Bus charging station monitoring system
By using cameras and deep learning models to monitor lane and charging pile status in bus charging stations, the problem of irregular charging station management was solved, and real-time status monitoring and unified management were achieved.
Patent Information
- Application Number
- CN202211638803.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-12-20
- Publication Date
- 2025-10-03
- Estimated Expiration
- 2042-12-20
AI Technical Summary
There is currently a lack of a real-time monitoring system for bus charging stations, resulting in irregular and inconsistent management of charging stations.
Using multiple cameras and edge computing devices, combined with deep learning target detection models, the status of lanes and charging piles in the charging field can be monitored in real time, and unified management can be achieved through background equipment.
It realizes real-time status monitoring of bus charging stations, supports standardized and unified management, and improves management efficiency.
Smart Images
Figure CN115955546B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of charging field monitoring, and in particular relates to a bus charging field monitoring system. Background Art
[0002] In recent years, urban public transportation, as a public welfare project and a public welfare project, has become deeply intertwined with residents' daily lives. With the continuous promotion and implementation of new energy buses, the construction and operation of new energy bus stations and charging piles have also rapidly followed suit. Consequently, the need for standardized and unified management of bus charging stations has also arisen. Therefore, it is necessary to monitor the status of lanes and charging piles in bus charging stations in real time. However, currently, there is no monitoring system for bus charging stations. Summary of the Invention
[0003] Based on this, in order to solve the above technical problems, a bus charging field monitoring system is provided.
[0004] The technical solution adopted in the present invention is as follows:
[0005] The present invention provides a bus charging station monitoring system, comprising:
[0006] a plurality of first cameras for capturing a first image of each lane in the charging field in real time;
[0007] a plurality of second cameras for capturing a second image of each charging pile in the charging field in real time;
[0008] a processing device, configured to identify the status of each lane based on the first screen, identify the status of each charging pile based on the second screen, and send the status of each lane and the status of each charging pile to a background device;
[0009] The backend device is used to receive the status of each lane and the status of each charging pile, and display the status of each lane and the status of each charging pile through a monitoring interface.
[0010] The present invention can monitor the bus charging field in real time, thereby obtaining the status of each lane and charging pile in the charging field in real time, which is conducive to the standardized and unified management of the bus charging field. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments:
[0012] Figure 1 It is a structural schematic diagram of the present invention;
[0013] Figure 2 A schematic diagram of a bus charging station according to the present invention;
[0014] Figure 3This is a schematic diagram of the vehicle rear target and the charging gun head target in the first frame of the present invention;
[0015] Figure 4 This is a schematic diagram of the charging gun head target and the gun head cable target in the second frame of the present invention. DETAILED DESCRIPTION
[0016] The following will illustrate the implementation of the present invention in conjunction with the drawings in the specification. It should be noted that the implementation methods involved in this specification are not exhaustive and do not represent the only implementation methods of the present invention. The following corresponding embodiments are only for the purpose of clearly illustrating the invention content of the patent of this invention and are not intended to limit its implementation methods. For ordinary technicians in this field, different forms of changes and modifications can be made based on the description of this embodiment. Any obvious changes or modifications that belong to the technical concept and invention content of the present invention are also within the scope of protection of the present invention.
[0017] like Figure 1 As shown, an embodiment of the present invention provides a bus charging station monitoring system, including multiple first cameras 11, multiple second cameras 12, a processing device 13 and a background device 14.
[0018] like Figure 2 As shown, the bus charging station of this embodiment has six lanes 2, three charging piles 3, five first cameras 11 and three second cameras 12. The six lanes 2 are arranged side by side, and the three charging piles 3 are located at the rear of the six lanes 2. Each charging pile 3 has two charging gun heads, so each charging pile 3 corresponds to two lanes 2. Each first camera 11 can capture the rear of the vehicles on the corresponding two adjacent lanes 2, and each second camera 12 can capture the front of the corresponding charging pile 3.
[0019] The plurality of first cameras 11 are used to capture a first image of each lane in the charging field in real time, and the plurality of second cameras 12 are used to capture a second image of each charging pile in the charging field in real time.
[0020] The processing device 13 is used to identify the status of each lane according to the first screen, identify the status of each charging pile according to the second screen, and send the status of each lane and the status of each charging pile to the background device 14.
[0021] The specific process of identifying the status of each lane based on the first image is as follows:
[0022] 1. Input the first image into the first deep learning target detection model to determine the position and number of the vehicle rear target, the charging gun head target, and the charging gun head target in the first image.
[0023] 2. If the charging gun head target is at the first target position of the vehicle rear target, it means that the charging gun head is inserted into the vehicle's charging port, and there is a vehicle charging in the corresponding lane.
[0024] 3. If there is a rear target but no charging gun head target, or the charging gun head target is not at the first target position of the rear target (indicating that the charging gun head is not inserted into the vehicle's charging port), then there is a vehicle that is not charging in the corresponding lane, indicating that the vehicle is not charging and is occupying the lane.
[0025] 4. If neither the vehicle rear target nor the charging gun head target exists, the corresponding lane is idle.
[0026] At the same time, the number of charging gun head targets located at the first target position in the first frame is determined.
[0027] Figure 3 The vehicle rear target and the charging gun head target in the first picture are shown, and the charging gun head target is located at the first target position.
[0028] The specific process of identifying the status of each charging pile according to the second screen is as follows:
[0029] 1. Input the second image into the second deep learning target detection model to determine the number of charging gun head targets in the second image.
[0030] 2. If the target number of charging gun heads is equal to the total number of gun heads of a single charging pile, the corresponding charging pile is idle.
[0031] 3. If the number of charging gun head targets is less than the total number of gun heads of a single charging pile, calculate the difference between the total number of gun heads and the target number of charging gun heads. If the difference is equal to the number of charging gun head targets located at the first target position in the first picture of the corresponding lane, the corresponding charging pile is charging; if the difference is greater than the number of charging gun head targets in the first picture of the corresponding lane, the corresponding charging pile has a missing gun head.
[0032] For example, if the number of charging gun head targets is 1 and the total number of gun heads is 2, the difference between the two is 1. If the number of charging gun head targets located at the first target position in the first picture of the two lanes corresponding to the current charging pile is 1, it means that the charging pile is charging. If the number of charging gun head targets located at the first target position is 0, it means that a gun head is missing at the current charging pile.
[0033] Furthermore, it is also possible to determine whether the charging gun head target in the second picture is located at the second target position. If not, it means that the charging gun head is not on the charging pile. For example, if it is on the ground, the corresponding charging pile has a charging gun head that is not correctly returned to its position.
[0034] Furthermore, a second deep learning target detection model can be used to determine whether the gun head cable target in the second picture is located at the third target position. If not, it means that the gun head cable is not properly organized. For example, if the gun head cable is on the ground, the gun head cable of the corresponding charging pile is not properly returned to its original position.
[0035] Figure 4 The second screen shows the charging gun head target and the gun head cable target, wherein the gun head cable target on the right is not correctly positioned.
[0036] Among them, the first deep learning target detection model and the second deep learning target detection model both adopt the YOLOv5 model.
[0037] In this embodiment, the processing device 13 includes multiple edge computing devices, and the multiple edge computing devices are connected to each camera one-to-one. The edge computing device can be independent of the camera or a computing chip inside the camera. Of course, if the computing power is sufficient, the number of edge computing devices can be less than the number of cameras, or even only one edge computing device can be set.
[0038] The background device 14 is used to receive the status of each lane and the status of each charging pile, and display the status of each lane and the status of each charging pile through a monitoring interface.
[0039] In this embodiment, a charging field digital twin system is provided on the background device 14, and the status of each lane and the status of each charging pile can be displayed through the monitoring interface of the charging field digital twin system. In this way, the management personnel can manage according to the status displayed in the monitoring interface. For example, if the vehicle is not charged and occupies the lane, the vehicle can be arranged to leave in time. If a gun head is lost, personnel can be arranged to check it in time. If the gun head cable is not returned to its original position, personnel can be arranged to sort it out in time.
[0040] As can be seen from the above, the system of the embodiment of the present invention can monitor the bus charging station in real time, thereby obtaining the status of each lane and charging pile in the charging station in real time, which is conducive to the standardized and unified management of the bus charging station.
[0041] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include these modifications and variations.
Claims
1. A bus charging field monitoring system, characterized in that: include: a plurality of first cameras for capturing a first image of a rear end of a vehicle on a corresponding lane in the charging field in real time; a plurality of second cameras for capturing a second image corresponding to the front of the charging pile in the charging field in real time; a processing device, configured to identify the status of each lane based on the first screen, identify the status of each charging pile based on the second screen, and send the status of each lane and the status of each charging pile to a background device; The backend device is used to receive the status of each lane and the status of each charging pile, and display the status of each lane and the status of each charging pile through a monitoring interface; The identifying the status of each lane according to the first image further includes: Input the first image into a first deep learning target detection model to determine the positions and number of the vehicle rear target, the charging gun head target, and the charging gun head target in the first image. If the charging gun head target is located at the first target position of the vehicle rear target, then there is a vehicle charging in the corresponding lane. If there is a vehicle rear target but no charging gun head target, or the charging gun head target is not at the first target position of the vehicle rear target, then there is a vehicle not charging in the corresponding lane. If neither the vehicle rear target nor the charging gun head target exists, then the corresponding lane is idle. Determining the number of charging gun head targets located at the first target position in the first image; The identifying the status of each charging pile according to the second screen further includes: Input the second image into a second deep learning target detection model to determine the number of charging gun head targets in the second image. If the number of charging gun head targets is equal to the total number of gun heads of a single charging pile, the corresponding charging pile is idle. If the number of charging gun head targets is less than the total number of gun heads of a single charging pile, calculate the difference between the total number of gun heads and the number of charging gun head targets. If the difference is equal to the number of charging gun head targets located at the first target position in the first image of the corresponding lane, the corresponding charging pile is charging. If the difference is greater than the number of charging gun head targets located at the first target position in the first image of the corresponding lane, then the corresponding charging pile has a gun head missing; The second deep learning target detection model is used to determine whether the gun head cable target in the second picture is located at the third target position. If not, the gun head cable of the corresponding charging pile is not correctly returned to its original position.
2. A bus charging field monitoring system according to claim 1, characterized in that: The identifying the status of each charging pile according to the second screen further includes: Determine whether the charging gun head target in the second picture is located at the second target position. If not, the charging gun head of the corresponding charging pile is not correctly returned to the position.
3. A bus charging field monitoring system according to claim 1, characterized in that: The first deep learning target detection model and the second deep learning target detection model both adopt the YOLOv5 model.
4. A bus charging station monitoring system according to any one of claims 1 to 3, characterized in that: The displaying of the status of each lane and the status of each charging pile through the monitoring interface further includes: The status of each lane and the status of each charging pile are displayed through the monitoring interface of the charging field digital twin system.
5. A bus charging station monitoring system according to claim 1, characterized in that: The processing device includes multiple edge computing devices, and the multiple edge computing devices are connected to each camera in a one-to-one correspondence.
Citation Information
Patent Citations
Target monitoring method and device, computer equipment and storage medium
CN110298239A
Charging station operation state monitoring method, electronic equipment and storage medium
CN114449220A