CN113851013A - Vehicle data processing system and method for multiple parking lots - Google Patents
Vehicle data processing system and method for multiple parking lots Download PDFInfo
- Publication number
- CN113851013A CN113851013A CN202110899930.5A CN202110899930A CN113851013A CN 113851013 A CN113851013 A CN 113851013A CN 202110899930 A CN202110899930 A CN 202110899930A CN 113851013 A CN113851013 A CN 113851013A
- Authority
- CN
- China
- Prior art keywords
- license plate
- vehicle
- video
- real
- equipment
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/148—Management of a network of parking areas
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/60—Network streaming of media packets
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/60—Network streaming of media packets
- H04L65/65—Network streaming protocols, e.g. real-time transport protocol [RTP] or real-time control protocol [RTCP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vehicle data processing system and a method for multiple parking lots, which are characterized in that license plate recognition equipment is accessed to a router or a switch of each parking lot, a camera unit in a local area network is searched and found based on an ONVIF (on-line visual interface) equipment discovery protocol, and a standard RTSP (real time streaming protocol) real-time transmission protocol is adopted to obtain a video code stream or a video picture; analyzing the obtained video code stream or video picture through an artificial neural network and a computer vision technology, and extracting license plate data in the video and a real-time video of corresponding vehicle booking duration; obtaining a vehicle identification result according to the license plate data and the real-time video; finally, the acquired license plate data and the real-time video are recorded and stored in the vehicle identification equipment through a communication unit of the vehicle identification equipment according to a service strategy; encrypting and reporting the identification result to a cloud data center; therefore, the camera of the existing vehicle identification equipment can be used for realizing the universal license plate data acquisition target which is cross-manufacturer and can be copied quickly, and the development cost and the development period are reduced.
Description
Technical Field
The invention relates to the technical field of intelligent parking, in particular to a vehicle data processing system with multiple parking lots and a corresponding method.
Background
Vehicle license plate information acquisition systems based on automated snapshot recognition technology have been commonly used in parking lot management, but all parking lots are self-collected and self-built, and the snapshot cameras and management software manufacturers (brands) used are complicated.
Because the license plate recognition product does not have a national standard or an industrial standard, and also does not have a communication standard, if a competent department needs to supervise, the license plate data of a plurality of parking lots are collected in a networking way, and the following two solutions are mainly adopted at present:
one is to adopt the way of private agreement to dock and develop, ask for the private agreement one by one and dock and develop one by one to every vehicle license plate information acquisition system manufacturer, the debugging cost of this kind of development way is high, cycle length, non-standard, communicate difficult, reproducibility low, difficult to popularize in a large scale, therefore, can't realize the networking collection of the universe parking area license plate data of provincial and city level at present yet;
the other solution is to obtain an effective data packet from a parking lot snapshot camera by capturing a network data packet and filtering the effective data packet, obtain offset values of a selected characteristic data head and a license plate data body by analyzing network data code stream characteristics, and jointly construct a license plate extraction algorithm, thereby realizing real-time extraction of effective license plate data based on the license plate extraction algorithm.
The method has the following disadvantages:
firstly, if a license plate manufacturer encrypts data of a license plate recognition result, the license plate data cannot be effectively extracted and analyzed on the premise that an encryption mode method is not mastered;
the encryption algorithms and encryption keys of a second and a plurality of license plate identification manufacturers are different, and the encryption modes belong to the technical passwords of the license plate manufacturers, so that the encryption modes cannot be easily disclosed, and the difficulty in identifying and extracting license plate data is further increased;
thirdly, even if the encryption mode of a certain license plate manufacturer is mastered by cracking a reverse engineering mode, the license plate manufacturer can easily change the encryption mode method by upgrading software, so that the encryption mode method obtained by cracking an analysis mode is completely invalid, and the cracking of the reverse method is time-consuming and labor-consuming and has the risk of violating laws;
fourthly, in a network layer, the extracted license plate data is distorted or lost due to abnormal conditions such as network data packet loss and network attack, for example, the extracted license plate data is forged due to network packet transmission of artificially forged license plate data.
