License plate recognition method and device
By acquiring vehicle perception information and images from base stations on traffic sign poles, extracting features, and matching them with an upstream base station database, the problem of low license plate recognition rate is solved and the recognition rate is improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 苏州万集车联网技术有限公司
- Filing Date
- 2024-12-02
- Publication Date
- 2026-06-02
AI Technical Summary
In existing technologies, license plate recognition is limited by camera field of view and vehicle occlusion, resulting in a low recognition rate.
Vehicle perception information and images are acquired by the first base station on the traffic sign pole, features are extracted, and the information is matched with the vehicle information feature database constructed by the upstream base station to determine the license plate information.
This improves the license plate recognition rate when downstream base stations are unable to recognize license plates due to geographical defects or vehicle obstruction.
Smart Images
Figure CN122135348A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of road traffic technology, and in particular relates to a license plate recognition method and device. Background Technology
[0002] License plate recognition refers to the process of photographing, processing, and recording passing vehicles in specific road scenarios, such as urban traffic intersections, highway toll stations, and tunnel entrances and exits, to identify vehicle license plates and thus determine the vehicle's identity, thereby helping to improve the efficiency of road traffic management.
[0003] In related technologies, cameras are typically installed on traffic sign poles to capture images of passing vehicles and identify their license plates. However, this method is limited by factors such as the camera's field of view and occlusion between vehicles, resulting in a low license plate recognition rate. Summary of the Invention
[0004] This application provides a license plate recognition method and apparatus that can improve the license plate recognition rate.
[0005] In a first aspect, embodiments of this application provide a license plate recognition method, the method comprising: acquiring first perception information of a vehicle to be recognized through a first base station; and acquiring a first image of the vehicle to be recognized through the first base station when the vehicle to be recognized enters the detection area of the first base station, wherein the first base station is installed on a traffic sign pole; extracting features from the first image to obtain first feature information corresponding to the vehicle to be recognized when the license plate information of the vehicle to be recognized cannot be identified based on the first image; determining a target vehicle that matches the first perception information and the first feature information in a vehicle information feature database, wherein the vehicle information feature database is constructed by collecting vehicle images and perception information through a second base station, the second base station being an upstream base station of the first base station; acquiring the license plate information corresponding to the target vehicle, and determining the license plate information corresponding to the target vehicle as the license plate information of the vehicle to be recognized.
[0006] Optionally, in one possible implementation of the first aspect, the first base station is equipped with a camera, and the acquisition of a first image of the vehicle to be identified through the first base station when the vehicle to be identified enters the detection area of the first base station includes: sending a capture command to the camera of the first base station when the vehicle to be identified enters the detection area of the first base station, so that the camera of the first base station captures the vehicle to be identified according to the capture command and obtains the first image.
[0007] Optionally, in another possible implementation of the first aspect, the vehicle information feature library includes multiple reference vehicles, and includes reference feature information and reference perception information corresponding to each reference vehicle. Determining the target vehicle matching the first perception information and the first feature information in the vehicle information feature library includes: calculating image feature similarity based on the first feature information and each reference feature information to obtain a first similarity calculation result; calculating perception information similarity based on the first perception information and each reference perception information to obtain a second similarity calculation result; and determining the target vehicle among the multiple reference vehicles based on the first similarity calculation result and the second similarity calculation result.
[0008] Optionally, in another possible implementation of the first aspect, the first sensing information includes first time information of the vehicle to be identified entering the detection area of the first base station, and the reference sensing information includes second time information of the reference vehicle entering the detection area of the second base station. The method further includes: determining at least one screening vehicle from all reference vehicles based on the first time information and the distance information between the first base station and the second base station, wherein the second time information corresponding to each screening vehicle is within a preset time period before the first time information; the above-mentioned calculation of image feature similarity based on the first feature information and each reference feature information to obtain a first similarity calculation result includes: determining the image feature similarity between the first feature information and the reference feature information of each screening vehicle to obtain a first similarity calculation result; the above-mentioned calculation of sensing information similarity based on the first sensing information and each reference sensing information to obtain a second similarity calculation result includes: determining the sensing information similarity between the first sensing information and the reference sensing information of each screening vehicle to obtain a second similarity calculation result.
[0009] Optionally, in another possible implementation of the first aspect, the method further includes: obtaining speed information of all vehicles passing through the detection area of the second base station within a target time period via the second base station, wherein the target time period is any time period during which vehicles enter or exit the detection area of the second base station; determining the lowest speed among the speed information of all vehicles passing through the detection area of the second base station within the target time period; and determining a preset time period based on the distance between the first base station and the second base station and the lowest speed.
[0010] Optionally, in another possible implementation of the first aspect, obtaining the license plate information corresponding to the target vehicle includes: determining the license plate information corresponding to the target vehicle from the reference perception information corresponding to the target vehicle.
[0011] Optionally, in another possible implementation of the first aspect, the method further includes: identifying the license plate information of the vehicle to be identified based on the first image.
[0012] Optionally, in another possible implementation of the first aspect, the first base station is equipped with a camera and a lidar or millimeter-wave radar; the second base station is mounted on a gantry and is equipped with a camera and a lidar or millimeter-wave radar; the camera is used to acquire images of the vehicle, and the lidar or millimeter-wave radar is used to acquire perception information of the vehicle.
[0013] Optionally, in another possible implementation of the first aspect, the aforementioned first sensing information includes first location information and size information of the vehicle to be identified. The method further includes: obtaining second location information of the detection area of the first base station through a high-precision map; and determining whether the vehicle to be identified has entered the detection area of the first base station based on the first location information, size information, and second location information.
[0014] Optionally, in another possible implementation of the first aspect, the method further includes: storing first perception information, first feature information, and license plate information of the vehicle to be identified through a first base station, so that if the third base station cannot identify the license plate information of the vehicle to be identified, the license plate information of the vehicle to be identified can be obtained according to the vehicle information feature database of the second base station, or by obtaining the first perception information, first feature information, and license plate information of the vehicle to be identified stored by the first base station, wherein the third base station is a downstream base station of the first base station and the third base station is set on the traffic sign pole.
[0015] Secondly, embodiments of this application provide a license plate recognition device, the device comprising:
[0016] The acquisition module is used to acquire first perception information of the vehicle to be identified through the first base station, and to acquire a first image of the vehicle to be identified through the first base station when the vehicle to be identified enters the detection area of the first base station. The first base station is set on a traffic sign pole.
[0017] The processing module is used to extract features from the first image when the license plate information of the vehicle to be identified cannot be identified based on the first image, so as to obtain the first feature information corresponding to the vehicle to be identified.
[0018] The processing module is also used to determine the target vehicle that matches the first perception information and the first feature information in the vehicle information feature database. The vehicle information feature database is constructed by collecting vehicle images and perception information through a second base station, which is an upstream base station of the first base station.
[0019] The processing module is also used to obtain the license plate information corresponding to the target vehicle and determine the license plate information corresponding to the target vehicle as the license plate information of the vehicle to be identified.
[0020] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device is able to implement any of the methods described in the first aspect above.
[0021] Fourthly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on an electronic device, enable the electronic device to perform any of the methods described in the first aspect.
[0022] Fifthly, embodiments of this application provide a computer program product, which includes a computer program. When the computer program is executed by an electronic device, the electronic device is able to implement any of the methods described in the first aspect.
[0023] The beneficial effects of this application embodiment compared with the prior art are as follows: This application discloses a license plate recognition method and apparatus. In this method, firstly, a first perception information and a first image of the vehicle to be recognized are acquired by a first base station installed on a traffic sign pole. Then, if the license plate information of the vehicle to be recognized cannot be identified based on the first image, features are extracted from the first image to obtain the first feature information corresponding to the vehicle to be recognized. Finally, a target vehicle matching the first perception information and the first feature information is determined from a vehicle information feature database constructed by a second base station. The second base station is an upstream base station of the first base station, and the license plate information corresponding to the target vehicle is also the license plate information of the vehicle to be recognized. Therefore, when the downstream base station cannot obtain the license plate through image recognition due to geographical defects or vehicle obstruction, the images collected by the downstream base station are matched with the vehicle information feature database constructed by the upstream base station through the linkage of upstream and downstream base stations, thereby obtaining the license plate information of the vehicle to be recognized, improving the license plate recognition rate of the first base station on the downstream traffic sign pole. Attached Figure Description
[0024] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0025] Figure 1 This is a schematic diagram illustrating an applicable scenario provided by an embodiment of this application;
[0026] Figure 2 This is a schematic flowchart of a license plate recognition method provided in an embodiment of this application;
[0027] Figure 3This is a schematic diagram of the structure of a license plate recognition device provided in an embodiment of this application;
[0028] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0029] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.
[0030] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.
[0031] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0032] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."
[0033] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0034] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.
[0035] It should be understood that the sequence number of each step in this embodiment does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of this application embodiment.
[0036] In related technologies, cameras are typically installed on traffic sign poles to capture images of passing vehicles and identify their license plates. However, this method is limited by factors such as the camera's field of view and occlusion between vehicles, resulting in a low license plate recognition rate.
[0037] In view of this, this application provides a license plate recognition method and apparatus. In this method, firstly, a first sensing information and a first image of the vehicle to be recognized are acquired by a first base station installed on a traffic sign pole. Then, if the license plate information of the vehicle to be recognized cannot be identified based on the first image, features are extracted from the first image to obtain first feature information corresponding to the vehicle to be recognized. Finally, a target vehicle matching the first sensing information and the first feature information is determined from a vehicle information feature database constructed by a second base station. The second base station is an upstream base station of the first base station, and the license plate information corresponding to the target vehicle is also the license plate information of the vehicle to be recognized. Therefore, when a downstream base station cannot obtain the license plate through image recognition due to geographical defects or vehicle obstruction, the images collected by the downstream base station are matched with the vehicle information feature database constructed by the upstream base station through the linkage of upstream and downstream base stations, thereby obtaining the license plate information of the vehicle to be recognized and improving the license plate recognition rate of the first base station on the downstream traffic sign pole.
[0038] To illustrate the technical solution of this application, specific embodiments are described below.
[0039] Figure 1 This is a schematic diagram illustrating an applicable scenario provided by an embodiment of this application. For example... Figure 1 As shown, the first base station 11 is installed on a traffic sign pole, and the second base station 12 is installed on a gantry. The first base station 11 is the downstream base station of the second base station 12. Figure 1The dashed line indicates the detection areas of the two base stations. Typically, the first base station 11 only has a camera to capture images of vehicles and identify their license plates. However, due to geographical limitations, the detection area of the first base station 11 is relatively limited, resulting in a low license plate recognition rate. The second base station 12 is positioned in a location with a better field of view and is usually equipped with cameras, LiDAR, millimeter-wave radar, and other devices to achieve high-precision vehicle perception and identification.
[0040] In this embodiment, the camera is used to capture images of vehicles on the road. This embodiment does not limit the number or installation location of the cameras, as long as they can successfully capture vehicle images. LiDAR or millimeter-wave radar is used to perceive and track vehicles entering its detection range from outside the scene, and can detect perception information entering the detection range. Similarly, this embodiment does not limit the number or installation location of LiDAR or millimeter-wave radar.
[0041] It should be understood that Figure 1 The traffic sign poles in this embodiment are exemplified by the F-type traffic sign pole (referred to as F pole). This application does not limit the type of traffic sign pole. The gantry can be installed at locations such as toll stations or tunnel entrances / exits.
[0042] about Figure 1 For details on the specific working principle and technical implementation of the system shown, please refer to the method embodiments below.
[0043] Reference Figure 2 The diagram shows a flowchart of a license plate recognition method provided in an embodiment of this application.
[0044] like Figure 2 As shown, the method may include the following steps:
[0045] Step 201: Obtain first perception information of the vehicle to be identified through the first base station, and obtain the first image of the vehicle to be identified through the first base station when the vehicle to be identified enters the detection area of the first base station.
[0046] In this embodiment of the application, the first base station is installed on a traffic sign pole.
[0047] In one embodiment, a camera is installed on the first base station. The camera first detects whether the vehicle to be identified has entered the detection area of the first base station. If the vehicle to be identified enters the detection area of the first base station, a capture command is sent to the camera of the first base station so that the camera of the first base station can capture the vehicle to be identified according to the capture command and obtain a first image.
[0048] In one embodiment, the camera's capture rate is easily affected by factors such as field of view and vehicle obstruction. Therefore, a lidar (single-line or multi-line) or millimeter-wave radar can be installed on the first base station to acquire the aforementioned first perception information. This first perception information may include the vehicle's first location information, size, transit time, speed, vehicle type, and body color. Using this first perception information to trigger the camera's capture can improve its success rate. Specifically, firstly, the second location information of the detection area of the first base station can be obtained through a high-precision map; based on the first location information, size information, and second location information, it is determined whether the vehicle to be identified has entered the detection area of the first base station.
[0049] Since the geographical location of the capture area is known, its latitude and longitude coordinates can be obtained from a high-precision map, which is represented here as the second location information. Then, based on the second location information and the received first sensing information, it can be determined whether the vehicle to be identified has entered the capture area. For example, the first sensing information can determine the current location of the vehicle to be identified, and then it can be determined whether that location falls within the range corresponding to the second location information.
[0050] It should be noted that the detection area of the lidar or millimeter-wave radar should be set to be wider than the capture area of the camera. This allows the lidar to detect vehicles outside the camera's capture area earlier, so as to determine when to send a capture command to the camera.
[0051] Step 202: If the license plate information of the vehicle to be identified cannot be identified from the first image, feature extraction is performed on the first image to obtain the first feature information corresponding to the vehicle to be identified.
[0052] Feature extraction aims to extract key features from the first image that represent the vehicle to be identified. These features can include color, shape, texture, and contour. By extracting these features, effective information can be provided for subsequent license plate recognition.
[0053] In another embodiment, if the license plate information of the vehicle to be identified can be obtained from the first image, then no further steps are required.
[0054] Step 203: In the vehicle information feature database, determine the target vehicle that matches the first perception information and the first feature information.
[0055] In this embodiment of the application, the vehicle information feature database is constructed by collecting vehicle images and perception information through a second base station, which is an upstream base station of the first base station.
[0056] In one embodiment, the second base station is typically installed in an environment with good visibility, such as a gantry crane. The second base station includes sensing devices such as cameras, lidar, and millimeter-wave radar, enabling high-precision vehicle perception and identification. The second base station can record feature information and perception information of each vehicle (referencing an example vehicle) over a period of time, forming a vehicle information feature database. Therefore, if the first base station fails to identify the license plate information of the vehicle to be identified from the first image, it can match the first feature information and the first perception information with data from the vehicle information feature database over a period of time to obtain possible target vehicles.
[0057] Specifically, the vehicle information feature database includes multiple reference vehicles, as well as reference feature information and reference perception information corresponding to each reference vehicle. First, image feature similarity is calculated based on the first feature information and each reference feature information to obtain a first similarity calculation result; then, perception information similarity is calculated based on the first perception information and each reference perception information to obtain a second similarity calculation result; finally, the target vehicle is determined among the multiple reference vehicles based on the first and second similarity calculation results.
[0058] The reference perception information includes not only location information, size, time of passage, vehicle speed, vehicle type, and body color, but also license plate information, which may include license plate number, license plate color, etc.
[0059] In one embodiment, during similarity calculation, it is not necessary to compare the vehicle to be identified with all reference vehicles in the vehicle information feature database. Instead, it is sufficient to combine the distance between upstream and downstream base stations and the time when the first base station detected the vehicle to be identified, selecting reference vehicles within a certain time period before that time for matching. Specifically, based on the first time information and the distance information between the first and second base stations, at least one filter vehicle can be determined from all reference vehicles. The second time information corresponding to each filter vehicle is within a preset time period before the first time information. Then, the image feature similarity between the first feature information and the reference feature information of each filter vehicle is determined to obtain the first similarity calculation result. Next, the perceptual information similarity between the first perceptual information and the reference perceptual information of each filter vehicle is determined to obtain the second similarity calculation result.
[0060] In one embodiment, the aforementioned preset time period needs to be universal, meaning it must ensure that the reference vehicles within this preset time period necessarily include the vehicle to be identified, thus avoiding matching failures. Specifically, the speed information of all vehicles passing through the detection area of the second base station within the target time period can be obtained first through the second base station. The target time period is any time interval during which vehicles enter or exit the detection area of the second base station. Then, the lowest speed among the speed information of all vehicles passing through the detection area of the second base station within the target time period is determined. Finally, the preset time period is determined based on the distance between the first and second base stations and the lowest speed. Therefore, by statistically analyzing the lowest speed of all vehicles within a historical time period and setting the preset time period based on this lowest speed, it can be ensured that the reference vehicles within the preset time period necessarily include the vehicle to be identified, improving the success rate of vehicle matching between upstream and downstream base stations.
[0061] Step 204: Obtain the license plate information corresponding to the target vehicle, and determine the license plate information corresponding to the target vehicle as the license plate information of the vehicle to be identified.
[0062] In this embodiment of the application, the license plate information of the reference vehicle is stored in the reference perception information of the reference vehicle in the vehicle information feature database. In other words, the license plate information of the target vehicle can be determined from the reference perception information of the target vehicle.
[0063] In one possible implementation, after obtaining the license plate information of the vehicle to be identified, the first base station can continue to save the license plate information. This way, if the downstream base station of the first base station cannot correctly identify the license plate, it can obtain the license plate information saved by the first base station to complete the license plate recognition. In other words, the first base station can save the first perception information, first feature information, and license plate information of the vehicle to be identified. This allows the license plate information of the vehicle to be identified to be obtained, either based on the vehicle information feature database of the second base station or by obtaining the first perception information, first feature information, and license plate information saved by the first base station, even if the third base station cannot identify the license plate information of the vehicle to be identified. The third base station is a downstream base station of the first base station and is located on a traffic sign pole.
[0064] It should also be understood that the vehicle matching between the first base station and the third base station is the same as the matching process between the first base station and the second base station mentioned above, and will not be repeated here.
[0065] It should also be understood that if the third base station is unable to identify the license plate information of the vehicle to be identified, it can choose to obtain the license plate information from the first base station, or it can choose to continue to interact with the upstream second base station that can achieve high-precision license plate perception in order to obtain the license plate information.
[0066] The license plate recognition method disclosed in the above embodiments of this application first acquires first perception information and a first image of the vehicle to be recognized through a first base station installed on a traffic sign pole. Then, if the license plate information of the vehicle to be recognized cannot be identified based on the first image, feature extraction is performed on the first image to obtain first feature information corresponding to the vehicle to be recognized. Finally, a target vehicle matching the first perception information and the first feature information is determined from a vehicle information feature database constructed by a second base station. The second base station is an upstream base station of the first base station, and the license plate information corresponding to the target vehicle is also the license plate information of the vehicle to be recognized. Thus, when the downstream base station cannot obtain the license plate through image recognition due to geographical defects or vehicle obstruction, the upstream and downstream base stations work together to match the image collected by the downstream base station with the vehicle information feature database constructed by the upstream base station, thereby obtaining the license plate information of the vehicle to be recognized, improving the license plate recognition rate of the first base station on the downstream traffic sign pole.
[0067] See Figure 3 The diagram shows a schematic of a license plate recognition device provided in an embodiment of this application. For ease of explanation, only the parts related to the embodiment of this application are shown.
[0068] The license plate recognition device 300 may specifically include the following modules:
[0069] The acquisition module 301 is used to acquire first perception information of the vehicle to be identified through the first base station, and to acquire a first image of the vehicle to be identified through the first base station when the vehicle to be identified enters the detection area of the first base station, wherein the first base station is set on a traffic sign pole.
[0070] The processing module 302 is used to extract features from the first image when the license plate information of the vehicle to be identified cannot be identified based on the first image, so as to obtain the first feature information corresponding to the vehicle to be identified.
[0071] The aforementioned processing module 302 is further configured to determine, in the vehicle information feature database, a target vehicle that matches the first perception information and the first feature information, wherein the vehicle information feature database is constructed by collecting vehicle images and perception information from a second base station, and the second base station is an upstream base station of the first base station.
[0072] The aforementioned processing module 302 is also used to obtain the license plate information corresponding to the target vehicle and determine the license plate information corresponding to the target vehicle as the license plate information of the vehicle to be identified.
[0073] The license plate recognition device disclosed in the above embodiments of this application first acquires first perception information and a first image of the vehicle to be recognized through a first base station installed on a traffic sign pole. Then, if the license plate information of the vehicle to be recognized cannot be identified based on the first image, feature extraction is performed on the first image to obtain first feature information corresponding to the vehicle to be recognized. Finally, a target vehicle matching the first perception information and the first feature information is determined from a vehicle information feature database constructed by a second base station. The second base station is an upstream base station of the first base station, and the license plate information corresponding to the target vehicle is also the license plate information of the vehicle to be recognized. Thus, when the downstream base station cannot obtain the license plate through image recognition due to geographical defects or vehicle obstruction, the upstream and downstream base stations work together to match the image collected by the downstream base station with the vehicle information feature database constructed by the upstream base station, thereby obtaining the license plate information of the vehicle to be recognized, improving the license plate recognition rate of the first base station on the downstream traffic sign pole.
[0074] Furthermore, in one possible implementation of this application embodiment, the first base station is equipped with a camera, and the acquisition module 301 may specifically include the following units:
[0075] The first transmitting unit is used to send a capture command to the camera of the first base station when the vehicle to be identified enters the detection area of the first base station, so that the camera of the first base station can capture the vehicle to be identified according to the capture command and obtain a first image.
[0076] Furthermore, in another possible implementation of this application embodiment, the vehicle information feature database includes multiple reference vehicles, as well as reference feature information and reference perception information corresponding to each reference vehicle. The processing module 302 may specifically include the following units:
[0077] The first processing unit is used to perform image feature similarity calculation based on the first feature information and each reference feature information to obtain the first similarity calculation result.
[0078] The second processing unit is used to perform perceptual information similarity calculation based on the first perceptual information and each reference perceptual information to obtain the second similarity calculation result.
[0079] The third processing unit is used to determine the target vehicle among multiple reference vehicles based on the first similarity calculation result and the second similarity calculation result.
[0080] Furthermore, in another possible implementation of this application embodiment, the first sensing information includes first time information of the vehicle to be identified entering the detection area of the first base station, and the reference sensing information includes second time information of the reference vehicle entering the detection area of the second base station. The processing module 302 may specifically include the following units:
[0081] The fourth processing unit is used to determine at least one screened vehicle from all reference vehicles based on the first time information and the distance information between the first base station and the second base station, wherein the second time information corresponding to each screened vehicle is within a preset time period before the first time information.
[0082] Correspondingly, the first processing unit is specifically used to determine the image feature similarity between the first feature information and the reference feature information of each screened vehicle, and to obtain the first similarity calculation result.
[0083] Correspondingly, the second processing unit is specifically used to determine the similarity between the first perception information and the reference perception information of each screened vehicle, and to obtain the second similarity calculation result.
[0084] Furthermore, in another possible implementation of this application embodiment, the above-mentioned processing module 302 may specifically include the following units:
[0085] The fifth processing unit is used to obtain the speed information of all vehicles passing through the detection area of the second base station within a target time period through the second base station, wherein the target time period is any time period during which vehicles enter or exit the detection area of the second base station.
[0086] The sixth processing unit is used to determine the lowest speed among all vehicles passing through the detection area of the second base station within the target time period.
[0087] The seventh processing unit is used to determine a preset time period based on the distance between the first base station and the second base station and the minimum speed.
[0088] Furthermore, in another possible implementation of this application embodiment, the above-mentioned processing module 302 is specifically used to determine the license plate information corresponding to the target vehicle from the reference perception information corresponding to the target vehicle.
[0089] Furthermore, in another possible implementation of this application embodiment, the above-mentioned processing module 302 may specifically include the following units:
[0090] The eighth processing unit is used to identify the license plate information of the vehicle to be identified based on the first image.
[0091] Furthermore, in another possible implementation of this application embodiment, the first base station is equipped with a camera, and also with a lidar or millimeter-wave radar. The second base station is mounted on a gantry, and also equipped with a camera, lidar, or millimeter-wave radar. The camera is used to acquire images of the vehicle, and the lidar or millimeter-wave radar is used to acquire perception information about the vehicle.
[0092] Furthermore, in another possible implementation of this application embodiment, the aforementioned first sensing information includes the first position information and size information of the vehicle to be identified. The aforementioned processing module 302 may specifically include the following units:
[0093] The first acquisition unit is used to acquire the second location information of the detection area of the first base station through a high-precision map.
[0094] The ninth processing unit is used to determine whether the vehicle to be identified has entered the detection area of the first base station based on the first location information, size information and second location information.
[0095] Furthermore, in another possible implementation of this application embodiment, the above-mentioned processing module 302 may specifically include the following units:
[0096] The tenth processing unit is used to store the first perception information, first feature information and license plate information of the vehicle to be identified through the first base station, so that when the third base station cannot identify the license plate information of the vehicle to be identified, the license plate information of the vehicle to be identified can be obtained according to the vehicle information feature database of the second base station, or by obtaining the first perception information, first feature information and license plate information of the vehicle to be identified stored by the first base station. The third base station is a downstream base station of the first base station and is set on the traffic sign pole.
[0097] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of this application. For example... Figure 4 As shown, the electronic device 400 of this embodiment includes: at least one processor 410 ( Figure 4 (Only one is shown in the diagram) a processor, a memory 420, and a computer program 421 stored in the memory 420 and executable on the at least one processor 410, wherein the processor 410 executes the computer program 421 to implement the steps in the above-described license plate recognition method embodiments.
[0098] The electronic device 400 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. This electronic device may include, but is not limited to, a processor 410 and a memory 420. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 400 and does not constitute a limitation on electronic device 400. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.
[0099] The processor 410 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.
[0100] In some embodiments, the memory 420 may be an internal storage unit of the electronic device 400, such as a hard disk or memory of the electronic device 400. In other embodiments, the memory 420 may be an external storage device of the electronic device 400, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 400. Furthermore, the memory 420 may include both internal and external storage units of the electronic device 400. The memory 420 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 420 can also be used to temporarily store data that has been output or will be output.
[0101] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0102] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0103] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0104] In the embodiments provided in this application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.
[0105] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0106] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0107] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.
[0108] The implementation of all or part of the processes in the methods of the above embodiments can also be accomplished by a computer program product. When the computer program product is run on an electronic device, the electronic device can implement the steps in the various method embodiments described above.
[0109] The embodiments described above are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A license plate recognition method, characterized in that, include: The system acquires first perception information of the vehicle to be identified through the first base station, and acquires a first image of the vehicle to be identified through the first base station when the vehicle to be identified enters the detection area of the first base station. The first base station is installed on a traffic sign pole. If the license plate information of the vehicle to be identified cannot be identified based on the first image, feature extraction is performed on the first image to obtain the first feature information corresponding to the vehicle to be identified. In the vehicle information feature database, a target vehicle matching the first perception information and the first feature information is determined, wherein the vehicle information feature database is constructed by collecting vehicle images and perception information by a second base station, and the second base station is an upstream base station of the first base station; Obtain the license plate information corresponding to the target vehicle, and determine the license plate information corresponding to the target vehicle as the license plate information of the vehicle to be identified.
2. The method according to claim 1, characterized in that, The first base station is equipped with a camera. When the vehicle to be identified enters the detection area of the first base station, acquiring a first image of the vehicle to be identified through the first base station includes: When a vehicle to be identified enters the detection area of the first base station, a capture command is sent to the camera of the first base station so that the camera of the first base station can capture the vehicle to be identified according to the capture command and obtain the first image.
3. The method according to claim 1, characterized in that, The vehicle information feature database includes multiple reference vehicles, as well as reference feature information and reference perception information corresponding to each reference vehicle. Determining the target vehicle matching the first perception information and the first feature information in the vehicle information feature database includes: Based on the first feature information and each of the reference feature information, image feature similarity is calculated to obtain the first similarity calculation result; Based on the first perception information and each of the reference perception information, a perception information similarity calculation is performed to obtain a second similarity calculation result; Based on the first similarity calculation result and the second similarity calculation result, the target vehicle is determined among the plurality of reference vehicles.
4. The method according to claim 3, characterized in that, The first sensing information includes first time information of the vehicle to be identified entering the detection area of the first base station, and the reference sensing information includes second time information of the reference vehicle entering the detection area of the second base station. The method further includes: Based on the first time information and the distance information between the first base station and the second base station, at least one screening vehicle is determined from all the reference vehicles, wherein the second time information corresponding to each screening vehicle is within a preset time period before the first time information; The step of calculating image feature similarity based on the first feature information and each of the reference feature information to obtain a first similarity calculation result includes: determining the image feature similarity between the first feature information and the reference feature information of each of the selected vehicles, and obtaining the first similarity calculation result; The step of calculating the similarity of perception information based on the first perception information and each of the reference perception information to obtain a second similarity calculation result includes: determining the similarity of perception information between the first perception information and the reference perception information of each of the selected vehicles, and obtaining the second similarity calculation result.
5. The method according to claim 4, characterized in that, The method further includes: The speed information of all vehicles passing through the detection area of the second base station within a target time period is obtained through the second base station, wherein the target time period is any time period during which vehicles enter or exit the detection area of the second base station; Determine the lowest speed among all vehicles passing through the detection area of the second base station within the target time period; The preset time period is determined based on the distance between the first base station and the second base station and the minimum speed.
6. The method according to claim 3, characterized in that, The step of obtaining the license plate information corresponding to the target vehicle includes: The license plate information corresponding to the target vehicle is determined from the reference perception information corresponding to the target vehicle.
7. The method according to any one of claims 1-6, characterized in that, The method further includes: Based on the first image, the license plate information of the vehicle to be identified is obtained.
8. The method according to any one of claims 1-6, characterized in that, The first base station is equipped with a camera and a lidar or millimeter-wave radar; the second base station is mounted on a gantry and is equipped with a camera and a lidar or millimeter-wave radar; the camera is used to acquire images of the vehicle, and the lidar or millimeter-wave radar is used to acquire perception information of the vehicle.
9. The method according to any one of claims 1-6, characterized in that, The first sensing information includes the first location information and size information of the vehicle to be identified, and the method further includes: The second location information of the detection area of the first base station is obtained through a high-precision map; Based on the first location information, the size information, and the second location information, it is determined whether the vehicle to be identified has entered the detection area of the first base station.
10. The method according to any one of claims 1-6, characterized in that, The method further includes: The first base station stores the first perception information, the first feature information, and the license plate information of the vehicle to be identified, so that if the third base station cannot identify the license plate information of the vehicle to be identified, the license plate information of the vehicle to be identified can be obtained according to the vehicle information feature database of the second base station, or by obtaining the first perception information, the first feature information, and the license plate information of the vehicle to be identified stored by the first base station. The third base station is a downstream base station of the first base station and is installed on a traffic sign pole.
11. A license plate recognition device, characterized in that, include: The acquisition module is used to acquire first perception information of the vehicle to be identified through the first base station, and to acquire a first image of the vehicle to be identified through the first base station when the vehicle to be identified enters the detection area of the first base station, wherein the first base station is set on a traffic sign pole; The processing module is used to extract features from the first image to obtain the first feature information corresponding to the vehicle to be identified when the license plate information of the vehicle to be identified cannot be identified based on the first image. The processing module is further configured to determine, in the vehicle information feature database, a target vehicle that matches the first perception information and the first feature information, wherein the vehicle information feature database is constructed by collecting vehicle images and perception information by a second base station, and the second base station is an upstream base station of the first base station. The processing module is further configured to obtain the license plate information corresponding to the target vehicle, and determine the license plate information corresponding to the target vehicle as the license plate information of the vehicle to be identified.
12. An electronic device, characterized in that, The electronic device includes: one or more processors, and a memory; the memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the electronic device to perform the method as described in any one of claims 1 to 10.
13. A computer program product, characterized in that, The computer program product includes a computer program that, when run on an electronic device, causes the electronic device to perform the method as described in any one of claims 1 to 10.