CN214507243U - Vehicle monitoring device and system - Google Patents
Vehicle monitoring device and system Download PDFInfo
- Publication number
- CN214507243U CN214507243U CN202022080168.1U CN202022080168U CN214507243U CN 214507243 U CN214507243 U CN 214507243U CN 202022080168 U CN202022080168 U CN 202022080168U CN 214507243 U CN214507243 U CN 214507243U
- Authority
- CN
- China
- Prior art keywords
- vehicle
- semantic information
- video stream
- number plate
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The utility model provides a vehicle monitoring device (11) which is positioned on a vehicle management site and is connected with a camera (10); the method comprises the following steps: an image acquisition interface (111), an image processor (112) connected with the image acquisition interface (111), and an information transmitter (113) connected with the image processor (112); the image acquisition interface (111) acquires a video stream from the camera (10) and sends the video stream to the image processor (112); the image processor (112) extracts semantic information of the behavior of the vehicle and semantic information of the number plate from the video stream and transmits the extracted semantic information to the server (12) at the rear end via the information transmitter (113) for vehicle management. The vehicle monitoring device processes the original video stream collected by the camera, and only sends semantic information for vehicle management to a server at the rear end, so that the requirement of network transmission bandwidth is greatly reduced, and the vehicle monitoring device has the advantage of real-time processing.
Description
Technical Field
The utility model relates to a traffic technical field, in particular to vehicle monitoring devices and system.
Background
In the smart city architecture, the vehicle monitoring system has high requirements on network bandwidth and network data transmission speed. The video stream shot by the camera needs to be sent to a server at the back end for further processing so as to realize applications such as vehicle management. Thus, network resources become a bottleneck in the deployment of conventional vehicle monitoring systems. Meanwhile, roadside facility reconstruction also has great influence on urban daily traffic and life.
SUMMERY OF THE UTILITY MODEL
The embodiment of the utility model provides a vehicle monitoring device and system, it utilizes and is located the vehicle management scene, for example the vehicle monitoring device in roadside or parking area etc. handles the original video stream that the camera was gathered, only sends the semantic information of the action of the semantic information of the number plate of the vehicle that is used for vehicle management and vehicle to the server of rear end, has greatly reduced the requirement to network transmission bandwidth, and has real-time processing's advantage.
In a first aspect, a vehicle monitoring device is provided, which is located at a vehicle management site and is connected with at least one camera; the vehicle monitoring device includes: the system comprises an image acquisition interface, an image processor connected with the image acquisition interface, and an information transmitter connected with the image processor; the image acquisition interface acquires a video stream shot on the vehicle management site from the at least one camera and sends the video stream to an image processor; the image processor receives the video stream from the image acquisition interface, extracts first semantic information of a license plate of a vehicle and second semantic information of behaviors of the vehicle from the video stream, and sends the first semantic information and the second semantic information to an information sender; and the information transmitter receives the first semantic information and the second semantic information and transmits the first semantic information and the second semantic information to a server at the rear end, so that the server can perform vehicle management.
In a second aspect, a vehicle surveillance system is provided, comprising the vehicle surveillance device of the first aspect and the at least one camera and the server.
The real-time application of vehicle management can be realized by processing the video stream in real time through the vehicle monitoring device deployed on the vehicle management field. The vehicle monitoring device transmits only the semantic information of the behavior of the vehicle and the semantic information of the number plate of the vehicle to the server, and can effectively reduce the network traffic load.
Optionally, the image processor comprises: the vehicle identification device comprises a vehicle identification device, a vehicle tracker connected with the vehicle identification device and a vehicle number plate identification device connected with the vehicle identification device; the vehicle identifier identifies the vehicle from the video stream; the vehicle tracker determines the information of the moving track of the vehicle according to the result identified by the vehicle identifier, and determines the second semantic information according to the information of the moving track of the vehicle; the vehicle license plate recognizer intercepts the area where the license plate of the vehicle is located from the image of the vehicle recognized from the video stream, recognizes the license plate of the vehicle from the area where the license plate of the vehicle is located, and generates the first semantic information.
The method comprises the steps of not only carrying out static vehicle identification, but also carrying out dynamic vehicle tracking, determining the behavior of the vehicle according to the moving track of the vehicle, and further generating second semantic information representing the vehicle behavior so as to carry out vehicle management. The method has the advantages of accurate judgment of vehicle behaviors and accurate vehicle management result.
Wherein the vehicle identifier identifies the vehicle from the video stream in an anchor-free manner.
Optionally, the image processor further comprises: a hardware decoder connected to the image acquisition interface and the vehicle identifier, respectively; the hardware decoder receives the video stream from the image acquisition interface, collects at least one frame of picture from the video stream, and marks a frame number for each collected frame of picture; the vehicle tracker stores the frame number of the picture, in which the vehicle is identified, in the at least one frame of picture; and the vehicle license plate identifier intercepts the area where the license plate of the vehicle is located from the picture according to the frame number of the picture for identifying the vehicle, which is stored by the vehicle tracker. Therefore, the number plate area can be determined quickly and accurately, and the speed of number plate identification is increased. Optionally, the pictures taken from the video stream are of higher resolution, such as: 1920 x 1080, the number plate area thus cut has a high resolution, facilitating accurate number plate determination.
Optionally, the image processor further comprises a trigger connected to the vehicle tracker and the vehicle license plate identifier, respectively; the trigger judges whether the behavior of the vehicle accords with a preset behavior mode; and when the behavior of the vehicle accords with a preset behavior mode, the vehicle number plate recognizer intercepts the area where the number plate of the vehicle is located from the picture of the vehicle recognized from the video stream, and recognizes the number plate of the vehicle from the area where the number plate of the vehicle is located. When the behavior of the vehicle conforms to the preset behavior pattern, subsequent identification of the vehicle number plate is performed, and unnecessary processing is avoided.
Optionally, the information transmitter transmits the first semantic information and the second semantic information to the server by wireless communication. The transformation of public facilities such as roads and the like in a limited communication mode can be avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a vehicle monitoring device and system according to an embodiment of the present invention.
Fig. 2 shows an application of the vehicle monitoring system provided by the embodiment of the invention in the field of parking charging.
Fig. 3 shows an internal structure of a vehicle monitoring apparatus and system provided by an embodiment of the present invention.
Description of the reference numerals
100: vehicle monitoring system 10: the camera 11: vehicle monitoring device
12: the server 13: the driver application 14: vehicle manager application
15: vehicle management system interface 12': wireless router
111: the image acquisition interface 112: the image processor 113: information transmitter
112 a: vehicle identifier 112 b: vehicle tracker 112 c: vehicle number plate recognizer
112 d: hardware decoder 112 e: flip-flop
20: video stream 21: picture marked with frame number
22: frame number marked border (bounding box) 23: track information of vehicle movement marked with frame number
24: second semantic information (semantic information of behavior of vehicle)
25: first semantic information (semantic information of number plate of vehicle)
Detailed Description
In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the following will combine the drawings in the embodiments of the present invention to clearly and completely describe the technical solution in the embodiments of the present invention, and obviously, the described embodiments are some embodiments of the present invention, rather than all embodiments, based on the embodiments in the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative work belong to the scope of the present invention.
Fig. 1 is a schematic structural diagram of a vehicle monitoring system according to an embodiment of the present invention. As shown in fig. 1, the system 100 may include: at least one camera 10 and a vehicle monitoring device 11 connected to the at least one camera 10, and a server 12 at a rear end connected to the vehicle monitoring device.
