same moment after the parking space is reached; and analyzing the parking space state according to the parking space image shot by the front-view camera, wherein the analysis comprises the step of judging whether the vehicle is parked or not by using a deep learning target classification recognition algorithm.
Optionally, if the target parking space is judged to stop the vehicle, the industrial personal computer identifies the license plate position of the vehicle through a license plate identification algorithm, judges whether shielding exists, and if the license plate position is identified and the shielding does not exist, the industrial personal computer identifies license plate information; meanwhile, the industrial personal computer invokes the picture information acquired by the three recent license plate cameras, synchronously carries out license plate information identification on the picture, selects one picture with the highest confidence coefficient of a license plate information identification algorithm as a license plate identification result of the picture shot by the license plate camera, carries out similarity comparison on the license plate identification information of the picture shot by the front-view camera and the license plate camera, takes the license plate identification information of the picture shot by the license plate camera as a parking vehicle license plate identification result of the parking place if the comparison result is similar, and takes the license plate identification information of the picture shot by the front-view camera as the parking vehicle license plate identification result of the parking place if the comparison result is not similar.
Optionally, if the license plate position cannot be identified or the license plate is judged to be blocked, the industrial personal computer controls the middle camera and the rearview camera to perform supplementary shooting on the vehicle on the parking space along with the advance of the inspection vehicle, and positions the license plate; if the license plate position can be positioned, license plate recognition is carried out, and the license plate information recognition algorithm with higher confidence coefficient is taken as a recognition result.
Optionally, if the industrial personal computer determines that the vehicle is parked at the parking space, the industrial personal computer classifies the identified vehicle, and the classification specifically includes: the identified vehicles are classified into vehicles containing license plate information such as cars, trucks and the like, are used for carrying out berth management charging, and are used for filtering vehicles such as tricycles, bicycles, carts and the like which cannot carry out charging management.
Optionally, before analyzing the parking space state according to the parking space image shot by the front-view camera, performing association between the front-view camera and the license plate camera, where the association specifically includes: and (3) comparing the similarity between the license plate image shot by the front-view camera and the license plate image shot by the license plate camera, wherein the threshold value of the similarity is set to be 60%, namely, comparing each character in the two license plate images, and if the characters are more than 60%, the correlation of the parking space parking vehicle information shot by the two cameras is completed, and finally taking the license plate identification information of the pictures shot by the license plate cameras as a license plate identification result.
Optionally, in the comparison of license plate recognition information of the pictures shot by the front-view camera and the license plate camera, if the license plate recognition result of the license plate camera has different license plate lengths, the position of each character of the license plate recognition result of the license plate camera can be compared with the corresponding position of the license plate recognition result of the front-view camera and the front-back position characters thereof, and if one position is consistent, the recognized characters are judged to be identical.
Optionally, if the comparison similarity of license plate identification information of the pictures shot by the front-view camera and the license plate camera is lower than a set threshold, the vehicle color and license plate color information of the pictures shot by the front-view camera and the license plate camera can be further identified and compared, if the vehicle color and the license plate color information are consistent, the correlation of the parking space parking vehicle information shot by the two cameras is completed, and the license plate identification information of the pictures shot by the license plate camera is selected as an identification result.
Optionally, under the condition of failure of association, images shot by the three license plate cameras can be acquired again to carry out license plate recognition and are compared with the front panoramic camera in similarity, so that the success rate of association is improved.
Optionally, when it is determined that the vehicle is not parked, the industrial personal computer acquires the three-dimensional point cloud image information, and the method for performing secondary determination on whether the vehicle is parked on the parking space specifically includes: starting a point cloud analysis algorithm to acquire a current latest point cloud frame; performing point cloud filtering according to a preset range, only reserving point cloud data of a target area, filtering out ground points by utilizing laser radar height information and a plane estimation algorithm, performing target segmentation according to point cloud clustering, and classifying by using a support vector machine model; judging whether a vehicle point cloud target occupies a current parking space area according to the positions of the vehicle and the pre-collected parking space, if the vehicle point cloud target is classified as a vehicle, judging that the parking space is on, and if the vehicle point cloud target is not present, judging that the parking space is off.
Optionally, when the secondary judgment determines that the vehicle stops on the target parking space, the industrial personal computer continues to judge whether the vehicle stops on the parking space according to the image shot by the front-view camera and carries out license plate position recognition of the vehicle.
Optionally, preset limiting conditions, and judging whether a vehicle exists on the parking space for multiple times and acquiring license plate information according to the limiting conditions; the limiting conditions comprise whether the detection area of the parking space is exceeded or not, and the size of the detection area is set and adjusted according to the range from the detection starting position to the detection ending position, the length of the parking space and the running speed of the vehicle. And synthesizing the detection information of multiple rounds, and sequencing the detection results according to the confidence level.
Optionally, the industrial personal computer gathers the parking space state, license plate number and corresponding confidence coefficient of the current parking space obtained by multiple times of detection, and verifies the parking space state, license plate number and corresponding confidence coefficient, and the verification specifically comprises: and acquiring the collected multiple detection results and the confidence coefficient thereof, and starting the verification of the vehicle type when the confidence coefficient of the detection results is 0, wherein the fact that the vehicle is not a normal passenger vehicle and cannot charge, such as delivery of express tricycles, is indicated by the fact that no vehicle license plate is detected or identified. When the confidence coefficient of the detection result is lower than 90, the reliability of the license plate recognition result is insufficient, and a secondary confirmation is needed by using different recognition algorithms, if the secondary recognition result is consistent with the given result, the confidence coefficient of the first recognition of the license plate is not high, but the correct probability is high, and the confidence coefficient of the license plate recognition is corrected. If the confidence is lower than a certain threshold, parking space line detection is needed, and whether the vehicle is far away from the parking space line or not is analyzed, which may be false detection of the vehicle on the road, because the imaging range of the license plate is smaller and the imaging effect of the license plate is poor in the common situation. The position relation between the vehicle detection area and the parking space line needs to be judged, if no intersection of the vehicle detection area and the parking space line exists, the result is misdetection, and correction is needed.
Optionally, after the patrol car is associated with the target parking space, sending indication information containing the number of the target parking space to an industrial personal computer, a laser radar module and an ARM computing unit at the same time, and receiving the indication information by the industrial personal computer to analyze the parking space state of the target parking space and judge whether the target parking space has a car or not; after receiving the indication information, the laser radar module generates three-dimensional point cloud image information aiming at a target parking space; after receiving the indication information, the ARM computing unit carries out convolution operation on the laser radar three-dimensional target detection algorithm and the license plate recognition algorithm to judge whether a vehicle exists on a target parking space or not and recognize a license plate of the vehicle. The industrial personal computer gathers the detection results of the multiple detection, and sorts the detection results of the multiple detection according to the confidence level.
And 104, receiving the identification result by the inspection cloud platform, and managing the vehicles on the parking spaces according to the identification result.
Optionally, the managing specifically includes: the inspection cloud platform receives identification results containing license plate identification information and evidence obtaining pictures shot by all cameras, and the identification results are used as a basis for parking space management charging and are used for managing vehicles on a parking space.
The application provides a scheme of adopting two cameras, wherein one camera is used for comprehensively obtaining evidence, and the other camera is specially used for license plate recognition. The results of the two paths of cameras are synchronized through a fusion algorithm, and are calibrated and filtered through a result verification module. Finally, the evidence obtaining images and the license plate recognition images are in one-to-one correspondence, so that the effect of the evidence obtaining images is guaranteed, the accuracy of license plate recognition is guaranteed, and the manual intervention rate is reduced. In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may be physically included separately, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.
The integrated units implemented in the form of software functional units described above may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform part of the steps of the transceiving method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
While the foregoing is directed to the preferred embodiments of the present application, it will be appreciated by those skilled in the art that various modifications and changes can be made without departing from the principles of the present application, and such modifications and changes are intended to be within the scope of the present application.
Claims (9)
1. The utility model provides a system is discerned in inspection of road berth management which characterized in that: the system comprises a patrol vehicle and a patrol cloud platform;
the inspection vehicle comprises:
the camera acquisition module is used for acquiring a parking space image and a license plate image; the camera acquisition module comprises: a front view camera, a middle view camera, a license plate camera and a rear view camera; the cameras are configured in the same local area network, and data are forwarded to the ARM computing unit and the industrial personal computer through the switch;
the integrated navigation module is used for acquiring positioning information of the inspection vehicle through integrated navigation equipment and sending the positioning information to the industrial personal computer;
the laser radar module is used for collecting three-dimensional point cloud image information of the vehicle and assisting in judging whether the vehicle is parked on the berth or not;
the industrial personal computer is used for judging whether the vehicle is parked in the parking space according to the parking space image shot by the front-view camera, when the vehicle is parked in the target parking space, identifying the license plate position of the vehicle, generating an identification result aiming at the target parking space, and sending the identification result to the inspection cloud platform; when judging that the vehicle is not parked, the industrial personal computer acquires three-dimensional point cloud image information generated by the laser radar, and judges whether the vehicle is parked on the parking space for the second time according to the three-dimensional point cloud image information;
the POE switch is used for respectively transmitting the parking space image and the license plate image acquired by the camera acquisition module to the industrial personal computer and the ARM computing unit;
the industrial personal computer takes license plate image information at the same moment after reaching a parking space from a license plate camera image queue; analyzing whether license plates exist in the corresponding image sensing areas, and if so, recognizing license plate numbers;
the industrial personal computer identifies the license plate position of the vehicle through an identification algorithm, judges whether shielding exists, and identifies license plate information if the license plate position is identified and the license plate position is not shielded; the industrial personal computer is used for calling the picture information acquired by the cameras of three recent license plates, synchronously identifying the license plate information of the picture, and selecting a picture with the highest license plate information identification confidence as a license plate identification result;
the ARM computing unit is provided with a GPU coprocessor and is used for convolution operation of a laser radar three-dimensional target detection algorithm and a license plate recognition algorithm;
the 4G router is used for connecting the industrial personal computer, receiving the identification result sent by the industrial personal computer and forwarding the identification result to the inspection cloud platform;
and the inspection cloud platform receives the identification result and manages the vehicles on the parking spaces according to the identification result.
2. The in-road berth management patrol identification system of claim 1, wherein: different transmission network segments are arranged for external data transmission of the camera acquisition module, the laser radar module and the integrated navigation module, so that data among the modules are isolated.
3. The in-road berth management patrol identification system of claim 2, wherein: the network segment of the external data transmission of the camera acquisition module is 192.168.3.X; the laser radar module transmits the external data in the network segment 192.168.1.X; the integrated navigation module transmits the external data to the network segment 192.168.2.X.
4. The in-road berth management patrol identification system of claim 1, wherein: when judging that the vehicle is not parked, the industrial personal computer acquires the three-dimensional point cloud image information and is used for carrying out secondary judgment on whether the vehicle is parked on the parking space or not, and the method specifically comprises the following steps: starting a point cloud analysis algorithm to acquire a current latest point cloud frame; performing point cloud filtering according to a preset range, only reserving point cloud data of a target area, filtering out ground points by utilizing laser radar height information and a plane estimation algorithm, performing target segmentation according to point cloud clustering, and classifying by using a support vector machine model; judging whether a vehicle point cloud target occupies a current parking space area according to the positions of the vehicle and the pre-collected parking space, if the vehicle point cloud target is classified as a vehicle, judging that the parking space is on, and if the vehicle point cloud target is not present, judging that the parking space is off.
5. A patrol identification method for managing berths in roads is characterized in that: the method is applied to the inspection vehicle and comprises the following steps:
step 101, an industrial personal computer of the patrol car acquires positioning information of the patrol car through integrated navigation equipment, and associates the patrol car with a target parking space according to the positioning information;
step 102, when the patrol vehicle runs to a target parking space, the industrial personal computer simultaneously acquires images shot by the front-view camera and the license plate camera;
step 103, judging whether the vehicle is parked in the parking space according to the image shot by the front-view camera, when judging that the vehicle is parked in the target parking space, identifying the license plate position of the vehicle, generating an identification result aiming at the target parking space, and sending the identification result to a patrol cloud platform; when judging that the vehicle is not parked, the industrial personal computer acquires three-dimensional point cloud image information generated by the laser radar, and judges whether the vehicle is parked on the parking space for the second time according to the three-dimensional point cloud image information;
if the target parking space is judged to stop the vehicle, the industrial personal computer identifies the license plate position of the vehicle through an identification algorithm, judges whether shielding exists, and if the license plate position is identified and the shielding does not exist, the industrial personal computer identifies license plate information; meanwhile, the industrial personal computer invokes the picture information acquired by the three recent license plate cameras, synchronously carries out license plate information identification on the picture, selects a picture with highest confidence coefficient of a license plate information identification algorithm as a license plate identification result of the picture shot by the license plate camera, carries out similarity comparison on the license plate identification information of the picture shot by the front-view camera and the license plate camera, takes the license plate identification information of the picture shot by the license plate camera as a license plate identification result of the parked vehicle at the berth if the comparison result is similar, and takes the license plate identification information of the picture shot by the front-view camera as the license plate identification result of the parked vehicle at the berth if the comparison result is not similar;
if the license plate position cannot be identified or the license plate is judged to be blocked, the industrial personal computer controls the middle camera and the rearview camera to carry out supplementary shooting on the vehicle on the parking space along with the advance of the inspection vehicle, and positions the license plate; if the license plate position can be positioned, license plate recognition is carried out, and a license plate information recognition algorithm with higher confidence coefficient is taken as a recognition result;
and 104, receiving the identification result by the inspection cloud platform, and managing the vehicles on the parking spaces according to the identification result.
6. The method for patrol identification of in-road berth management according to claim 5, wherein: pre-calibrating berth calibration information, wherein the berth calibration information comprises longitude and latitude and tour inspection course angle information; in the process of inspecting the inspection vehicle, the industrial personal computer receives the positioning information output by the integrated navigation equipment in real time, compares the positioning information with the pre-calibrated berth calibration information, judges whether the inspection vehicle enters a specified berth acquisition area, establishes a one-to-one correspondence between the photographed evidence obtaining pictures and the berths, and is used for completing the association between the inspection vehicle and a target parking space.
7. The method for patrol identification of in-road berth management according to claim 6, wherein: the industrial personal computer judges that the inspection vehicle enters a specified berth acquisition area, and simultaneously acquires images shot by the front-view camera and the license plate camera; the images shot by the front-view camera are the latest front-view images taken out of the front-view camera image queue, namely the parking space image information at the same moment after the parking space is reached; and analyzing the parking space state according to the parking space image shot by the front-view camera, wherein the analysis comprises the step of judging whether the vehicle is parked or not by using a deep learning target classification recognition algorithm.
8. The method for patrol identification of in-road berth management according to claim 5, wherein: when judging that the vehicle is not parked, the industrial personal computer acquires the three-dimensional point cloud image information, and is used for carrying out secondary judgment on whether the vehicle is parked on the parking space or not, and specifically comprises the following steps: starting a point cloud analysis algorithm to acquire a current latest point cloud frame; performing point cloud filtering according to a preset range, only reserving point cloud data of a target area, filtering out ground points by utilizing laser radar height information and a plane estimation algorithm, performing target segmentation according to point cloud clustering, and classifying by using a support vector machine model; judging whether a vehicle point cloud target occupies a current parking space area according to the positions of the vehicle and the pre-collected parking space, if the vehicle point cloud target is classified as a vehicle, judging that the parking space is on, and if the vehicle point cloud target is not present, judging that the parking space is off.
9. A computer medium having stored thereon a computer program which when executed by a processor implements the method of patrol identification for in-road berth management of any one of claims 5-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211119839.8A CN115641724B (en) | 2022-09-15 | 2022-09-15 | Inspection identification method, system and computer medium for managing berths in roads |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211119839.8A CN115641724B (en) | 2022-09-15 | 2022-09-15 | Inspection identification method, system and computer medium for managing berths in roads |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115641724A CN115641724A (en) | 2023-01-24 |
| CN115641724B true CN115641724B (en) | 2023-10-27 |
Family
ID=84940987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211119839.8A Active CN115641724B (en) | 2022-09-15 | 2022-09-15 | Inspection identification method, system and computer medium for managing berths in roads |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115641724B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109767626A (en) * | 2018-12-20 | 2019-05-17 | 北京筑梦园科技有限公司 | A kind of curb parking method for inspecting, system, cruiser and server |
| CN112949530A (en) * | 2021-03-12 | 2021-06-11 | 新疆爱华盈通信息技术有限公司 | Inspection method and system for parking lot inspection vehicle and inspection vehicle |
| CN113436361A (en) * | 2021-06-03 | 2021-09-24 | 超级视线科技有限公司 | Roadside berth management system based on unmanned inspection vehicle |
| CN113542678A (en) * | 2021-06-17 | 2021-10-22 | 超级视线科技有限公司 | Parking management removes system of patrolling and examining |
| CN114446059A (en) * | 2021-12-29 | 2022-05-06 | 北京智联云海科技有限公司 | System and method for vehicle-mounted monitoring of roadside parking vehicles |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130066829A (en) * | 2011-12-13 | 2013-06-21 | 한국전자통신연구원 | Parking lot management system based on cooperation of intelligence cameras |
-
2022
- 2022-09-15 CN CN202211119839.8A patent/CN115641724B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109767626A (en) * | 2018-12-20 | 2019-05-17 | 北京筑梦园科技有限公司 | A kind of curb parking method for inspecting, system, cruiser and server |
| CN112949530A (en) * | 2021-03-12 | 2021-06-11 | 新疆爱华盈通信息技术有限公司 | Inspection method and system for parking lot inspection vehicle and inspection vehicle |
| CN113436361A (en) * | 2021-06-03 | 2021-09-24 | 超级视线科技有限公司 | Roadside berth management system based on unmanned inspection vehicle |
| CN113542678A (en) * | 2021-06-17 | 2021-10-22 | 超级视线科技有限公司 | Parking management removes system of patrolling and examining |
| CN114446059A (en) * | 2021-12-29 | 2022-05-06 | 北京智联云海科技有限公司 | System and method for vehicle-mounted monitoring of roadside parking vehicles |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115641724A (en) | 2023-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110487562B (en) | Driveway keeping capacity detection system and method for unmanned driving | |
| AU2018397461B2 (en) | Multiple operating modes to expand dynamic range | |
| CN110210303B (en) | Beidou vision fusion accurate lane identification and positioning method and implementation device thereof | |
| JP7218535B2 (en) | Traffic violation vehicle identification system and server | |
| US11834038B2 (en) | Methods and systems for providing depth maps with confidence estimates | |
| US7366325B2 (en) | Moving object detection using low illumination depth capable computer vision | |
| US11100806B2 (en) | Multi-spectral system for providing precollision alerts | |
| KR101891460B1 (en) | Method and apparatus for detecting and assessing road reflections | |
| CN104616502B (en) | Car license recognition and alignment system based on combination type bus or train route video network | |
| CN107305627A (en) | A kind of automobile video frequency monitoring method, server and system | |
| CN112466141A (en) | Vehicle-road-collaboration-oriented intelligent network connection end equipment interaction method, system and storage medium | |
| CN103824037B (en) | Vehicle anti-tracking alarm device | |
| CN101510356A (en) | Video detection system and data processing device thereof, video detection method | |
| CN111915883A (en) | Road traffic condition detection method based on vehicle-mounted camera shooting | |
| CN105894818A (en) | Vehicle intersection traffic violation evidence obtaining system and method | |
| CN109874099B (en) | Networking vehicle-mounted equipment flow control system | |
| CN111862621B (en) | Intelligent snapshot system of multi-type adaptive black cigarette vehicle | |
| US20200394435A1 (en) | Distance estimation device, distance estimation method, and distance estimation computer program | |
| CN115641724B (en) | Inspection identification method, system and computer medium for managing berths in roads | |
| CN116892949A (en) | Ground object detection device, ground object detection method, and computer program for ground object detection | |
| CN115909223A (en) | Method and system for matching WIM system information with monitoring video data | |
| CN205541428U (en) | Vehicle crossing traffic violation system of collecting evidence | |
| CN115206091B (en) | Road condition and event monitoring system and method based on multiple cameras and millimeter wave radar | |
| EP4275194A1 (en) | Methods and systems for providing depth maps with confidence estimates | |
| CN113689691A (en) | Traffic detection 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 |