Disclosure of Invention
In order to achieve the goal of acquiring universal license plate data which is cross-manufacturer (brand) and can be copied quickly and reduce development cost and period, the invention provides a method for processing the vehicle data of a parking lot which is cross-manufacturer by using a camera of the existing vehicle identification equipment without carrying out proprietary protocol butt joint and network data code stream characteristic extraction.
In order to achieve the purpose, the invention adopts the technical scheme that:
a multi-parking lot vehicle data processing system, comprising:
a device access module: the license plate recognition equipment is connected to a router or a switch of each parking lot, so that the license plate recognition equipment is connected to a corresponding local area network; the vehicle identification equipment comprises a communication unit and a detection identification unit, the vehicle identification equipment is in communication connection with camera units of the parking lot, and each camera unit is provided with one vehicle identification equipment, or more than one camera unit is connected with one vehicle identification equipment at the same time;
a video acquisition module: searching and discovering a camera unit in a local area network based on an ONVIF (on-line video interface) equipment discovery protocol, and acquiring a video code stream or a video picture by adopting a standard RTSP (real time streaming protocol);
the license plate recognition module: analyzing the obtained video code stream or video picture through an artificial neural network and a computer vision technology, and extracting license plate data in the video and a real-time video of corresponding vehicle booking duration; obtaining a vehicle identification result according to the license plate data and the real-time video; the vehicle identification result includes: whether the position of the vehicle, the color of the license plate, the number of the license plate, the color of the vehicle body, the type of the vehicle, the face of a driver, the face of a copilot and the light barrier are opened or not;
a data storage module: storing the acquired license plate data and the real-time video in the vehicle identification equipment according to a service strategy record through a communication unit of the vehicle identification equipment; and the identification result is encrypted and reported to a cloud data center.
Preferably, the camera unit adopts a network camera, and is accessed to a local area network in a wired or wireless mode through the communication unit; the camera unit is arranged at an entrance, an exit, a parking space, a parking lot intersection and a parking lot turning intersection of the parking lot.
Preferably, the video acquiring module acquires an IP address of an accessed network camera and a port number corresponding to the ONVIF device discovery protocol from a router or a switch through the ONVIF device discovery protocol; and acquiring the video code stream or the video picture through an RTSP (real time streaming protocol) based on the IP address, the port number and the equipment mark of the camera unit.
Preferably, the license plate recognition module decodes the video code stream to obtain a decoded video frame; vehicle detection is carried out on the ROI of the video frame or the video picture by adopting a vehicle detection model based on a neural network; and further adopting a license plate detection model based on a neural network to carry out license plate recognition on the video frame or video picture of the detected vehicle to obtain the color and the number of the license plate.
Further extracting a real-time video with the corresponding vehicle duration of 5 to 10 seconds from the video frame of the detected vehicle; and identifying whether the position of the vehicle, the color of the vehicle body, the model of the vehicle, the face of the driver, the face of the copilot and the light barrier are opened or not according to the real-time video.
Preferably, the license plate detection model is trained by adopting license plate styles, license plate colors and license plate languages of all countries, so that the trained license plate detection model is adopted to carry out license plate recognition on the video frames or video pictures.
Preferably, when the license plate recognition module only recognizes a part of license plate numbers, identity recognition is further carried out according to the vehicle model or the face of a driver or the face of a copilot, and a complete license plate number of the cloud data center is called according to an identity recognition result; or directly matching the partial license plate numbers with the complete license plate numbers stored in the cloud data center, and obtaining the complete license plate numbers according to the matching result.
Further judging whether abnormal behaviors exist or not according to a driver face recognition result, a copilot face recognition result, a light barrier opening recognition result or not and a license plate number recognition result; and triggering an abnormal reminding function when abnormal behaviors exist.
Corresponding to the system, the invention also provides a vehicle data processing method of the multiple parking lots, which comprises the following steps:
the license plate recognition equipment is connected to a router or a switch of each parking lot, so that the license plate recognition equipment is connected to a corresponding local area network; the vehicle identification equipment comprises a communication unit and a detection identification unit, the vehicle identification equipment is in communication connection with camera units of the parking lot, and each camera unit is provided with one vehicle identification equipment, or more than one camera unit is connected with one vehicle identification equipment at the same time;
searching and discovering a camera unit in a local area network based on an ONVIF (on-line video interface) equipment discovery protocol, and acquiring a video code stream or a video picture by adopting a standard RTSP (real time streaming protocol);
analyzing the obtained video code stream or video picture through an artificial neural network and a computer vision technology, and extracting license plate data in the video and a real-time video of corresponding vehicle booking duration; obtaining a vehicle identification result according to the license plate data and the real-time video; the vehicle identification result includes: whether the position of the vehicle, the color of the license plate, the number of the license plate, the color of the vehicle body, the type of the vehicle, the face of a driver, the face of a copilot and the light barrier are opened or not;
storing the acquired license plate data and the real-time video in the vehicle identification equipment according to a service strategy record through a communication unit of the vehicle identification equipment; and the identification result is encrypted and reported to a cloud data center.
The invention has the beneficial effects that:
(1) the invention connects the license plate recognition device with operation and network communication ability to the router or exchanger used by the original parking lot license plate recognition system, so that the license plate recognition device is connected to the local area network.
(2) The method adopts an international universal standard protocol, does not need to master the communication protocol and the encryption method of each license plate manufacturer, and can greatly reduce the investment of manpower and material resources.
(3) The method of the invention obtains the real video picture of the camera instead of the network data packet of the packet capturing, and can ensure the validity and the authenticity of the data.
(4) The invention also records the original video picture while identifying the license plate, and can restore the real picture for proofreading in modes of playback and the like when the data has doubt.
(5) The accuracy of license plate recognition of the invention depends on the own license plate recognition algorithm and does not depend on the respective algorithms of numerous license plate recognition manufacturers, and for the condition of vehicles which cannot be recognized, the own license plate recognition algorithm can achieve richer recognition categories through customized training, which is a characteristic that network packet capturing does not have;
(6) the invention further judges whether the vehicle belongs to abnormal behaviors according to the identification results of the license plate number, the face and the light barrier, thereby playing a role in risk prevention; the existing parking lot mainly adopts manual management or directly rejects vehicles without license plates, so that vehicle data is lost and reliable supervision cannot be carried out;
(7) the scheme of the invention can coexist with the existing license plate recognition system, is compatible with equipment of a plurality of manufacturers, realizes the transfer of license plate data under the condition of not needing a proprietary docking protocol of the license plate recognition equipment manufacturers, and has the advantages of saving hardware deployment cost and flexible algorithm;
(8) the invention can expand the application on the basis of obtaining the video picture, and can realize more applications under the condition of upgrading the algorithm.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention clearer and more obvious, the present invention is further described in detail with reference to specific embodiments below. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention relates to a vehicle data processing system of a multi-parking lot, which comprises:
a device access module: the license plate recognition equipment is connected to a router or a switch of each parking lot (the router or the switch can directly use the router or the switch used by the original parking lot license plate recognition system, so that the hardware cost is saved), and the license plate recognition equipment is connected to a corresponding local area network; the vehicle identification equipment comprises a communication unit and a detection identification unit, the vehicle identification equipment is in communication connection with camera units of the parking lot, and each camera unit is provided with one vehicle identification equipment, or more than one camera unit is connected with one vehicle identification equipment at the same time;
a video acquisition module: searching and discovering a camera unit in a local area network based on an ONVIF (on-line video interface) equipment discovery protocol, and acquiring a video code stream or a video picture by adopting a standard RTSP (real time streaming protocol);
the license plate recognition module: analyzing the obtained video code stream or video picture through an artificial neural network and a computer vision technology, and extracting license plate data in the video and a real-time video of corresponding vehicle booking duration; obtaining a vehicle identification result according to the license plate data and the real-time video; the vehicle identification result includes: whether the position of the vehicle, the color of the license plate, the number of the license plate, the color of the vehicle body, the type of the vehicle, the face of a driver, the face of a copilot and the light barrier are opened or not;
a data storage module: storing the acquired license plate data and the real-time video in the vehicle identification equipment according to a service strategy record through a communication unit of the vehicle identification equipment; and the identification result is encrypted and reported to a cloud data center.
The ONVIF (open Network Video Interface forum) protocol provides a standardized Network open Interface, and realizes integration among license plate identification devices of different manufacturers by using the functions of SOAP, RTP, Motion JPEG, MPEG-4 and H.264 Video decoding.
Rtsp (real Time Streaming protocol) real-Time Streaming protocol is an application layer protocol in TCP/IP protocol system, which defines how one-to-many applications can effectively transmit multimedia data over IP networks. RTSP is a multimedia streaming protocol used to control audio or video and allows simultaneous multiple streaming demand control.
The camera unit adopts a network camera and is accessed to a local area network in a wired or wireless mode through the communication unit; the camera unit is arranged at an entrance, an exit, a parking space, a parking lot intersection and a parking lot turning intersection of the parking lot. The network camera is the combination of a traditional camera and a network video technology, and has all image capturing functions of a common traditional camera, and a digital compression controller and a WEB-based operating system are also arranged in the network camera, so that video data are compressed and encrypted and then are sent to a terminal user through a local area network, an internet or a wireless network. The remote user can use a standard web browser on the PC to access the web camera according to the IP address of the web camera, monitor the condition of the target site in real time, edit and store image data in real time, and control the pan-tilt and the lens of the camera to monitor in all directions.
The video acquisition module acquires an IP address of an accessed network camera and a port number corresponding to the ONVIF equipment discovery protocol from a router or a switch through the ONVIF equipment discovery protocol; and acquiring the video code stream or the video picture through an RTSP (real time streaming protocol) based on the IP address, the port number and the equipment mark of the camera unit.
The license plate recognition module decodes the video code stream to obtain a decoded video frame; vehicle detection is carried out on the ROI of the video frame or the video picture by adopting a vehicle detection model based on a neural network; and further adopting a license plate detection model based on a neural network to carry out license plate recognition on the video frame or video picture of the detected vehicle to obtain the color and the number of the license plate.
In the embodiment, a real-time video with the corresponding vehicle duration of 5 to 10 seconds is further extracted from the video frame of the detected vehicle; and identifying whether the position of the vehicle, the color of the vehicle body, the model of the vehicle, the face of the driver, the face of the copilot and the light barrier are opened or not according to the real-time video.
The license plate detection model is trained by adopting license plate styles, license plate colors and license plate languages of all countries, so that the trained license plate detection model is adopted to carry out license plate recognition on the video frames or the video pictures. Therefore, license plate numbers (such as foreign license plate numbers) which are not stored in the cloud data center can be accurately identified, and richer identification categories are achieved.
When the license plate recognition module only recognizes partial license plate numbers, identity recognition is further carried out according to the vehicle model or the face of a driver or the face of a copilot, and the complete license plate number of the cloud data center is called according to the identity recognition result;
or when the license plate recognition module only recognizes partial license plate numbers, directly matching the partial license plate numbers with the complete license plate numbers stored in the cloud data center, and obtaining the complete license plate numbers according to the matching result; for example, when the camera unit at the exit of the parking lot only shoots part of license plate numbers, the complete license plate numbers which are shot and stored in advance such as the parking lot entrance or the parking space and the like stored in the cloud data center can be called to be used as the matching result during license plate recognition.
In addition, the invention further judges whether abnormal behaviors exist according to the face recognition result of the driver, the face recognition result of the co-driver, the recognition result of whether the light barrier is opened or not and the license plate number recognition result; for example, when a human face is not recognized (it is detected that the human face is blocked or it is detected that sunglasses are worn) and the light barrier is opened, it is determined that the behavior is abnormal; or, when the human face is not recognized and no license plate number is detected (no license plate vehicle), the abnormal behavior is judged. And when abnormal behaviors exist, triggering an abnormal reminding function, such as system popup reminding or short message reminding of an administrator.
Corresponding to the system, the invention also provides a vehicle data processing method of the multiple parking lots, which comprises the following steps:
the license plate recognition equipment is connected to a router or a switch of each parking lot, so that the license plate recognition equipment is connected to a corresponding local area network; the vehicle identification equipment comprises a communication unit and a detection identification unit, the vehicle identification equipment is in communication connection with camera units of the parking lot, and each camera unit is provided with one vehicle identification equipment, or more than one camera unit is connected with one vehicle identification equipment at the same time;
searching and discovering a camera unit in a local area network based on an ONVIF (on-line video interface) equipment discovery protocol, and acquiring a video code stream or a video picture by adopting a standard RTSP (real time streaming protocol);
analyzing the obtained video code stream or video picture through an artificial neural network and a computer vision technology, and extracting license plate data in the video and a real-time video of corresponding vehicle booking duration; obtaining a vehicle identification result according to the license plate data and the real-time video; the vehicle identification result includes: whether the position of the vehicle, the color of the license plate, the number of the license plate, the color of the vehicle body, the type of the vehicle, the face of a driver, the face of a copilot and the light barrier are opened or not;
storing the acquired license plate data and the real-time video in the vehicle identification equipment according to a service strategy record through a communication unit of the vehicle identification equipment; and the identification result is encrypted and reported to a cloud data center.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. As for the method embodiment, since it is basically similar to the system embodiment, the description is simple, and the relevant points can be referred to the partial description of the system embodiment.
Also, in this document, 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 identical elements in a process, method, article, or apparatus that comprises the element. In addition, those skilled in the art will appreciate that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing associated hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disk, or the like.
While the above description shows and describes the preferred embodiments of the present invention, it is to be understood that the invention is not limited to the forms disclosed herein, but is not to be construed as excluding other embodiments and is capable of use in various other combinations, modifications, and environments and is capable of changes within the scope of the inventive concept as expressed herein, commensurate with the above teachings, or the skill or knowledge of the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A vehicle data processing system for multiple parking lots, comprising:
a device access module: the license plate recognition equipment is connected to a router or a switch of each parking lot, so that the license plate recognition equipment is connected to a corresponding local area network; the vehicle identification equipment comprises a communication unit and a detection identification unit, the vehicle identification equipment is in communication connection with camera units of the parking lot, and each camera unit is provided with one vehicle identification equipment, or more than one camera unit is connected with one vehicle identification equipment at the same time;
a video acquisition module: searching and discovering a camera unit in a local area network based on an ONVIF (on-line video interface) equipment discovery protocol, and acquiring a video code stream or a video picture by adopting a standard RTSP (real time streaming protocol);
the license plate recognition module: analyzing the obtained video code stream or video picture through an artificial neural network and a computer vision technology, and extracting license plate data in the video and a real-time video of corresponding vehicle booking duration; obtaining a vehicle identification result according to the license plate data and the real-time video; the vehicle identification result includes: whether the position of the vehicle, the color of the license plate, the number of the license plate, the color of the vehicle body, the type of the vehicle, the face of a driver, the face of a copilot and the light barrier are opened or not;
a data storage module: storing the acquired license plate data and the real-time video in the vehicle identification equipment according to a service strategy record through a communication unit of the vehicle identification equipment; and the identification result is encrypted and reported to a cloud data center.
2. The vehicle data processing system for a multi-parking lot according to claim 1, characterized in that: the camera unit adopts a network camera and is accessed to a local area network in a wired or wireless mode through the communication unit; the camera unit is arranged at an entrance, an exit, a parking space, a parking lot intersection and a parking lot turning intersection of the parking lot.
3. The vehicle data processing system for a multi-parking lot according to claim 2, characterized in that: the video acquisition module acquires an IP address of an accessed network camera and a port number corresponding to the ONVIF equipment discovery protocol from a router or a switch through the ONVIF equipment discovery protocol; and acquiring the video code stream or the video picture through an RTSP (real time streaming protocol) based on the IP address, the port number and the equipment mark of the camera unit.
4. The vehicle data processing system for a multi-parking lot according to claim 1, characterized in that: the license plate recognition module decodes the video code stream to obtain a decoded video frame; vehicle detection is carried out on the ROI of the video frame or the video picture by adopting a vehicle detection model based on a neural network; and further adopting a license plate detection model based on a neural network to carry out license plate recognition on the video frame or video picture of the detected vehicle to obtain the color and the number of the license plate.
5. The vehicle data processing system for a multi-parking lot according to claim 4, characterized in that: further extracting a real-time video with the corresponding vehicle duration of 5-10 seconds from the video frame of the detected vehicle; and identifying whether the position of the vehicle, the color of the vehicle body, the model of the vehicle, the face of the driver, the face of the copilot and the light barrier are opened or not according to the real-time video.
6. The vehicle data processing system for a multi-parking lot according to claim 4, characterized in that: the license plate detection model is trained by adopting license plate styles, license plate colors and license plate languages of all countries, so that the trained license plate detection model is adopted to carry out license plate recognition on the video frames or the video pictures.
7. The vehicle data processing system for a multi-parking lot according to claim 5, characterized in that: when the license plate recognition module only recognizes partial license plate numbers, identity recognition is further carried out according to the vehicle model or the face of a driver or the face of a copilot, and the complete license plate number of the cloud data center is called according to the identity recognition result; or directly matching the partial license plate numbers with the complete license plate numbers stored in the cloud data center, and obtaining the complete license plate numbers according to the matching result.
8. The vehicle data processing system for a multi-parking lot according to claim 5, characterized in that: further judging whether abnormal behaviors exist or not according to a driver face recognition result, a copilot face recognition result, a light barrier opening recognition result or not and a license plate number recognition result; and triggering an abnormal reminding function when abnormal behaviors exist.
9. A vehicle data processing method for multiple parking lots is characterized by comprising the following steps:
the license plate recognition equipment is connected to a router or a switch of each parking lot, so that the license plate recognition equipment is connected to a corresponding local area network; the vehicle identification equipment comprises a communication unit and a detection identification unit, the vehicle identification equipment is in communication connection with camera units of the parking lot, and each camera unit is provided with one vehicle identification equipment, or more than one camera unit is connected with one vehicle identification equipment at the same time;
searching and discovering a camera unit in a local area network based on an ONVIF (on-line video interface) equipment discovery protocol, and acquiring a video code stream or a video picture by adopting a standard RTSP (real time streaming protocol);
analyzing the obtained video code stream or video picture through an artificial neural network and a computer vision technology, and extracting license plate data in the video and a real-time video of corresponding vehicle booking duration; obtaining a vehicle identification result according to the license plate data and the real-time video; the vehicle identification result includes: whether the position of the vehicle, the color of the license plate, the number of the license plate, the color of the vehicle body, the type of the vehicle, the face of a driver, the face of a copilot and the light barrier are opened or not;
storing the acquired license plate data and the real-time video in the vehicle identification equipment according to a service strategy record through a communication unit of the vehicle identification equipment; and the identification result is encrypted and reported to a cloud data center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110899930.5A CN113851013A (en) | 2021-08-06 | 2021-08-06 | Vehicle data processing system and method for multiple parking lots |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110899930.5A CN113851013A (en) | 2021-08-06 | 2021-08-06 | Vehicle data processing system and method for multiple parking lots |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113851013A true CN113851013A (en) | 2021-12-28 |
Family
ID=78975563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110899930.5A Pending CN113851013A (en) | 2021-08-06 | 2021-08-06 | Vehicle data processing system and method for multiple parking lots |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113851013A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114745229A (en) * | 2022-02-15 | 2022-07-12 | 成都臻识科技发展有限公司 | Embedded AI video gateway and implementation method thereof |
| CN115941573A (en) * | 2022-12-07 | 2023-04-07 | 四川天邑康和通信股份有限公司 | Method for analyzing monitoring video frame loss and judging switch performance |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105872453A (en) * | 2015-12-15 | 2016-08-17 | 乐视致新电子科技（天津）有限公司 | Web camera monitoring method and system as well as server |
| CN107633687A (en) * | 2017-09-08 | 2018-01-26 | 绵阳西真科技有限公司 | A kind of vehicle identification method and system for parking lot |
| CN109035860A (en) * | 2018-10-19 | 2018-12-18 | 深圳市安立克电子有限公司 | A kind of parking position statistical system and its workflow |
| CN110008298A (en) * | 2019-03-28 | 2019-07-12 | 武汉星视源科技有限公司 | Parking multidimensional information aware application system and method |
| CN111401287A (en) * | 2020-03-24 | 2020-07-10 | 安阳工学院 | Vehicle authentication method and device in parking charging system |
| CN111694861A (en) * | 2020-06-16 | 2020-09-22 | 天津白泽技术有限公司 | License plate data extraction method based on network data code stream characteristic analysis |
-
2021
- 2021-08-06 CN CN202110899930.5A patent/CN113851013A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105872453A (en) * | 2015-12-15 | 2016-08-17 | 乐视致新电子科技（天津）有限公司 | Web camera monitoring method and system as well as server |
| CN107633687A (en) * | 2017-09-08 | 2018-01-26 | 绵阳西真科技有限公司 | A kind of vehicle identification method and system for parking lot |
| CN109035860A (en) * | 2018-10-19 | 2018-12-18 | 深圳市安立克电子有限公司 | A kind of parking position statistical system and its workflow |
| CN110008298A (en) * | 2019-03-28 | 2019-07-12 | 武汉星视源科技有限公司 | Parking multidimensional information aware application system and method |
| CN111401287A (en) * | 2020-03-24 | 2020-07-10 | 安阳工学院 | Vehicle authentication method and device in parking charging system |
| CN111694861A (en) * | 2020-06-16 | 2020-09-22 | 天津白泽技术有限公司 | License plate data extraction method based on network data code stream characteristic analysis |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114745229A (en) * | 2022-02-15 | 2022-07-12 | 成都臻识科技发展有限公司 | Embedded AI video gateway and implementation method thereof |
| CN114745229B (en) * | 2022-02-15 | 2024-04-12 | 成都臻识科技发展有限公司 | Embedded AI video gateway and implementation method thereof |
| CN115941573A (en) * | 2022-12-07 | 2023-04-07 | 四川天邑康和通信股份有限公司 | Method for analyzing monitoring video frame loss and judging switch performance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3999561B2 (en) | Surveillance system and surveillance camera | |
| CN113851013A (en) | Vehicle data processing system and method for multiple parking lots | |
| WO2020057355A1 (en) | Three-dimensional modeling method and device | |
| CN102833478B (en) | Fault-tolerant background model | |
| CN106559645B (en) | Monitoring method, system and device based on camera | |
| KR102237086B1 (en) | Apparatus and method for controlling a lobby phone that enables video surveillance through a communication terminal that can use a 5G mobile communication network based on facial recognition technology | |
| WO2007063970A1 (en) | Monitor camera system and face image trace recording method | |
| CN112887511A (en) | Intelligent video processing device | |
| CN103049460A (en) | Video surveillance scene information classifying and storing method and search method | |
| CN102176746A (en) | Intelligent monitoring system used for safe access of local cell region and realization method thereof | |
| KR102297217B1 (en) | Method and apparatus for identifying object and object location equality between images | |
| US20180270454A1 (en) | Video monitoring method and device | |
| CN106060470A (en) | Video monitoring method and system | |
| CN110852306A (en) | Safety monitoring system based on artificial intelligence | |
| KR20200013340A (en) | syntax-based method of providing inter-operative processing with video analysis system of compressed video | |
| CN114092865A (en) | Prisoner supervision method and system based on neural network | |
| TW202303399A (en) | Equipment linkage method, equipment and computer-readable storage medium | |
| CN110855947B (en) | Image snapshot processing method and device | |
| KR101547255B1 (en) | Object-based Searching Method for Intelligent Surveillance System | |
| CN110895663A (en) | Two-wheel vehicle identification method and device, electronic equipment and monitoring system | |
| CN108200390A (en) | Video structure analyzing method and device | |
| CN109951690B (en) | Robot body security system and method based on image analysis of camera array | |
| CN112601054B (en) | Pickup picture acquisition method and device, storage medium and electronic equipment | |
| CN208013967U (en) | A kind of examination hall monitor camera and system based on face recognition technology | |
| CN111382697B (en) | Image data processing method and first electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |