Method, device, storage medium and electronic device for identifying non-motor vehicle

Abstract

Embodiments of the present application provide a non-motor vehicle identification method and device, a storage medium and an electronic device, wherein the method comprises: obtaining reading results of N radio frequency devices, a reading area of each radio frequency device is set to be located on a corresponding one of N virtual lanes, and the N virtual lanes are virtual lanes divided according to a target driving lane; in a case where the reading results include a first electronic tag read by a first radio frequency device, determining a first non-motor vehicle object located in a first image area in target image information, a first reading area of the first radio frequency device is set to be located on a first virtual lane of the N virtual lanes, and the first image area corresponds to the first reading area on the first virtual lane; and binding the first electronic tag with the first non-motor vehicle object in the target image information. Through the present application, the problem of low accuracy of non-motor vehicle identification in the related art is solved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of monitoring technology, and more specifically, to a method, apparatus, storage medium, and electronic device for identifying non-motorized vehicles. Background Technology

[0002] With the development of artificial intelligence and image analysis technologies, AI devices are widely used in various scenarios, especially in the field of smart urban transportation. Therefore, it is essential to explore how to use AI technology to establish a comprehensive non-motorized vehicle violation monitoring system.

[0003] In related technologies, in the context of managing non-motorized vehicle violations, pure image analysis often encounters problems such as small license plates of non-motorized vehicles and license plates being obscured due to the large number of vehicles, making it impossible to accurately obtain the license plate numbers of violating non-motorized vehicles, resulting in incomplete evidence collection. In other words, related technologies suffer from the problem of low accuracy in identifying non-motorized vehicle license plate numbers based on image analysis.

[0004] There is currently no effective solution to the problem of low accuracy in non-motorized vehicle identification in related technologies. Summary of the Invention

[0005] This invention provides a method, apparatus, storage medium, and electronic device for identifying non-motorized vehicles, in order to at least solve the problem of low accuracy in non-motorized vehicle identification in related technologies.

[0006] According to an embodiment of the present invention, a method for identifying non-motorized vehicles is provided, comprising: acquiring the reading results of N radio frequency devices, wherein the reading area of ​​each of the N radio frequency devices is set to be located on a corresponding virtual lane among N virtual lanes, N being a positive integer greater than or equal to 2, the N radio frequency devices being used to read electronic tags recorded on non-motorized vehicles, and the N virtual lanes being virtual lanes divided from a target driving lane; when the reading results of the N radio frequency devices include a first electronic tag read by a first radio frequency device among the N radio frequency devices, determining a first non-motorized vehicle object located in a first image area in target image information, wherein the first reading area of ​​the first radio frequency device is set to be located on the first virtual lane among the N virtual lanes, the first image area corresponding to the first reading area on the first virtual lane, the target image information being image information captured by a target camera, the capturing area of ​​the target camera including the target driving lane; and binding the first electronic tag to the first non-motorized vehicle object in the target image information.

[0007] In an exemplary embodiment, determining the first non-motorized vehicle object located in the first image region in the target image information includes: acquiring a target frame image at a target time in the target image information, wherein the target time is the time when the first radio frequency device reads the first electronic tag, and the reading results of the N radio frequency devices include the target time; and determining the non-motorized vehicle object identified in the first image region in the target frame image as the first non-motorized vehicle object.

[0008] In one exemplary embodiment, the method further includes: when the reading results of the N radio frequency devices include the first electronic tag read by the first radio frequency device and the second electronic tag read by the second radio frequency device among the N radio frequency devices, and the first electronic tag and the second electronic tag are read simultaneously, determining the first non-motorized vehicle object located in the first image area and the second non-motorized vehicle object located in the second image area in the target image information, wherein the second reading area of ​​the second radio frequency device is set to be located on the second virtual lane among the N virtual lanes, and the second image area corresponds to the second reading area on the second virtual lane; binding the first electronic tag to the first non-motorized vehicle object and binding the second electronic tag to the second non-motorized vehicle object in the target image information.

[0009] In an exemplary embodiment, the method further includes: when the reading results of the N radio frequency devices include the first electronic tag and the third electronic tag read sequentially by the first radio frequency device, determining the first non-motorized vehicle object and the third non-motorized vehicle object that appear sequentially in the first image area in the target image information; binding the first electronic tag to the first non-motorized vehicle object and binding the third electronic tag to the third non-motorized vehicle object in the target image information.

[0010] In an exemplary embodiment, the step of determining the first non-motorized vehicle object and the third non-motorized vehicle object that appear sequentially in the first image area in the target image information, binding the first electronic tag to the first non-motorized vehicle object in the target image information, and binding the third electronic tag to the third non-motorized vehicle object includes: acquiring a first frame image at a first moment in the target image information, wherein the first moment is the moment when the first radio frequency device reads the first electronic tag, and the reading results of the N radio frequency devices include the first moment; if a non-motorized vehicle object is identified in the first image area in the first frame image, the identified non-motorized vehicle object is identified as the first non-motorized vehicle object, and the first electronic tag is bound to the first non-motorized vehicle object. Binding; acquiring a second frame image at a second moment from the target image information, wherein the second moment is the moment when the first radio frequency device reads the third electronic tag, the reading results of the N radio frequency devices include the second moment, the second moment is later than the first moment, and the first electronic tag and the third electronic tag are electronic tags read by the first radio frequency device in two consecutive reads; in the case where two non-motorized vehicle objects are identified in the first image area of ​​the second frame image, and the non-motorized vehicle object that is forward in the driving direction of the two non-motorized vehicle objects is bound to the first electronic tag as the first non-motorized vehicle object, the non-motorized vehicle object that is backward in the driving direction of the two non-motorized vehicle objects is determined as the third non-motorized vehicle object, and the third electronic tag is bound to the third non-motorized vehicle object.

[0011] In an exemplary embodiment, after binding the first electronic tag to the first non-motorized vehicle object in the target image information, the method further includes: when it is determined based on the target image information that the first non-motorized vehicle object exhibits a target behavior, capturing a frame image of a third moment in the target image information, wherein the third moment is used to indicate the moment when the first non-motorized vehicle object exhibits the target behavior; storing the frame image of the third moment and the first electronic tag with a corresponding relationship; or when it is determined based on the target image information that the first non-motorized vehicle object exhibits a target behavior, capturing a target image information segment in the target image information, wherein the target image information segment includes the frame image of the third moment; storing the target image information segment and the first electronic tag with a corresponding relationship.

[0012] According to another embodiment of the present invention, a non-motorized vehicle identification device is also provided, comprising: an acquisition module, configured to acquire the reading results of N radio frequency devices, wherein the reading area of ​​each of the N radio frequency devices is set to be located on a corresponding virtual lane among N virtual lanes, N being a positive integer greater than or equal to 2, the N radio frequency devices being used to read electronic tags recorded on non-motorized vehicles, and the N virtual lanes being virtual lanes divided from a target driving lane; a first determination module, configured to determine a first non-motorized vehicle object located in a first image area in target image information when the reading results of the N radio frequency devices include a first electronic tag read by a first radio frequency device among the N radio frequency devices, wherein the first reading area of ​​the first radio frequency device is set to be located on a first virtual lane among the N virtual lanes, the first image area corresponding to the first reading area on the first virtual lane, the target image information being image information captured by a target camera, and the capturing area of ​​the target camera including the target driving lane; and a first binding module, configured to bind the first electronic tag to the first non-motorized vehicle object in the target image information.

[0013] In an exemplary embodiment, the first determining module includes: an acquisition unit, configured to acquire a target frame image at a target time from the target image information, wherein the target time is the time when the first radio frequency device reads the first electronic tag, and the reading results of the N radio frequency devices include the target time; and a determining unit, configured to determine the non-motorized vehicle object identified in the first image region in the target frame image as the first non-motorized vehicle object.

[0014] According to yet another embodiment of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when it is run.

[0015] According to yet another embodiment of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0016] Through this invention, when a non-motorized vehicle passes through the first reading area of ​​a first radio frequency (RF) device, the first RF device reads the first electronic tag, and then identifies the first non-motorized vehicle located in the first image area within the target image information. The first reading area is set to be located on a first virtual lane, and the first image area corresponds to the first reading area on the first virtual lane. The target image information is obtained by a target camera capturing an area including the target driving lane. Then, the first electronic tag is bound to the first non-motorized vehicle within the target image information. By first identifying the first electronic tag of the non-motorized vehicle and then binding it to the first non-motorized vehicle in the target image information, the first RF device is responsible for identifying the electronic tag of the non-motorized vehicle, while the target camera is mainly responsible for capturing the non-motorized vehicle's driving behavior. Therefore, it is possible to improve the accuracy of tag recognition of non-motorized vehicles in the image information without needing to add a new high-resolution camera to identify the non-motorized vehicle tag, thus solving the problem of low accuracy in non-motorized vehicle identification in related technologies and achieving the effect of improving the accuracy of non-motorized vehicle identification. Attached Figure Description

[0017] Figure 1 This is a hardware structure block diagram of a mobile terminal for a non-motorized vehicle identification method according to an embodiment of the present invention.

[0018] Figure 2 This is a schematic diagram of a non-motorized vehicle license plate recognition method in related technologies;

[0019] Figure 3 This is a flowchart of a method for identifying non-motorized vehicles according to an embodiment of the present invention;

[0020] Figure 4 This is an example of an application scenario according to a specific embodiment of the present invention. Figure 1 ;

[0021] Figure 5 This is an example of an application scenario according to a specific embodiment of the present invention. Figure 2 ;

[0022] Figure 6 This is an example of an application scenario according to a specific embodiment of the present invention. Figure 3 ;

[0023] Figure 7 This is a flowchart of a method for collecting evidence of traffic violations by non-motorized vehicles according to an embodiment of the present invention;

[0024] Figure 8 This is a structural block diagram of a non-motorized vehicle identification device according to an embodiment of the present invention. Detailed Implementation

[0025] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0027] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a non-motorized vehicle identification method according to an embodiment of the present invention. For example... Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0028] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the non-motorized vehicle identification method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0029] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0030] Current non-motorized vehicle violation monitoring systems mainly consist of two aspects: violation evidence collection and license plate recognition. Violations are primarily identified and evidenced through image information, while license plate recognition currently employs two methods: image information recognition and radio frequency identification (RFID). Among related technologies, some use pure image analysis, which is accurate in evidence collection, but license plate recognition may encounter errors when non-motorized vehicles are congested or have been altered. Other methods combine image analysis with RFID, which retrieves the corresponding RFID license plate after a violation is detected. However, because existing RFID readers use far-field antennas with large recognition areas, they often cannot pinpoint the relative position of the license plate, making it difficult to match license plates with multiple targets in the image information when multiple non-motorized vehicles are passing. When a single non-motorized vehicle is found to be violating traffic rules among multiple non-motorized vehicles, the multiple license plates detected by radio frequency identification (RFID) may not be able to match the specific violating vehicle, easily leading to misjudgment. Another solution uses high-definition cameras to identify non-motorized vehicle license plates. After identifying a violating non-motorized vehicle based on image information, the license plate is identified from the image and then matched with license plates read by RFID within the same time period, based on the license plate numbers and their confidence levels. The RFID-ready license plate is then used to correct the license plate in the image information. Figure 2 This is a schematic diagram of a non-motorized vehicle license plate recognition method in related technologies. The cost of building high-definition cameras and training license plate recognition algorithms in this scheme is relatively high. Moreover, it does not demonstrate the accuracy advantage of radio frequency recognition over image recognition of license plates. Furthermore, high-definition cameras generally need to be rebuilt on non-motorized vehicle lanes, making it impossible to reuse existing ones, and the construction cost is also relatively high.

[0031] This embodiment provides a method for identifying non-motorized vehicles. Figure 3 This is a flowchart of a non-motorized vehicle identification method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0032] Step S302: Obtain the reading results of N radio frequency devices, wherein the reading area of ​​each of the N radio frequency devices is set to be located on a corresponding virtual lane among the N virtual lanes, where N is a positive integer greater than or equal to 2, the N radio frequency devices are used to read the electronic tags recorded on non-motorized vehicles, and the N virtual lanes are virtual lanes obtained by dividing the target driving lane;

[0033] Step S304: If the reading results of the N radio frequency devices include the first electronic tag read by the first radio frequency device among the N radio frequency devices, determine the first non-motorized vehicle object located in the first image area in the target image information. The first reading area of ​​the first radio frequency device is set to be located on the first virtual lane among the N virtual lanes. The first image area corresponds to the first reading area on the first virtual lane. The target image information is the image information captured by the target camera. The shooting area of ​​the target camera includes the target driving lane.

[0034] Step S306: Bind the first electronic tag to the first non-motorized vehicle object in the target image information.

[0035] Through the above steps, when a non-motorized vehicle passes through the first reading area of ​​the first radio frequency device, the first radio frequency device reads the first electronic tag and then identifies the first non-motorized vehicle located in the first image area in the target image information. The first reading area is set to be located on the first virtual lane, and the first image area corresponds to the first reading area on the first virtual lane. The target image information is image information obtained by the target camera capturing an area including the target driving lane. Then, the first electronic tag is bound to the first non-motorized vehicle in the target image information. By first identifying the first electronic tag of the non-motorized vehicle and then binding it to the first non-motorized vehicle in the target image information, the first radio frequency device is responsible for identifying the electronic tag of the non-motorized vehicle, while the target camera is mainly responsible for capturing the non-motorized vehicle's driving behavior. Therefore, it is possible to improve the accuracy of tag recognition of non-motorized vehicles in the image without needing to add a new high-resolution camera to identify the non-motorized vehicle tag, thus solving the problem of low accuracy in non-motorized vehicle recognition in related technologies and achieving the effect of improving the accuracy of non-motorized vehicle recognition.

[0036] The entity executing the above steps can be a processor, a server, or a terminal device, such as an image analysis device or an image processing device, or a processor with human-computer interaction capabilities configured on a storage device, or a processing device or processing unit with similar processing capabilities, but is not limited to these. The following explanation uses a processor performing the above operations as an example (this is merely an illustrative example; in actual operation, other devices or modules can also perform the above operations):

[0037] In the above embodiment, the processor acquires the reading results from N radio frequency (RF) devices. The reading area of ​​each of the N RF devices is set to be located on a corresponding virtual lane among the N virtual lanes, where N is a positive integer greater than or equal to 2. The N RF devices are used to read the electronic tags recorded on non-motorized vehicles, and the N virtual lanes are virtual lanes obtained by dividing the target driving lane. Figure 4 This is an example of an application scenario according to a specific embodiment of the present invention. Figure 1 , Figure 4 The non-motorized vehicle lane is divided into 3 virtual lanes (this is just an example; there could also be 2 or more virtual lanes), and each of the 3 virtual lanes is equipped with a radio frequency device (e.g., Figure 4 (RFID1~RFID3), each radio frequency device's reading area (or identification area) corresponds to a virtual lane. When a non-motorized vehicle passes through the reading area of ​​the virtual lane (corresponding to...) Figure 4 The text describes a process involving multiple radio frequency (RF) devices. The first RF device reads the electronic tag (or license plate) of a non-motorized vehicle within the corresponding virtual lane (shaded area). In practical applications, each RF device uses a near-field antenna or a low-power linearly polarized directional far-field antenna, with its control range covering only the non-motorized vehicle portion of the corresponding reading area. Once the RF device reads the electronic tag of a non-motorized vehicle, it transmits the reading result to the processor (or backend device). If the reading results from N RF devices include the first electronic tag read by the first RF device, the first non-motorized vehicle located in the first image area is determined from the target image information. The first reading area of ​​the first RF device is set to be located on the first virtual lane among the N virtual lanes. The first image area corresponds to the first reading area on the first virtual lane. The target image information is the image information captured by the target camera, and the camera's shooting area includes the target driving lane. For example, the first RF device... Figure 4The radio frequency device above the virtual lane in the middle uses an electronic tag for non-motorized vehicles in the shaded area of ​​the virtual lane. The device then identifies non-motorized vehicles located in a first image region within the target image information. This first image region can correspond to a first reading region. For example, based on the reading results from the radio frequency device, the non-motorized vehicle in the corresponding first image region is identified as the first non-motorized vehicle object in the target image information. Then, the first electronic tag is bound to the first non-motorized vehicle object in the target image information. Optionally, when the first non-motorized vehicle object is identified in the target image information, the bound first electronic tag and the first non-motorized vehicle object can also be displayed in the target image information. For example, the detection frames of the first electronic tag and the first non-motorized vehicle object can be bound together for display, and the first electronic tag and the first non-motorized vehicle object can be dynamically displayed in subsequently acquired image information. This embodiment enables efficient and accurate identification of license plates (or electronic tags) of non-motorized vehicles in the corresponding reading areas by each of the N radio frequency devices, even in situations with multiple non-motorized vehicle targets. The license plates are then linked to the corresponding non-motorized vehicles in the target image information. Furthermore, when subsequent image information analysis reveals a violation by a non-motorized vehicle, evidence of the violation can be promptly collected. This avoids the low accuracy issues associated with related technologies that primarily rely on image analysis to identify license plates, and also avoids the high costs associated with using high-resolution cameras for license plate identification. Therefore, it solves the problem of low accuracy in non-motorized vehicle identification in related technologies, thereby improving the overall accuracy of non-motorized vehicle identification.

[0038] In an optional embodiment, determining the first non-motorized vehicle object located in the first image region in the target image information includes: acquiring a target frame image of a target time in the target image information, wherein the target time is the time when the first radio frequency device reads the first electronic tag, and the reading results of the N radio frequency devices include the target time; and determining the non-motorized vehicle object identified in the first image region in the target frame image as the first non-motorized vehicle object. In this embodiment, based on the target time when the first radio frequency device reads the first electronic tag, or based on the target time when the first radio frequency device uploads the reading result to the processor (or back-end device), a target frame image corresponding to the target time is acquired in the target image information. Then, the non-motorized vehicle object identified in the first image region in the target frame image is determined as the first non-motorized vehicle object (i.e., the non-motorized vehicle corresponding to the first electronic tag). Figure 4 For example, the first radio frequency device (such as...) Figure 4The radio frequency device (RF device) above the middle virtual lane reads the first electronic tag, then identifies the non-motorized vehicle object from the first image region of the target frame image (the region corresponding to the shaded part of the middle virtual lane), and identifies the non-motorized vehicle object as the first non-motorized vehicle object. This embodiment achieves the goal of identifying the corresponding first non-motorized vehicle object in the target image information when the first RF device reads the first electronic tag, fully demonstrating the advantage of RF identification accuracy and avoiding the problems of low efficiency and low accuracy caused by relying mainly on pure image analysis to identify non-motorized vehicle license plates in related technologies.

[0039] In an optional embodiment, the method further includes: when the reading results of the N radio frequency devices include the first electronic tag read by the first radio frequency device and the second electronic tag read by the second radio frequency device among the N radio frequency devices, and the first electronic tag and the second electronic tag are read simultaneously, determining the first non-motorized vehicle object located in the first image area and the second non-motorized vehicle object located in the second image area in the target image information, wherein the second reading area of ​​the second radio frequency device is set to be located on the second virtual lane among the N virtual lanes, and the second image area corresponds to the second reading area on the second virtual lane; binding the first electronic tag to the first non-motorized vehicle object and binding the second electronic tag to the second non-motorized vehicle object in the target image information. In this embodiment, when multiple radio frequency devices among the N radio frequency devices read the electronic tag simultaneously, taking the simultaneous reading of the electronic tag by the first radio frequency device and the second radio frequency device as an example, this is only an example and is not limited to only two radio frequency devices reading the electronic tag simultaneously. It can also be that more radio frequency devices read the electronic tag simultaneously. For example, in practical applications, when multiple non-motorized vehicles pass side by side... Figure 4 In the shaded area, multiple radio frequency (RF) devices above the virtual lanes simultaneously read the electronic tags of non-motorized vehicles and transmit the reading results to the processor (or backend device). Because related technologies use far-field antennas and have large recognition areas, they cannot pinpoint the relative position of license plates. For example, if an RF device reports two license plate results simultaneously, it cannot distinguish which license plate corresponds to a non-motorized vehicle on the left and which corresponds to a non-motorized vehicle on the right. However, the solution in this embodiment uses a reading area corresponding to each RF device. For example, the first RF device corresponds to the first reading area, and the second RF device corresponds to the second reading area. Assuming the first reading area is... Figure 4 The shaded area in the middle of the virtual lane is the second reading area. Figure 4The shaded area of ​​the virtual lane in the lower center allows for accurate association of non-motorized vehicles with the first electronic tag read by the first radio frequency device when analyzing frame images in the target image information. Similarly, it allows for accurate identification of the non-motorized vehicle in the first image area corresponding to the second electronic tag read by the second radio frequency device. Furthermore, it enables the binding of the first electronic tag to the first non-motorized vehicle and the second electronic tag to the second non-motorized vehicle in the target image information. This embodiment achieves the goal of accurately distinguishing the electronic tag corresponding to each non-motorized vehicle in the target image information when multiple non-motorized vehicle targets are simultaneously identified.

[0040] In an optional embodiment, the method further includes: when the reading results of the N radio frequency devices include the first electronic tag and the third electronic tag read sequentially by the first radio frequency device, determining the first non-motorized vehicle object and the third non-motorized vehicle object appearing sequentially in the first image area in the target image information; binding the first electronic tag to the first non-motorized vehicle object and binding the third electronic tag to the third non-motorized vehicle object in the target image information. In this embodiment, when the reading results include the first electronic tag and the third electronic tag read sequentially by the first radio frequency device, the non-motorized vehicle objects appearing sequentially in the first image area in the target image information can be combined to determine the first non-motorized vehicle object corresponding to the first electronic tag and the third non-motorized vehicle object corresponding to the third electronic tag, and then binding the first electronic tag to the first non-motorized vehicle object and binding the third electronic tag to the third non-motorized vehicle object in the target image information. In practical applications, when the time interval between the reading of the first and third electronic tags is large, or when the time interval between the non-motorized vehicles corresponding to the first and third electronic tags passing through the reading area (such as the first reading area) is long, the image frames in the target image information corresponding to the reading times of the first and third electronic tags (i.e., two frames in total) can be used to determine the first and third non-motorized vehicles from the two frames. In this case, only one non-motorized vehicle may appear in the first image area (corresponding to the first reading area of ​​the first radio frequency) in each frame. Conversely, when the time interval between the reading of the first and third electronic tags is small, two non-motorized vehicles may appear simultaneously in or near the first image area of ​​a frame in the target image information. In this case, the two non-motorized vehicles that arrived at the first reading area sequentially can be determined from the frame images of the target image information based on the order in which the first and third electronic tags are read by the first radio frequency. Through this embodiment, when different electronic tags are identified sequentially in the same virtual lane, different non-motorized vehicles that arrived at the radio frequency reading area sequentially can be accurately matched from the target image information based on their chronological order.

[0041] In an optional embodiment, the step of determining the first non-motorized vehicle object and the third non-motorized vehicle object that appear sequentially in the first image area in the target image information, binding the first electronic tag to the first non-motorized vehicle object in the target image information, and binding the third electronic tag to the third non-motorized vehicle object includes: acquiring a first frame image at a first moment in the target image information, wherein the first moment is the moment when the first radio frequency device reads the first electronic tag, and the reading results of the N radio frequency devices include the first moment; if a non-motorized vehicle object is identified in the first image area in the first frame image, the identified non-motorized vehicle object is identified as the first non-motorized vehicle object, and the first electronic tag is bound to the first non-motorized vehicle object. Binding; Obtaining a second frame image at a second moment from the target image information, wherein the second moment is the moment when the first radio frequency device reads the third electronic tag, the reading results of the N radio frequency devices include the second moment, the second moment is later than the first moment, and the first electronic tag and the third electronic tag are electronic tags read by the first radio frequency device in two consecutive reads; In the case where two non-motorized vehicle objects are identified in the first image region of the second frame image, and the non-motorized vehicle object that is forward in the driving direction is bound to the first electronic tag as the first non-motorized vehicle object, the non-motorized vehicle object that is backward in the driving direction is identified as the third non-motorized vehicle object, and the third electronic tag is bound to the third non-motorized vehicle object. Combined with... Figure 5 This embodiment will be described below. Figure 5 This is an example of an application scenario according to a specific embodiment of the present invention. Figure 2 When the read result includes the first radio frequency device (such as...) Figure 5 The radio frequency device above the virtual lane in the middle of the lane read the first electronic tag (such as...). Figure 5 Central African motor vehicle A) and third electronic tags (such as Figure 5 (For example, in the case of non-motorized vehicles B), the first electronic tag is read by the first radio frequency device at the first moment. Then, the first frame image at the first moment is obtained from the target image information. When a non-motorized vehicle object is identified in the first image region of the first frame image, such as... Figure 5 In the lower left image, the non-motorized vehicle is designated as the first non-motorized vehicle, and the first electronic tag is bound to the first non-motorized vehicle. Figure 5In the scenario shown in the left image, when the non-motorized vehicle corresponding to the third electronic tag passes through the first reading area of ​​the first radio frequency device, there may be a long time interval between it and the preceding non-motorized vehicle (such as the non-motorized vehicle corresponding to the first electronic tag). Thus, in the frame image corresponding to the moment the third electronic tag is read, there will only be one non-motorized vehicle object in the corresponding first image area. In this case, this non-motorized vehicle object can be identified as the third non-motorized vehicle object. However, regarding... Figure 5 In the scenario shown in the right-hand diagram, when the time interval between reading the first and third electronic tags in the reading result is small (i.e., the time interval between two non-motorized vehicles passing through the first reading area is short), the second frame image at the second moment is obtained from the target image information. When two non-motorized vehicle objects are identified in the first image area of ​​the second frame image, and the non-motorized vehicle that is in front of the first non-motorized vehicle is already bound to the first electronic tag, the non-motorized vehicle that is behind the second non-motorized vehicle can be identified as the third non-motorized vehicle object. Then, the third electronic tag is bound to the third non-motorized vehicle object. Since the same method as the aforementioned embodiment is used, when the first electronic tag of the first non-motorized vehicle is read first, the first electronic tag has already been bound to the first non-motorized vehicle object in the target image information. When the second frame image is obtained, the non-motorized vehicle that is in front of the first non-motorized vehicle in the image (e.g., the first electronic tag of the first non-motorized vehicle is read first) is then bound to the first non-motorized vehicle object. Figure 5 In the diagram on the right, A) has been bound to the first electronic tag, which will enable accurate identification of the non-motorized vehicle at the rear as the third non-motorized vehicle.

[0042] In an optional embodiment, after binding the first electronic tag to the first non-motorized vehicle object in the target image information, the method further includes: when it is determined based on the target image information that the first non-motorized vehicle object exhibits a target behavior, capturing a frame image of a third moment in the target image information, wherein the third moment is used to indicate the time when the first non-motorized vehicle object exhibits the target behavior; storing the frame image of the third moment and the first electronic tag with a corresponding relationship; or when it is determined based on the target image information that the first non-motorized vehicle object exhibits a target behavior, capturing a target image information segment in the target image information, wherein the target image information segment includes the frame image of the third moment; storing the target image information segment and the first electronic tag with a corresponding relationship. In this embodiment, when it is determined through analysis of the target image information that the first non-motorized vehicle exhibits a target behavior, the target behavior could be a violation by the non-motorized vehicle, such as running a red light, crossing a solid line, or illegally changing lanes. In practical applications, the existence of a target behavior can be determined by analyzing the behavioral characteristics of the first non-motorized vehicle in the target image information. When it is determined that the first non-motorized vehicle exhibits a target behavior at a third moment, a frame image of the third moment can be captured from the target image information, and the frame image of the third moment can be stored in correspondence with the first electronic tag, i.e., storing the frame image of the third moment and the first electronic tag with a corresponding relationship; or, when it is determined that the first non-motorized vehicle exhibits a target behavior at a third moment, a segment of target image information, including the frame image of the third moment, can be captured, and the target image information segment with a corresponding relationship can be stored with the first electronic tag. This achieves the purpose of timely evidence collection of the target behavior, avoiding the problem in related technologies where image information analysis is used to confirm the license plate of the non-motorized vehicle after the target behavior occurs, resulting in untimely evidence collection, and also potentially leading to license plate misidentification. This embodiment achieves the goal of timely evidence collection from non-motorized vehicles that have engaged in the target behavior.

[0043] Obviously, the embodiments described above are only some embodiments of the present invention, and not all embodiments. The present invention will be specifically described below using a multi-target non-motorized vehicle violation monitoring system as an example.

[0044] The monitoring system mainly consists of each set of radio frequency antennas to control the corresponding area, identify the radio frequency license plates of non-motorized vehicles passing through different locations at different times, and match the license plate information (corresponding to the aforementioned electronic tags, such as the first, second, and third electronic tags) with the non-motorized vehicles captured by the image information through simple location information (front and rear + left and right lanes), and bind the radio frequency identified license plates with the non-motorized vehicles in the image.

[0045] This invention can solve the problem of matching images of non-motorized vehicles with radio frequency license plates under multi-target conditions. Furthermore, it delegates license plate recognition to radio frequency, ensuring high accuracy. Meanwhile, image recognition handles the identification of non-motorized vehicle violations. The combination of these two methods results in a non-motorized vehicle management solution that is highly accurate, high-performance, and low-cost.

[0046] The construction layout of the non-motorized vehicle violation monitoring system based on radio frequency and image information is the same as... Figure 4 Among them, the camera (or webcam) can be an existing old camera in the city traffic that can capture non-motorized vehicle lanes, because it is only necessary to identify the non-motorized vehicle target and the corresponding violation, so the camera pixel requirement is not high.

[0047] The radio frequency (RF) antenna requires a RF pole to be erected above the non-motorized vehicle lane. Then, a near-field antenna or a low-power linearly polarized directional far-field antenna should be used, with the control range covering only the corresponding non-motorized vehicle section, such as... Figure 4 As shown, the wider non-motorized vehicle lane can be divided into three virtual lanes from left to right by dashed lines (corresponding to the aforementioned virtual lanes). The license plates of non-motorized vehicles passing through each virtual lane will be read by the corresponding antenna (corresponding to the aforementioned electronic tags).

[0048] Therefore, when 2-3 non-motorized vehicles cross side by side, such as Figure 6 As shown, Figure 6 This is an example of an application scenario according to a specific embodiment of the present invention. Figure 3 We can match non-motorized vehicles in the left, center, and right positions by using different radio frequency license plates read from different antennas. For non-motorized vehicles traveling in front and behind each other in the same lane, we can match them by the time it takes for the antenna to read the license plate. Figure 5 As shown.

[0049] This embodiment controls the limited read / write range of the antenna to easily determine the front, back, left, and right positions of the read license plate. The position is then matched with the non-motorized vehicle target in the image information. Therefore, by assigning a non-motorized vehicle license plate to the non-motorized vehicle in the image information using unified location information, evidence can be promptly collected and saved when subsequent image information identifies a non-motorized vehicle violation (corresponding to the aforementioned target behavior).

[0050] Figure 7 This is a flowchart of a method for collecting evidence of traffic violations by non-motorized vehicles according to an embodiment of the present invention, including the following steps:

[0051] S702, the radio frequency reads the electronic tag information; in this step, it is necessary to first adjust the reading and writing range of the radio frequency reading and writing antenna to achieve the area control effect of multiple antennas; divide the non-motorized vehicle lane into multiple virtual lanes through multiple radio frequency reading and writing antennas; at the same time, confirm in the image information that each radio frequency antenna can read the area of ​​license plate recognition (corresponding to the aforementioned first image area and second image area).

[0052] S704, Non-motorized vehicle targets are detected in the camera control area; The camera (or camera) is mainly responsible for capturing image information to record the driving situation of vehicles on the non-motorized vehicle lane. Of course, the image information can also record the situation on the motorized vehicle lane or the sidewalk.

[0053] It should be noted that there is no strict order for the above steps S702 and S704. Step S704 can be executed first, followed by step S702, or S702 and S704 can be executed simultaneously.

[0054] S706, based on the left and right lanes and the entry time of the front and rear of the electronic tag, matches the non-motorized vehicle targets in the image information and assigns license plates to the targets;

[0055] When multiple non-motorized vehicles pass parallel or sequentially through the license plate recognition area (corresponding to the aforementioned reading area) of the non-motorized vehicle lane, the non-motorized vehicle target in the image information is assigned an RFID license plate (corresponding to the aforementioned binding of the electronic tag to the non-motorized vehicle object), which may specifically include:

[0056] 1) Parallel non-motorized vehicle license plate matching logic: The license plate read by the left, center and right radio frequency antennas is assigned to the non-motorized vehicle in the same position in the image information;

[0057] 2) Matching logic for non-motorized vehicles in the same lane: Based on the license plate events read by the radio frequency antenna, match the non-motorized vehicles that arrive at the recognition area in the image information in sequence.

[0058] S708: After each non-motorized vehicle passes through the license plate recognition area in the image information, it is assigned an RFID license plate. The non-motorized vehicle is then tracked to identify its violations (corresponding to the aforementioned target behavior). When a violation is detected, the evidence is collected and saved, thus completing the subsequent business logic loop.

[0059] In other words, assigning radio frequency license plates to non-motorized vehicle targets in image information can facilitate further tracking, analysis, violation detection, and evidence collection.

[0060] The above embodiments effectively combine the high accuracy of image information in recognizing non-motorized vehicle violations with the high accuracy of radio frequency (RF) license plate recognition for non-motorized vehicle management. This overcomes the low accuracy problem of image information in recognizing non-motorized vehicle license plates in related technologies, enabling users to conduct more accurate targeted management. Furthermore, the inclusion of the RF solution reduces overall costs, further facilitating the construction of smart transportation and smart cities.

[0061] This embodiment differs from related technologies in the following ways: (1) The image does not recognize non-motor vehicle license plates, but only recognizes illegal acts of non-motor vehicle license plates. License plate recognition is completed by radio frequency equipment. In this embodiment, the matching between the vehicle in the image information and the license plate in the radio frequency is guaranteed; (2) The existing solution of first recognizing illegal non-motor vehicles and then recognizing their corresponding license plates is changed to first recognizing all non-motor vehicle license plates and then tracking whether they violate regulations; (3) The antenna of the radio frequency equipment is changed from a far-field wide-coverage antenna to a near-field linearly polarized directional antenna to ensure the regional control effect of the antenna array so as to meet the matching effect between the radio frequency license plate and the vehicle in the image information.

[0062] The embodiments of the present invention have the following advantages: (1) low cost, no need to add a new high-pixel camera to identify non-motor vehicle license plates, and old traffic management cameras can be used; (2) accurate license plate recognition, no interference from radio frequency identification of license plates, avoiding the potential inaccuracy or alteration of image recognition; (3) in the case of multiple non-motor vehicle targets, the image recognition target and the radio frequency target can be accurately matched through location information; (4) the license plate uses a passive radio frequency tag, which does not require regular battery replacement, improving feasibility.

[0063] It should be noted that when this method is applied to other fields, such as the Internet of Things or Ethernet data processing, it can also efficiently process large amounts of traffic data and deduplicate specific target data, thereby improving the accuracy of data processing and analysis results.

[0064] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0065] This embodiment also provides a non-motorized vehicle identification device. Figure 8This is a structural block diagram of a non-motorized vehicle identification device according to an embodiment of the present invention, such as... Figure 8 As shown, the device includes:

[0066] The acquisition module 802 is used to acquire the reading results of N radio frequency devices, wherein the reading area of ​​each of the N radio frequency devices is set to be located on a corresponding virtual lane among the N virtual lanes, where N is a positive integer greater than or equal to 2, the N radio frequency devices are used to read the electronic tags recorded on non-motorized vehicles, and the N virtual lanes are virtual lanes obtained by dividing the target driving lane;

[0067] The first determining module 804 is configured to determine a first non-motorized vehicle object located in a first image region in the target image information when the reading results of the N radio frequency devices include a first electronic tag read by the first radio frequency device among the N radio frequency devices. The first reading region of the first radio frequency device is set to be located on a first virtual lane among the N virtual lanes, and the first image region corresponds to the first reading region on the first virtual lane. The target image information is image information captured by a target camera, and the capturing area of ​​the target camera includes the target driving lane.

[0068] The first binding module 806 is used to bind the first electronic tag to the first non-motorized vehicle object in the target image information.

[0069] In an optional embodiment, the first determining module 804 includes: an acquisition unit, configured to acquire a target frame image at a target time from the target image information, wherein the target time is the time when the first radio frequency device reads the first electronic tag, and the reading results of the N radio frequency devices include the target time; and a determining unit, configured to determine the non-motorized vehicle object identified in the first image region in the target frame image as the first non-motorized vehicle object.

[0070] In an optional embodiment, the above-mentioned device further includes: a second determining module, configured to determine, in the target image information, a first non-motorized vehicle object located in the first image area and a second non-motorized vehicle object located in the second image area when the reading results of the N radio frequency devices include the first electronic tag read by the first radio frequency device and the second electronic tag read by the second radio frequency device among the N radio frequency devices, and the first electronic tag and the second electronic tag are read simultaneously, wherein the second reading area of ​​the second radio frequency device is set to be located on the second virtual lane among the N virtual lanes, and the second image area corresponds to the second reading area on the second virtual lane; and a second binding module, configured to bind the first electronic tag to the first non-motorized vehicle object and bind the second electronic tag to the second non-motorized vehicle object in the target image information.

[0071] In an optional embodiment, the above-mentioned device further includes: a third determining module, configured to determine, in the target image information, the first non-motorized vehicle object and the third non-motorized vehicle object appearing sequentially in the first image area when the reading results of the N radio frequency devices include the first electronic tag and the third electronic tag read sequentially by the first radio frequency device; and a third binding module, configured to bind the first electronic tag to the first non-motorized vehicle object and bind the third electronic tag to the third non-motorized vehicle object in the target image information.

[0072] In an optional embodiment, the above-described apparatus is further configured to determine the first non-motorized vehicle object and the third non-motorized vehicle object, and to bind the first electronic tag to the first non-motorized vehicle object and the third electronic tag to the third non-motorized vehicle object in the following manner: acquiring a first frame image at a first moment in the target image information, wherein the first moment is the moment when the first radio frequency device reads the first electronic tag, and the reading results of the N radio frequency devices include the first moment; if a non-motorized vehicle object is identified in the first image region in the first frame image, the identified non-motorized vehicle object is identified as the first non-motorized vehicle object, and the first electronic tag is bound to the first non-motorized vehicle object; in the target image information The second frame image at the second moment is obtained, wherein the second moment is the moment when the first radio frequency device reads the third electronic tag, and the reading results of the N radio frequency devices include the second moment, which is later than the first moment. The first electronic tag and the third electronic tag are electronic tags read by the first radio frequency device in two consecutive steps. If two non-motorized vehicle objects are identified in the first image area of ​​the second frame image, and the non-motorized vehicle object that is forward in the driving direction is identified as the first non-motorized vehicle object and bound to the first electronic tag, the non-motorized vehicle object that is backward in the driving direction is identified as the third non-motorized vehicle object, and the third electronic tag is bound to the third non-motorized vehicle object.

[0073] In an optional embodiment, the above apparatus further includes: a first interception module, configured to, after binding the first electronic tag to the first non-motorized vehicle object in the target image information, and when it is determined based on the target image information that the first non-motorized vehicle object exhibits target behavior, intercept a frame image of a third moment in the target image information, wherein the third moment is used to indicate the moment when the first non-motorized vehicle object exhibits target behavior; a first storage module, configured to store the frame image of the third moment and the first electronic tag having a corresponding relationship; or, a second interception module, configured to, when it is determined based on the target image information that the first non-motorized vehicle object exhibits target behavior, intercept a target image information segment in the target image information, wherein the target image information segment includes the frame image of the third moment; a second storage module, configured to store the target image information segment and the first electronic tag having a corresponding relationship.

[0074] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0075] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0076] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0077] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0078] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0079] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0080] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0081] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for identifying non-motorized vehicles, characterized in that, include: Obtain the reading results of N radio frequency devices, wherein the reading area of ​​each of the N radio frequency devices is set to be located on a corresponding virtual lane among the N virtual lanes, where N is a positive integer greater than or equal to 2, the N radio frequency devices are used to read the electronic tags recorded on non-motorized vehicles, and the N virtual lanes are virtual lanes obtained by dividing the target driving lane; If the reading results of the N radio frequency devices include the first electronic tag read by the first radio frequency device among the N radio frequency devices, the first non-motorized vehicle object located in the first image area is determined in the target image information. The first reading area of ​​the first radio frequency device is set to be located on the first virtual lane among the N virtual lanes. The first image area corresponds to the first reading area on the first virtual lane. The target image information is the image information captured by the target camera. The shooting area of ​​the target camera includes the target driving lane. The first electronic tag is bound to the first non-motorized vehicle object in the target image information; The method further includes: when the reading results of the N radio frequency devices include the first electronic tag read by the first radio frequency device and the second electronic tag read by the second radio frequency device among the N radio frequency devices, and the first electronic tag and the second electronic tag are read simultaneously, determining the first non-motorized vehicle object located in the first image area and the second non-motorized vehicle object located in the second image area in the target image information, wherein the second reading area of ​​the second radio frequency device is set to be located on the second virtual lane among the N virtual lanes, and the second image area corresponds to the second reading area on the second virtual lane; binding the first electronic tag to the first non-motorized vehicle object and binding the second electronic tag to the second non-motorized vehicle object in the target image information.

2. The method according to claim 1, characterized in that, The step of determining the first non-motorized vehicle object located in the first image region from the target image information includes: Obtain a target frame image at a target time from the target image information, wherein the target time is the time when the first radio frequency device reads the first electronic tag, and the reading results of the N radio frequency devices include the target time; The non-motorized vehicle object identified in the first image region of the target frame image is determined as the first non-motorized vehicle object.

3. The method according to claim 1, characterized in that, The method further includes: If the reading results of the N radio frequency devices include the first electronic tag and the third electronic tag read by the first radio frequency device in sequence, the first non-motorized vehicle object and the third non-motorized vehicle object that appear in the first image area in sequence are determined from the target image information. In the target image information, the first electronic tag is bound to the first non-motorized vehicle object, and the third electronic tag is bound to the third non-motorized vehicle object.

4. The method according to claim 3, characterized in that, The step of determining the first non-motorized vehicle object and the third non-motorized vehicle object that appear sequentially in the first image area from the target image information, binding the first electronic tag to the first non-motorized vehicle object in the target image information, and binding the third electronic tag to the third non-motorized vehicle object includes: The first frame image at a first moment is obtained from the target image information, wherein the first moment is the moment when the first radio frequency device reads the first electronic tag, and the reading results of the N radio frequency devices include the first moment; If a non-motorized vehicle object is identified in the first image region of the first frame image, the identified non-motorized vehicle object is identified as the first non-motorized vehicle object, and the first electronic tag is bound to the first non-motorized vehicle object; The second frame image at the second moment is obtained from the target image information, wherein the second moment is the moment when the first radio frequency device reads the third electronic tag, the reading results of the N radio frequency devices include the second moment, the second moment is later than the first moment, and the first electronic tag and the third electronic tag are electronic tags read by the first radio frequency device in two consecutive steps; If two non-motorized vehicle objects are identified in the first image region of the second frame image, and the non-motorized vehicle object that is forward in the direction of travel is bound to the first electronic tag as the first non-motorized vehicle object, then the non-motorized vehicle object that is backward in the direction of travel is identified as the third non-motorized vehicle object, and the third electronic tag is bound to the third non-motorized vehicle object.

5. The method according to claim 1, characterized in that, After binding the first electronic tag to the first non-motorized vehicle object in the target image information, the method further includes: When it is determined based on the target image information that the first non-motorized vehicle object exhibits target behavior, a frame image at a third moment is captured from the target image information, wherein the third moment indicates the time when the first non-motorized vehicle object exhibits target behavior; the frame images at the third moment with corresponding relationships are stored with the first electronic tag; or When it is determined that the first non-motorized vehicle object has a target behavior based on the target image information, a target image information segment is extracted from the target image information, wherein the target image information segment includes the frame image at the third moment; the target image information segment with a corresponding relationship and the first electronic tag are stored.

6. A non-motorized vehicle identification device, characterized in that, include: The acquisition module is used to acquire the reading results of N radio frequency devices, wherein the reading area of ​​each of the N radio frequency devices is set to be located on a corresponding virtual lane among the N virtual lanes, where N is a positive integer greater than or equal to 2, the N radio frequency devices are used to read the electronic tags recorded on non-motorized vehicles, and the N virtual lanes are virtual lanes obtained by dividing the target driving lane; The first determining module is configured to determine a first non-motorized vehicle object located in a first image region in the target image information when the reading results of the N radio frequency devices include a first electronic tag read by the first radio frequency device among the N radio frequency devices. The first reading region of the first radio frequency device is set to be located on a first virtual lane among the N virtual lanes, and the first image region corresponds to the first reading region on the first virtual lane. The target image information is image information captured by a target camera, and the shooting area of ​​the target camera includes the target driving lane. The first binding module is used to bind the first electronic tag to the first non-motorized vehicle object in the target image information; The aforementioned device further includes: a second determining module, configured to, when the reading results of the N radio frequency devices include the first electronic tag read by the first radio frequency device and the second electronic tag read by the second radio frequency device among the N radio frequency devices, and the first electronic tag and the second electronic tag are read simultaneously, determine, in the target image information, the first non-motorized vehicle object located in the first image area and the second non-motorized vehicle object located in the second image area, wherein the second reading area of ​​the second radio frequency device is set to be located on the second virtual lane among the N virtual lanes, and the second image area corresponds to the second reading area on the second virtual lane; and a second binding module, configured to bind the first electronic tag to the first non-motorized vehicle object and bind the second electronic tag to the second non-motorized vehicle object in the target image information.

7. The apparatus according to claim 6, characterized in that, The first determining module includes: An acquisition unit is configured to acquire a target frame image at a target time from the target image information, wherein the target time is the time when the first radio frequency device reads the first electronic tag, and the reading results of the N radio frequency devices include the target time; The determining unit is used to determine the non-motorized vehicle object identified in the first image region of the target frame image as the first non-motorized vehicle object.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of claims 1 to 5.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 5.

Images