Wherein each of the at least one camera 10 photographs a monitored vehicle management site, and transmits a photographed video stream 20 to a vehicle monitoring apparatus 11 located at the vehicle management site; the vehicle monitoring device 11 receives and processes the video stream 20 from the at least one camera 10, obtains semantic information 25 (denoted as "first semantic information") of the number plate of the vehicle and semantic information 24 (denoted as "second semantic information") of the behavior of the vehicle, and transmits the semantic information to the server 12 at the back end, and the server 12 at the back end performs vehicle management according to the received semantic information.
Fig. 2 illustrates an application of the vehicle monitoring system 100 provided by the embodiment of the present invention in a parking management system. The driver leaves after parking the vehicle at the roadside, the camera 10 at the roadside collects the video stream of the vehicle and sends the video stream to the vehicle monitoring device 11, the vehicle monitoring device 11 processes the video stream to obtain semantic information related to parking behaviors, semantic information of a number plate and the like) and sends the semantic information to the server 12 at the rear end (the server 12 is located at the cloud end in the example shown in fig. 2), the server 12 can run micro-services, charging processing is carried out according to the received semantic information, and the driver runs the client application program 13 on the mobile phone to pay. Optionally, the mobile phone of the roadside parking manager may also run the parking manager application 14 for parking space management, fee review, and the like. The server 12 may provide an interface to a parking management program for the system administrator or other authorized personnel to perform maintenance operations on the entire parking management system. Compared with the existing parking charging system, the system shown in fig. 2 has the advantages of labor saving and real-time charging.
Since the server 12 from the vehicle management site to the back end sends semantic information rather than video streams or pictures, the requirements on network bandwidth and traffic are greatly reduced. Fig. 3 shows a vehicle monitoring system provided by another embodiment of the present invention, wherein the vehicle monitoring device 11 and the server 12 at the back end can be connected via a wireless network, such as a fourth generation mobile communication network 4G, such as the 4G router 12 shown here.
The vehicle monitoring apparatus 11 may include an image acquisition interface 111, an image processor 112, and an information transmitter 113, wherein the image acquisition interface 111 receives the video stream 20 from the at least one camera 10 and transmits to the image processor 112; the image processor 112 receives the video stream 20 from the image acquisition interface 111, extracts semantic information of the behavior of one vehicle and semantic information of the number plate of the vehicle in the vehicle management scene from the video stream 20, and sends the two items of semantic information to the information transmitter 113; the information transmitter 113 receives the two items of semantic information and transmits them to the server 12 at the back end, so that the server 12 performs vehicle management based on the two items of semantic information.
As shown in fig. 3, the image processor 112 may include: a hardware decoder 112d connected to the image acquisition interface 111, a vehicle identifier 112a connected to the hardware decoder 112d, a vehicle tracker 112b connected to the vehicle identifier 112a, a trigger 112e connected to the vehicle tracker, and a vehicle number plate identifier 112c connected to the trigger 112e and the vehicle identifier 112 a.
Wherein the hardware decoder 112d receives the video stream 20 from the image capture interface 111, captures at least one frame of picture 21 from the video stream 20 (optionally, the frame may be stored in a file system in a memory), and marks a frame number for each captured frame of picture 21 (where the obtained picture of each frame has a higher resolution, such as 1920 × 1080). The video stream 20 may be a video stream conforming to a Real Time Streaming Protocol (RTSP), and each camera 10 outputs one video stream 20.
Optionally, each frame of the picture 21 is processed by the vehicle identifier 112a, such as by using a deep learning inference model for object recognition.
The vehicle identifier 112a identifies the designated vehicle from each frame of the picture 21, wherein the vehicle identifier 112a can identify the vehicle from the picture in an anchor-free manner. In the identification process, information 22 (which may include position information of the frame and the frame number of the frame) including the frame (bounding box) of each vehicle is generated.
The vehicle tracker 112b determines information of a trajectory along which the vehicle moves (which may include an identification of the vehicle from other vehicles in the vehicle monitoring apparatus 11, a frame number of a picture in which the vehicle is recognized, and position information of a frame surrounding the vehicle in each frame, etc.) from the result of recognition by the vehicle recognizer 112a, and determines semantic information 24 of behavior of the vehicle from the information of the trajectory along which the vehicle moves (moving state or stationary state, and position information).
The trigger 112d determines whether the behavior of the vehicle conforms to a preset behavior pattern (such as parking) according to the semantic information 24 of the behavior of the vehicle. Optionally, the frame number of the picture in which the vehicle is recognized, the identification of the vehicle in the vehicle monitoring device 11 from other vehicles, and the type of behavior that conforms to the preset behavior pattern are stored.
The vehicle number plate identifier 112c cuts out the area where the number plate of the vehicle is located from the picture in which the vehicle is identified in the at least one frame of picture 21 when the behavior of the vehicle conforms to the preset behavior pattern, and identifies the semantic information 25 of the number plate of the vehicle from the area where the number plate of the vehicle is located.
The vehicle tracker 112b and the vehicle number plate recognizer 112c transmit semantic information 24 of the behavior of the vehicle and semantic information 25 of the number plate of the vehicle to the information transmitter 113, respectively, and transmit to the server 12 at the rear end via the information transmitter 113. Wherein the information transmitter 113 transmits the semantic information 25 of the number plate of the vehicle and the semantic information 24 of the behavior to the server 12 by way of wireless communication (such as by the 4G router 12' shown in fig. 3).
To sum up, the embodiment of the utility model provides a vehicle monitoring system carries out real-time processing to the video stream through the vehicle monitoring device who deploys at the vehicle management scene, can realize the real-time application of vehicle management. The vehicle monitoring device transmits only the semantic information of the behavior of the vehicle and the semantic information of the number plate of the vehicle to the server, and can effectively reduce the network traffic load.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other similar elements in a process, method, article, or apparatus that comprises the element.
Finally, it is to be noted that: the above description is only the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, and is not used to limit the protection scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention is included in the protection scope of the present invention.
Claims (5)
1. A vehicle surveillance device (11), characterized in that the vehicle surveillance device (11) is located at a vehicle management site, connected to at least one camera (10);
the vehicle monitoring device (11) includes: an image acquisition interface (111), an image processor (112) connected to the image acquisition interface (111), and an information transmitter (113) connected to the image processor (112);
the image acquisition interface (111) acquires a video stream shot at the vehicle management site from the at least one camera (10) and sends the video stream to an image processor (112);
the image processor (112) receives the video stream from the image acquisition interface (111), extracts first semantic information of a number plate of a vehicle and second semantic information of a behavior of the vehicle in the vehicle management scene from the video stream, and transmits the first semantic information and the second semantic information to an information transmitter (113);
the information transmitter (113) receives the first semantic information and the second semantic information of the number plate and transmits the first semantic information and the second semantic information to a server (12) at the rear end, so that the server (12) can manage vehicles;
the image processor (112) comprises: a vehicle identifier (112a), a vehicle tracker (112b) connected to the vehicle identifier (112a), and a vehicle license plate identifier (112c) connected to the vehicle identifier (112 a);
the vehicle identifier (112a) identifies the vehicle from the video stream;
the vehicle tracker (112b) determines information of a trajectory of movement of the vehicle according to a result of recognition by the vehicle recognizer (112a), and determines the second semantic information according to the information of the trajectory of movement of the vehicle;
the vehicle number plate recognizer (112c) intercepts the area where the number plate of the vehicle is located from the picture of the vehicle recognized from the video stream, recognizes the number plate of the vehicle from the area where the number plate of the vehicle is located, and generates the first semantic information;
the image processor (112) further comprises a trigger (112e) connected to the vehicle tracker (112b) and the vehicle license plate identifier (112c), respectively;
the trigger (112e) determines whether the behavior of the vehicle conforms to a preset behavior pattern;
and when the behavior of the vehicle conforms to a preset behavior mode, the vehicle number plate identifier (112c) intercepts the area where the number plate of the vehicle is located from the picture of the vehicle identified from the video stream, and identifies the number plate of the vehicle from the area where the number plate of the vehicle is located.
2. The apparatus of claim 1 wherein said vehicle identifier (112a) identifies said vehicle from said video stream in an anchor-free manner.
3. The apparatus of claim 1,
the image processor (112) further comprises: a hardware decoder (112d), the hardware decoder (112d) being connected to the image acquisition interface (111) and the vehicle identifier (112a), respectively; the hardware decoder (112d) receives the video stream from the image acquisition interface (111), collects at least one frame of picture from the video stream, and marks a frame number for each collected frame of picture;
the vehicle tracker (112b) stores a frame number of a picture of the at least one picture, in which the vehicle is identified;
and the vehicle number plate identifier (112c) intercepts the area where the number plate of the vehicle is located from the picture according to the frame number of the picture for identifying the vehicle, which is stored by the vehicle tracker (112 b).
4. The apparatus of claim 1, wherein the information transmitter (113) transmits the first semantic information and the second semantic information to the server by way of wireless communication.
5. A vehicle surveillance system (100) comprising a vehicle surveillance device (11) according to any of claims 1-4 and said at least one camera (10) and said server (12).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202022080168.1U CN214507243U (en) | 2020-09-21 | 2020-09-21 | Vehicle monitoring device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202022080168.1U CN214507243U (en) | 2020-09-21 | 2020-09-21 | Vehicle monitoring device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN214507243U true CN214507243U (en) | 2021-10-26 |
Family
ID=78196532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202022080168.1U Active CN214507243U (en) | 2020-09-21 | 2020-09-21 | Vehicle monitoring device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN214507243U (en) |
-
2020
- 2020-09-21 CN CN202022080168.1U patent/CN214507243U/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bura et al. | An edge based smart parking solution using camera networks and deep learning | |
| CN111405241B (en) | Edge calculation method and system for video monitoring | |
| CN107705574A (en) | A kind of precisely full-automatic capturing system of quick road violation parking | |
| CN106791613B (en) | A kind of intelligent monitor system combined based on 3DGIS and video | |
| KR100785757B1 (en) | System and method for automatically monitoring illegally-stopping/parking vehicle using fixed camera | |
| CN104200671A (en) | Method and system for managing virtual gate based on big data platform | |
| US9760783B2 (en) | Vehicle occupancy detection using passenger to driver feature distance | |
| CN109905423B (en) | Intelligent management system | |
| WO2019144746A1 (en) | Service management method and related devices | |
| CN113378616A (en) | Video analysis method, video analysis management method and related equipment | |
| KR100413382B1 (en) | System and Method for Integrated Remote Control of Watching Camera using Communication Network and Method for Processing Image Data Using the Same | |
| CN111929672A (en) | Method and device for determining movement track, storage medium and electronic device | |
| US20210084229A1 (en) | System, method and apparatus for networking independent synchronized generation of a series of images | |
| CN214507243U (en) | Vehicle monitoring device and system | |
| CN112653871A (en) | Method and device for collecting and searching distributed video monitoring | |
| CN114078319A (en) | Method and device for detecting potential hazard site of traffic accident | |
| CN112102623A (en) | Traffic violation identification method and device and intelligent wearable device | |
| CN114512005B (en) | Road self-inspection method and device, unmanned aerial vehicle and storage medium | |
| CN115909126A (en) | Target detection method, apparatus and storage medium | |
| CN113850111A (en) | Road condition identification method and system based on semantic segmentation and neural network technology | |
| CN111275006A (en) | Information interaction method, device and system, mobile device and electronic device | |
| Forkan et al. | Mobile IoT-RoadBot: an AI-powered mobile IoT solution for real-time roadside asset management | |
| CN111651634A (en) | Method and device for establishing video event list | |
| CN109697857A (en) | Intelligent traffic control system based on image recognition and neural network algorithm | |
| CN112202786B (en) | Illegal data identification method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |