Roadside parking charging method and device, computer equipment, storage medium and program product
By using image recognition technology that combines bullet cameras and dome cameras, the shortcomings of geomagnetic and manual modes in roadside parking management have been solved, enabling unmanned and accurate roadside parking billing, reducing costs and forming a complete chain of evidence.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-31
- Publication Date
- 2026-04-03
AI Technical Summary
In existing technologies, roadside parking management relies on geomagnetic sensors and manual management. Geomagnetic solutions damage the road surface and have limited functionality, while manual methods are costly and inefficient, making it difficult to achieve unmanned operation and accurate roadside parking billing.
By using a combination of bullet cameras and dome cameras, and deploying image recognition technology on poles, vehicle information is identified and billing is performed, forming a complete chain of evidence and avoiding damage to the road surface and reliance on manual labor.
It achieves fully automated, unattended operation and accurate billing, reduces operating costs, ensures transparent and reliable billing, forms full-process image evidence, and is suitable for 24-hour unattended management.
Smart Images
Figure CN121789302A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent transportation technology, and in particular to a roadside parking billing method, device, computer equipment, storage medium and program product. Background Technology
[0002] With the acceleration of urbanization and the continuous increase in the number of motor vehicles, roadside parking has become an indispensable and important way to alleviate urban parking pressure. Therefore, how to manage roadside parking efficiently and orderly has also become an indispensable and key task in urban governance.
[0003] Traditional roadside parking management relies primarily on two methods: geomagnetic sensors and manual management. Geomagnetic sensors require road surface damage for deployment, are difficult to maintain, and cannot identify vehicles. Manual management, on the other hand, is costly, inefficient, and struggles to achieve 24 / 7 unmanned operation.
[0004] Therefore, how to achieve accurate roadside parking billing without damaging the road surface or relying on manual labor has become an urgent problem to be solved. Summary of the Invention
[0005] Therefore, it is necessary to provide a roadside parking billing method, device, computer equipment, storage medium, and program product that can achieve accurate roadside parking billing without damaging the road surface or relying on manual labor, in order to address the above-mentioned technical problems.
[0006] In a first aspect, this application provides a roadside parking fee calculation method, comprising: receiving a first roadside parking space scene image and a target parking space number sent by a bullet camera, wherein the first roadside parking space scene image is an image captured by the bullet camera when it detects a vehicle entering the roadside parking space; sending a first shooting command to a first dome camera based on the target parking space number, and receiving a first vehicle image of the target vehicle in the target parking space sent by the first dome camera; the first dome camera and the bullet camera are on the same pole; recognizing the first roadside parking space scene image and the first vehicle image to obtain the vehicle information of the target vehicle entering the parking space; and sending the vehicle information to a roadside parking fee calculation platform so that the roadside parking fee calculation platform can start calculating fees for the target vehicle based on the vehicle information.
[0007] In one embodiment, the method further includes: receiving a second roadside parking space scene image and a target parking space number sent by a bullet camera, wherein the second roadside parking space scene image is an image captured by the bullet camera when it detects a vehicle leaving the roadside parking space; sending a second shooting command to a first dome camera based on the target parking space number, and receiving an empty space image of the target parking space sent by the first dome camera; obtaining the vehicle information of the target vehicle leaving based on the empty space image; and sending the vehicle information of the leaving vehicle to the roadside parking billing platform so that the roadside parking billing platform can terminate the billing of the target vehicle based on the vehicle information of the leaving vehicle.
[0008] In one embodiment, the method further includes: sending a first shooting command to a second spherical camera on a target pole based on the target parking space number, and receiving a second vehicle image of the target vehicle in the target parking space sent by the second spherical camera; wherein the target pole and the pole where the bullet camera is located are opposite poles; correspondingly, identifying the first roadside parking space scene image and the first vehicle image to obtain the vehicle information of the target vehicle entering the parking space, including: identifying the first roadside parking space scene image, the first vehicle image, and the second vehicle image to obtain the vehicle information of the target vehicle entering the parking space.
[0009] In one embodiment, the entry information of the target vehicle is obtained by recognizing the first roadside parking space scene image, the first vehicle image, and the second vehicle image, including: inputting the first roadside parking space scene image, the first vehicle image, and the second vehicle image into a vehicle recognition model to obtain the license plate number of the target vehicle; and obtaining the entry information of the target vehicle based on the license plate number, the entry time of the target vehicle, and the target vehicle image, wherein the target vehicle image is the first vehicle image and / or the second vehicle image.
[0010] In one embodiment, the method further includes: receiving an event type sent by a bullet camera; if the event type is an entry event, performing a step of sending a first shooting command to a first PTZ camera based on the target parking space number; if the event type is a departure event, performing a step of sending a second shooting command to the first PTZ camera based on the target parking space number.
[0011] In one embodiment, after sending the information of the entering vehicle to the roadside parking billing platform, the method further includes: sending a third shooting instruction to the first spherical camera, the third shooting instruction being used to instruct the spherical camera to take a round of shots of all the parking spaces that can be shot at a preset time interval.
[0012] Secondly, this application also provides a roadside parking metering device, comprising:
[0013] The first transceiver module is used to receive the first roadside parking space scene image and the target parking space number sent by the bullet camera. The first roadside parking space scene image is the image taken by the bullet camera when it detects a vehicle entering the roadside parking space.
[0014] The first transceiver module is also used to send a first shooting command to the first dome camera based on the target parking space number, and to receive the first vehicle image of the target vehicle in the target parking space sent by the first dome camera; the first dome camera and the bullet camera are on the same pole;
[0015] The recognition module is used to recognize the first roadside parking space scene image and the first vehicle image to obtain the vehicle information of the target vehicle entering the parking space.
[0016] The second transceiver module is used to send the information of the entering vehicle to the roadside parking billing platform, so that the roadside parking billing platform can start billing the target vehicle based on the information of the entering vehicle.
[0017] In one embodiment, the first transceiver module is further configured to receive a second roadside parking space scene image and a target parking space number sent by a bullet camera, wherein the second roadside parking space scene image is an image captured by the bullet camera when it detects a vehicle leaving the roadside parking space; the first transceiver module is further configured to send a second shooting command to a first dome camera based on the target parking space number, and receive an empty space image of the target parking space sent by the first dome camera; the second transceiver module is further configured to obtain the vehicle information of the target vehicle leaving based on the empty space image; and send the vehicle information of the leaving vehicle to the roadside parking billing platform so that the roadside parking billing platform can terminate the billing of the target vehicle based on the vehicle information of the leaving vehicle.
[0018] In one embodiment, the first transceiver module is further configured to send a first shooting command to the second spherical camera on the target pole based on the target parking space number, and receive a second vehicle image of the target vehicle in the target parking space sent by the second spherical camera; wherein the target pole and the pole where the bullet camera is located are opposing poles; correspondingly, the recognition module is specifically configured to recognize the first roadside parking space scene image, the first vehicle image and the second vehicle image to obtain the vehicle information of the target vehicle entering the parking space.
[0019] In one embodiment, the identification module is specifically used to input a first roadside parking space scene image, a first vehicle image, and a second vehicle image into a vehicle identification model to obtain the license plate number of the target vehicle; and to obtain the vehicle information of the target vehicle based on the license plate number, the entry time of the target vehicle, and the target vehicle image, wherein the target vehicle image is the first vehicle image and / or the second vehicle image.
[0020] In one embodiment, the first transceiver module is further configured to receive the event type sent by the bullet camera; in the case of an entry event, execute the step of sending a first shooting command to the first PTZ camera based on the target parking space number; in the case of an exit event, execute the step of sending a second shooting command to the first PTZ camera based on the target parking space number.
[0021] In one embodiment, the first transceiver module is further configured to send a third shooting instruction to the first spherical camera, the third shooting instruction being configured to instruct the spherical camera to take a round of shots of all parking spaces that can be shot at a preset time interval.
[0022] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any one of the first aspects above.
[0023] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects above.
[0024] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the first aspects above.
[0025] The aforementioned roadside parking fee calculation method, device, computer equipment, storage medium, and program product receive a first roadside parking space scene image and a target parking space number sent by a bullet camera. The first roadside parking space scene image is taken by the bullet camera when it detects a vehicle entering the roadside parking space. Then, based on the target parking space number, a first shooting command is sent to a first dome camera on the same pole as the bullet camera, and the first vehicle image of the target vehicle in the target parking space is received from the first dome camera. Subsequently, the first roadside parking space scene image and the first vehicle image are identified to obtain the vehicle information of the target vehicle, which is then sent to the roadside parking fee calculation platform so that the platform can start charging the target vehicle based on the vehicle information. Since the bullet camera and the first dome camera are deployed on the roadside pole, there is no need to damage the road surface. Roadside parking fee calculation is achieved by recognizing the images captured by the bullet camera and the first dome camera, eliminating the need for manual intervention. Therefore, the roadside parking fee calculation method of this application can achieve accurate roadside parking fee calculation without damaging the road surface or relying on manual intervention. Attached Figure Description
[0026] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0027] Figure 1 This is a diagram illustrating the application environment of a roadside parking billing method in one embodiment;
[0028] Figure 2 This is a flowchart illustrating a roadside parking billing method in one embodiment;
[0029] Figure 3 This is a flowchart illustrating the roadside parking billing method in another embodiment;
[0030] Figure 4 This is a schematic diagram illustrating the principle of roadside parking billing in one embodiment;
[0031] Figure 5 This is a structural block diagram of a roadside parking metering device in one embodiment;
[0032] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0033] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0034] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.
[0035] With the acceleration of urbanization and the continuous increase in the number of motor vehicles, roadside parking has become an indispensable and important way to alleviate urban parking pressure. Therefore, how to manage roadside parking efficiently and orderly has also become an indispensable and key task in urban governance.
[0036] Traditional roadside parking management relies primarily on two methods: geomagnetic sensors and manual management. The geomagnetic approach requires burying sensors beneath the road surface; however, construction damages the road structure, making maintenance and replacement extremely inconvenient. Furthermore, it lacks functionality and a chain of evidence, as geomagnetic sensors can only detect occupancy status and cannot obtain vehicle images or license plate information. This lack of comprehensive recording and evidence preservation of the parking process can easily lead to billing disputes. The manual method requires a large number of managers, resulting in high labor costs, low management efficiency, and difficulty in achieving 24-hour unmanned operation, thus failing to realize standardized, unmanned modern traffic management.
[0037] Therefore, how to achieve accurate roadside parking billing without damaging the road surface or relying on manual labor has become an urgent problem to be solved. The attached figures below illustrate in detail how this application solves the above-mentioned technical problems.
[0038] The roadside parking billing method provided in this application embodiment can be applied to, for example, Figure 1 The application environment is shown. Computer device 101 communicates with bullet camera 102, dome camera 103, and roadside parking fee collection platform 104. Computer device 101 is equipped with an edge computing unit and is deployed on-site at the roadside, possessing data acquisition, real-time computing, AI inference, and network communication capabilities. Pole-mounted devices are installed on both sides of the road, each equipped with one bullet camera 102 and one dome camera 103. The bullet camera 102 monitors a fixed area and is suitable for large-scale, continuous scene monitoring. The dome camera 103 has a pan-tilt-zoom (PTZ) mechanism to ensure its viewing angle covers parking spaces on the opposite side of the road and clearly captures license plates. It should be noted that the installation location and number of bullet cameras 102 and dome cameras 103 can be adaptively adjusted according to the monitoring range of a specific road segment. The roadside parking fee collection platform 104 can be a cloud platform.
[0039] In one exemplary embodiment, such as Figure 2 As shown, a roadside parking billing method is provided, which is applied to... Figure 1 The following steps, 201 to 204, are used as an example of computer equipment.
[0040] Step 201: Receive the first roadside parking space scene image and the target parking space number sent by the bullet camera. The first roadside parking space scene image is the image taken by the bullet camera when it detects a vehicle entering the roadside parking space.
[0041] The bullet camera captures images of roadside parking spaces in real time, creating a video stream. Based on image detection algorithms, the video stream is analyzed. Therefore, when a vehicle enters a roadside parking space, the bullet camera can detect the vehicle's stopping event and the parking space where the vehicle is stopping through the video stream and image detection algorithms.
[0042] When the bullet camera detects a vehicle stopping, it immediately captures an image of the scene, obtaining a first roadside parking space scene image. It then sends this first roadside parking space scene image and the target parking space number of the detected target vehicle to the computer device, which then receives the first roadside parking space scene image and the target parking space number sent by the bullet camera.
[0043] When the computer device receives the first roadside parking space scene image and the target parking space number, it is equivalent to triggering a vehicle stopping event, and the computer device will execute step 202.
[0044] Step 202: Send a first shooting command to the first dome camera based on the target parking space number, and receive the first vehicle image of the target vehicle in the target parking space sent by the first dome camera; the first dome camera and the bullet camera are on the same pole.
[0045] The first shooting command instructs the first spherical camera to rotate, aim at the front or rear of the target vehicle parked in the target parking space, capture the license plate, and obtain a high-resolution image. The target parking space is the parking space corresponding to the target parking space number.
[0046] In one possible implementation, after receiving a first shooting command, the first spherical camera rotates to capture a high-definition image of the front or rear of the target vehicle, i.e., a first vehicle image, and sends the first vehicle image to a computer device, so that the computer device can receive the first vehicle image sent by the first spherical camera.
[0047] Since the first vehicle image is taken by the first spherical camera pointing at the front or rear of the target vehicle, the first vehicle image contains the license plate number of the target vehicle.
[0048] Step 203: Recognize the first roadside parking space scene image and the first vehicle image to obtain the vehicle information of the target vehicle entering the parking space.
[0049] The information on the vehicles entering the area includes the license plate number, the entry time of the target vehicle, and a picture of the first vehicle. In addition, the information on the vehicles entering the area may also include vehicle structure information, which includes at least one of the following: license plate color (blue, yellow, white, black, green, etc.), license plate type (ordinary civilian vehicle license plate, police car, military vehicle, embassy / consulate license plate, etc.), vehicle type (sedan, truck, bus, etc.), vehicle color (red, white, black, blue, silver, etc.), and vehicle brand (Volkswagen, Toyota, BMW, Audi, etc.).
[0050] In one possible implementation, the visual algorithm service in the computer device inputs the first roadside parking space scene image and the first vehicle image into the vehicle recognition model to obtain the license plate number of the target vehicle; based on the license plate number, the entry time of the target vehicle, and the vehicle image, the entry vehicle information of the target vehicle is obtained.
[0051] In another possible implementation, the visual algorithm service in the computer device inputs the first roadside parking space scene image and the first vehicle image into the vehicle recognition model to obtain the license plate number and vehicle structure information of the target vehicle; based on the license plate number, vehicle structure information, the entry time of the target vehicle and the vehicle image, the entry vehicle information of the target vehicle is obtained.
[0052] The vehicle recognition model can be a multimodal large model, which refers to an artificial intelligence model capable of simultaneously processing and understanding multiple types of data such as images and text. The vehicle recognition model is a pre-trained model. The training method includes: inputting sample roadside parking space scene images and sample vehicle images into the model to be trained to obtain sample license plate numbers and sample vehicle structured information; calculating the first loss value and the second loss value corresponding to the sample license plate number and sample vehicle structured information respectively based on the loss function; weighting and summing the first loss value and the second loss value to obtain the target loss value; and tuning the parameters of the model to be trained based on this target loss value. After training, the vehicle recognition model is obtained.
[0053] The entry time of the target vehicle can be sent by the bullet camera along with the first roadside parking space scene image and the target parking space number, or it can be generated by the computer device after receiving the first roadside parking space scene image and the target parking space number sent by the bullet camera. There is no limitation here.
[0054] Step 204: Send the information of the entering vehicle to the roadside parking billing platform so that the roadside parking billing platform can start billing the target vehicle based on the information of the entering vehicle.
[0055] In other words, after receiving information about an entering vehicle, the roadside parking billing platform records the entry event as the basis for billing.
[0056] The aforementioned roadside parking fee calculation method involves receiving a first roadside parking space scene image and a target parking space number from a bullet camera. The first roadside parking space scene image is captured by the bullet camera when it detects a vehicle entering the roadside parking space. Then, based on the target parking space number, a first shooting command is sent to a first dome camera on the same pole as the bullet camera, and the method receives a first vehicle image of the target vehicle in the target parking space from the first dome camera. Subsequently, the first roadside parking space scene image and the first vehicle image are identified to obtain the vehicle entry information of the target vehicle. This entry information is then sent to the roadside parking fee calculation platform, which uses this information to begin charging the target vehicle. Since the bullet camera and the first dome camera are deployed on roadside poles, there is no need to damage the road surface. Roadside parking fee calculation is achieved by recognizing the images captured by the bullet camera and the first dome camera, eliminating the need for manual intervention. Therefore, the roadside parking fee calculation method of this application can achieve accurate roadside parking fee calculation without damaging the road surface or relying on manual labor.
[0057] In one exemplary embodiment, such as Figure 3 As shown, another method for calculating roadside parking fees is provided, which further includes steps 301 to 304. Wherein:
[0058] Step 301: Receive the second roadside parking space scene image and the target parking space number sent by the bullet camera. The second roadside parking space scene image is the image taken by the bullet camera when it detects a vehicle leaving the roadside parking space.
[0059] The bullet camera captures images of roadside parking spaces in real time, creating a video stream. Based on image detection algorithms, it analyzes the video stream. Therefore, when a vehicle leaves a roadside parking space, the bullet camera can detect the vehicle leaving the parking space through the video stream and image detection algorithms.
[0060] When the bullet camera detects a vehicle leaving the parking space, it immediately captures an image of the scene, obtaining a second roadside parking space scene image. It then sends this second roadside parking space scene image and the target parking space number of the detected target vehicle to the computer device, which receives the second roadside parking space scene image and the target parking space number sent by the bullet camera.
[0061] When the computer device receives the scene image of the second roadside parking space and the target parking space number, it is equivalent to triggering a vehicle departure event, and the computer device will execute step 302.
[0062] Step 302: Send a second shooting command to the first spherical camera based on the target parking space number, and receive the empty space image of the target parking space sent by the first spherical camera.
[0063] The second shooting command is used to instruct the first spherical camera to rotate and shoot at the target parking space corresponding to the target parking space number.
[0064] In one possible implementation, after receiving the second shooting instruction, the first spherical camera rotates according to the second shooting instruction to capture an image of the empty parking space corresponding to the target parking space number (which is now empty). The empty parking space image is then sent to a computer device, so that the computer device can receive the empty parking space image sent by the first spherical camera to preserve evidence that the vehicle has left the scene.
[0065] Step 303: Obtain the departure information of the target vehicle based on the empty space image.
[0066] The information on departing vehicles may include images of empty parking spaces, the departure time of the target vehicle, and its license plate number.
[0067] In one possible implementation, the departure information of the target vehicle is obtained based on the empty space image, the departure time of the target vehicle, and the license plate number.
[0068] The departure time of the target vehicle can be sent by the bullet camera along with the second roadside parking space scene image and the target parking space number, or it can be generated by the computer device after receiving the second roadside parking space scene image and the target parking space number sent by the bullet camera. There is no limitation here.
[0069] Step 304: Send the information of the departing vehicle to the roadside parking billing platform so that the roadside parking billing platform can terminate the billing of the target vehicle based on the departing vehicle information.
[0070] In other words, after receiving information about a departing vehicle, the roadside parking billing platform automatically calculates the parking duration of the target vehicle based on the time difference between the vehicle's entry time and departure time, and then calculates the fee accordingly.
[0071] It is understandable that both the entry time and departure time of the target vehicle are timestamps.
[0072] In an exemplary embodiment, the method further includes: sending a first shooting command to a second dome camera on a target pole based on the target parking space number, and receiving a second vehicle image of the target vehicle in the target parking space sent by the second dome camera; wherein the target pole and the pole where the bullet camera is located are opposite poles.
[0073] In one possible implementation, after receiving the first shooting instruction, the second spherical camera rotates based on the first shooting instruction to capture a high-definition image of the front or rear of the target vehicle, i.e., a second vehicle image, and sends the second vehicle image to a computer device, so that the computer device can receive the second vehicle image sent by the second spherical camera.
[0074] Correspondingly, the first roadside parking space scene image and the first vehicle image are identified to obtain the vehicle information of the target vehicle entering the parking space. This includes: identifying the first roadside parking space scene image, the first vehicle image, and the second vehicle image to obtain the vehicle information of the target vehicle entering the parking space.
[0075] In one possible implementation, the first roadside parking space scene image, the first vehicle image, and the second vehicle image are input into the vehicle recognition model to obtain the license plate number of the target vehicle; based on the license plate number, the entry time of the target vehicle, and the target vehicle image, the entry vehicle information of the target vehicle is obtained; wherein, the target vehicle image is the first vehicle image and / or the second vehicle image.
[0076] In this embodiment, the computer device also sends a first shooting command to a second dome camera on a pole opposite to the pole where the bullet camera is located, and obtains a second vehicle image sent by the second dome camera on the opposite pole. The computer then identifies the first roadside parking space scene image, the first vehicle image, and the second vehicle image to obtain the vehicle information of the target vehicle entering the parking space, which can improve the accuracy of the vehicle information of the target vehicle entering the parking space.
[0077] It is understood that the computer equipment can send a first shooting command to multiple PTZ cameras. These multiple PTZ cameras can be at least two of the following: a first PTZ camera on the same pole as the bullet camera; a second PTZ camera on a pole opposite the bullet camera; a third PTZ camera on an adjacent pole; and a fourth PTZ camera on an adjacent pole. There is no limitation on which specific PTZ cameras the computer equipment sends the first shooting command to; it can be configured according to on-site requirements.
[0078] In an exemplary embodiment, the method further includes: receiving an event type sent by a bullet camera; if the event type is an entry event, performing a step of sending a first shooting command to a first dome camera based on a target parking space number; if the event type is a departure event, performing a step of sending a second shooting command to the first dome camera based on a target parking space number.
[0079] In this embodiment, the computer device determines the next step to be executed by receiving the event type sent by the bullet camera, avoiding complex judgments by the computer device, thus reducing the resource consumption of the computer device.
[0080] In an exemplary embodiment, after sending the information of the entering vehicle to the roadside parking billing platform, the method further includes: sending a third shooting instruction to the first spherical camera, the third shooting instruction being used to instruct the spherical camera to take a round of shots of all the parking spaces that can be shot at a preset time interval.
[0081] The preset duration can be, for example, 10 minutes.
[0082] It is understandable that after the computer device sends the third shooting command to the first spherical camera, it will receive multiple images of the target vehicle parked, along with the shooting time for each image. The computer device then sends these images, along with the shooting time and the vehicle's license plate number, to the roadside parking billing platform. The roadside parking billing platform will then save the received images and the shooting time.
[0083] This embodiment enables timed snapshots of all parking spaces during vehicle parking, forming a continuous chain of evidence for the parking process. The chain of evidence refers to a complete record consisting of a series of chronologically arranged and interconnected images, used to reconstruct the entire event.
[0084] like Figure 4 As shown, a schematic diagram of the principle of roadside parking billing is provided. The process has been described in detail above and will not be repeated here.
[0085] In summary, the roadside parking billing method proposed in this application has the following advantages:
[0086] 1. The roadside parking billing method of this application can achieve fully automatic unattended operation. The system realizes full automation from vehicle detection and license plate recognition to billing generation through the linkage of gun and ball and vehicle recognition model, completely replacing manual labor and greatly reducing operating costs.
[0087] 2. The hardware required for the roadside parking billing method of this application is deployed in a non-destructive manner. The gun and ball are deployed on the roadside poles without damaging the road surface, making construction convenient and maintenance simple.
[0088] 3. The roadside parking billing method of this application is accurate and reliable. By combining precise timestamps and multimodal large model recognition, it ensures the accuracy of entry / exit times and makes the billing process transparent and trustworthy.
[0089] 4. The roadside parking billing method proposed in this application can form a complete chain of evidence: through event-triggered snapshots and timed inspection snapshots, the system retains image evidence of the entire parking process, effectively addressing billing disputes.
[0090] 5. The roadside parking billing method of this application involves a high degree of system integration, utilizes edge computing units to complete most of the calculations locally, reduces the pressure on the cloud, responds quickly, and has strong system stability.
[0091] 6. The roadside parking billing method of this application can work offline. The multimodal large model is deployed on the edge computing unit side and can still work normally even if it is not connected to the cloud network.
[0092] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.
[0093] Based on the same inventive concept, this application also provides a roadside parking billing device for implementing the roadside parking billing method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more roadside parking billing device embodiments provided below can be found in the limitations of the roadside parking billing method described above, and will not be repeated here.
[0094] In one exemplary embodiment, such as Figure 5 As shown, a roadside parking metering device 500 is provided, comprising: a first transceiver module 501, an identification module 502, and a second transceiver module 503, wherein:
[0095] The first transceiver module 501 is used to receive the first roadside parking space scene image and the target parking space number sent by the bullet camera. The first roadside parking space scene image is an image taken by the bullet camera when it detects a vehicle entering the roadside parking space.
[0096] The first transceiver module 501 is also used to send a first shooting command to the first spherical camera based on the target parking space number, and to receive the first vehicle image of the target vehicle in the target parking space sent by the first spherical camera; the first spherical camera and the bullet camera are on the same pole;
[0097] The recognition module 502 is used to recognize the first roadside parking space scene image and the first vehicle image to obtain the vehicle information of the target vehicle entering the parking space.
[0098] The second transceiver module 503 is used to send the information of the entering vehicle to the roadside parking billing platform so that the roadside parking billing platform can start billing the target vehicle based on the information of the entering vehicle.
[0099] In one embodiment, the first transceiver module 501 is further configured to receive a second roadside parking space scene image and a target parking space number sent by a bullet camera. The second roadside parking space scene image is an image captured by the bullet camera when it detects a vehicle leaving the roadside parking space. The first transceiver module is further configured to send a second shooting command to a first dome camera based on the target parking space number, and receive an empty space image of the target parking space sent by the first dome camera. The second transceiver module 503 is further configured to obtain the vehicle information of the target vehicle leaving based on the empty space image; and send the vehicle information to the roadside parking billing platform so that the roadside parking billing platform can terminate the billing of the target vehicle based on the vehicle information.
[0100] In one embodiment, the first transceiver module 501 is further configured to send a first shooting command to the second spherical camera on the target pole based on the target parking space number, and receive the second vehicle image of the target vehicle in the target parking space sent by the second spherical camera; wherein the target pole and the pole where the bullet camera is located are opposite poles; correspondingly, the recognition module 502 is specifically configured to recognize the first roadside parking space scene image, the first vehicle image and the second vehicle image to obtain the vehicle information of the target vehicle entering the parking space.
[0101] In one embodiment, the recognition module 502 is specifically used to input the first roadside parking space scene image, the first vehicle image, and the second vehicle image into the vehicle recognition model to obtain the license plate number of the target vehicle; and to obtain the vehicle information of the target vehicle based on the license plate number, the entry time of the target vehicle, and the target vehicle image, wherein the target vehicle image is the first vehicle image and / or the second vehicle image.
[0102] In one embodiment, the first transceiver module 501 is further configured to receive the event type sent by the bullet camera; in the case of an entry event, execute the step of sending a first shooting command to the first spherical camera based on the target parking space number; in the case of an exit event, execute the step of sending a second shooting command to the first spherical camera based on the target parking space number.
[0103] In one embodiment, the first transceiver module 501 is further configured to send a third shooting instruction to the first spherical camera, the third shooting instruction instructing the spherical camera to take a round of shots of all parking spaces that can be captured at preset intervals. Each module in the aforementioned roadside parking fee metering device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.
[0104] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores information such as vehicle entry and exit data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a roadside parking fee calculation method.
[0105] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0106] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any one of the above method embodiments.
[0107] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the above method embodiments.
[0108] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in any one of the above method embodiments.
[0109] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.
[0110] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0111] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for calculating roadside parking fees, characterized in that, The method includes: Receive a first roadside parking space scene image and a target parking space number sent by a bullet camera. The first roadside parking space scene image is an image taken by the bullet camera when it detects a vehicle entering a roadside parking space. Based on the target parking space number, a first shooting command is sent to the first spherical camera, and a first vehicle image of the target vehicle in the target parking space is received from the first spherical camera; the first spherical camera and the bullet camera are on the same pole; The first roadside parking space scene image and the first vehicle image are identified to obtain the vehicle information of the target vehicle entering the parking space. The information of the entering vehicle is sent to the roadside parking billing platform so that the roadside parking billing platform can start billing the target vehicle based on the information of the entering vehicle.
2. The method according to claim 1, characterized in that, The method further includes: The system receives a second roadside parking space scene image and the target parking space number sent by the bullet camera. The second roadside parking space scene image is an image taken by the bullet camera when it detects a vehicle leaving the roadside parking space. Based on the target parking space number, a second shooting command is sent to the first spherical camera, and an image of the empty space of the target parking space is received from the first spherical camera. Based on the empty space image, the departing vehicle information of the target vehicle is obtained; The information of the departing vehicle is sent to the roadside parking billing platform so that the roadside parking billing platform can terminate the billing of the target vehicle based on the information of the departing vehicle.
3. The method according to claim 1, characterized in that, The method further includes: Based on the target parking space number, the first shooting command is sent to the second spherical camera on the target pole, and the second vehicle image of the target vehicle in the target parking space is received from the second spherical camera; wherein, the target pole and the pole where the bullet camera is located are opposite poles; Correspondingly, the step of recognizing the first roadside parking space scene image and the first vehicle image to obtain the vehicle information of the target vehicle includes: The first roadside parking space scene image, the first vehicle image, and the second vehicle image are identified to obtain the vehicle information of the target vehicle entering the parking space.
4. The method according to claim 3, characterized in that, The step of identifying the first roadside parking space scene image, the first vehicle image, and the second vehicle image to obtain the vehicle information of the target vehicle entering the parking space includes: The first roadside parking space scene image, the first vehicle image, and the second vehicle image are input into the vehicle recognition model to obtain the license plate number of the target vehicle. Based on the license plate number, the entry time of the target vehicle, and the image of the target vehicle, the entry information of the target vehicle is obtained, wherein the image of the target vehicle is the first vehicle image and / or the second vehicle image.
5. The method according to claim 2, characterized in that, The method further includes: Receive the event type sent by the bullet camera; In the case where the event type is an entry event, the step of sending a first shooting command to the first spherical camera based on the target parking space number is executed. In the case of an event type of departure, the step of sending a second shooting command to the first spherical camera based on the target parking space number is executed.
6. The method according to claim 1, characterized in that, After sending the information of the entering vehicle to the roadside parking billing platform, the method further includes: A third shooting command is sent to the first spherical camera, which instructs the spherical camera to take a round of shots of all the parking spaces that can be captured at preset intervals.
7. A roadside parking metering device, characterized in that, The device includes: The first transceiver module is used to receive a first roadside parking space scene image and a target parking space number sent by a bullet camera. The first roadside parking space scene image is an image taken by the bullet camera when it detects a vehicle entering a roadside parking space. The first transceiver module is further configured to send a first shooting command to the first spherical camera based on the target parking space number, and receive a first vehicle image of the target vehicle in the target parking space sent by the first spherical camera; the first spherical camera and the bullet camera are on the same pole; The recognition module is used to recognize the first roadside parking space scene image and the first vehicle image to obtain the vehicle information of the target vehicle entering the parking space. The second transceiver module is used to send the information of the entering vehicle to the roadside parking billing platform, so that the roadside parking billing platform can start billing the target vehicle based on the information of the entering vehicle.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.