CN110728846B - Vehicle snapshot accurate control method - Google Patents
Vehicle snapshot accurate control method Download PDFInfo
- Publication number
- CN110728846B CN110728846B CN201911004975.0A CN201911004975A CN110728846B CN 110728846 B CN110728846 B CN 110728846B CN 201911004975 A CN201911004975 A CN 201911004975A CN 110728846 B CN110728846 B CN 110728846B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- camera
- license plate
- video
- height
- 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
Classifications
-
- 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
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/64—Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a vehicle snapshot accurate control method, which comprises the following steps of initializing a preset position; step two, detecting an illegal vehicle, and pushing the structured data of the illegal vehicle into kafka; step three, consuming the kafka message, starting a video at the same time, acquiring frame position information of the vehicle, and pushing a camera forward; fourthly, carrying out video screenshot on the video and carrying out snapshot comparison on the vehicle; step five, intercepting a medium scene picture, finding the position information of the license plate, and pushing a camera forward; step six, intercepting a close-range picture, identifying the license plate number in the picture, and executing step eight if the license plate number is a compliant license plate number; if not, executing step seven; step seven, closing the original video and restarting the video; step eight, taking the central point of the license plate as a center, and pulling the camera backwards; step nine, taking the center point of the vehicle as a center, and pulling the camera backwards; and step ten, swinging the camera, adjusting the camera to return to a preset position, and stopping recording.
Description
Technical Field
The invention relates to a vehicle snapshot accurate control technology, in particular to a vehicle snapshot accurate control method.
Background
With the continuous updating of the security industry standards and the implementation of AI algorithms, artificial intelligence and the like, automation and intellectualization have become the trend of security and related industries. The updating of safety, automation and intellectualization promotes the continuous improvement of the national requirements on the compatibility and intellectualization between security industry platforms. With the continuous expansion of the intelligent security range, the application based on the video analysis method becomes the development direction of the security industry.
At present, algorithms for video images are more, including video vehicle structured algorithms, human body structured algorithms, human face structured algorithms, behavior structured algorithms and the like, but a camera cannot be scheduled to realize multi-dimensional snapshot of long shot, medium shot and close shot according to standards, and the degree of automation is not high.
Disclosure of Invention
In order to solve the problems, the invention provides a vehicle snapshot accurate control method.
In order to realize the purpose, the invention adopts the technical scheme that:
a vehicle snapshot accurate control method comprises the following steps:
the method comprises the following steps: initializing a preset bit, a historical video path and a coding library;
step two: the system detects a vehicle staying in a no-parking area for more than the allowable time through intrusion detection, and pushes the structured data of the vehicle into kafka;
step three: consuming the kafka message, starting video recording, snapshotting subsequent behavior actions of the vehicle through a camera, analyzing structural data, acquiring frame position information of the vehicle, setting the width and height of the vehicle after frame pulling by taking the center point of the vehicle as the center point of a pull frame of the camera, and pushing the camera forwards;
step four: carrying out video screenshot on the video of the video, carrying out vehicle snapshot comparison, not retrieving repeated data, executing the fifth step, retrieving the repeated data, and executing the ninth step;
step five: intercepting a middle scene picture, analyzing the picture into data through a structured analysis method, finding the position information of the license plate, setting the width and the height of the license plate after the license plate is pulled by taking the center point of the license plate as the center point of the pull frame of the camera, and pushing the camera forwards;
step six: intercepting a close-range picture, identifying the license plate number of the vehicle in the picture, judging whether the license plate number is a compliant license plate number, and if so, executing the step eight; if not, executing step seven;
step seven: closing the original video and restarting the video;
step eight: setting the width and the height to be half of the width and the height of a current screen by taking the central point of a license plate as a center, and pulling a camera backwards;
step nine: setting the width and the height to be half of the width and the height of a current screen by taking a central point of a vehicle as a center, and pulling the camera backwards;
step ten: swinging the camera;
step eleven: and adjusting the camera to return to a preset position, and stopping recording.
Preferably, the allowable time in the second step may be set to 30 s.
Preferably, the intrusion detection in the second step is realized by a video annotation function.
Preferably, the width and the height of the vehicle behind the pull frame in the third step are both 1.4 times of the width and the height of the vehicle in front of the pull frame.
Preferably, in the fifth step, the width and the height of the license plate after being drawn are 1.4 times of the width and the height of the license plate before being drawn.
Preferably, the identification of the license plate number of the vehicle in the sixth step is realized by adopting an OCR image character recognition technology.
Preferably, the camera is pulled backwards in the step eight and the step nine and then stays for 3-5s respectively.
Preferably, the camera is a high-definition camera with more than 200 ten thousand pixels, and can be a high-definition dome camera, a moving dome gun camera or a high-point dome camera.
The invention has the advantages that the video monitoring is used for accurately capturing, the integrity and the uniqueness of an evidence chain are further provided, the multi-dimensional capturing of long-range scenes, medium-range scenes and close-range scenes of illegal vehicles can be realized according to the standards of traffic laws, the capturing is not limited to a special camera, and the cost is lower.
Drawings
The accompanying drawings are included to provide a further understanding of the invention.
In the drawings:
FIG. 1 is a work flow diagram of a vehicle snapshot precision control method according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a vehicle snapshot precision control method includes the following steps:
the method comprises the following steps: initializing preset bits, historical video paths, a coding library and other environments;
step two: starting to detect videos in real time, realizing intrusion detection by the system through a video marking function, detecting vehicles staying in a no-parking area for exceeding the allowable time, and pushing the structural data of the vehicles into kafka;
step three: consuming the kafka message, starting video recording at the same time, capturing subsequent behavior actions of the vehicle through a camera, and setting the permission time to be 30 s; after analyzing the vehicle structure data, obtaining frame position information of the vehicle, taking a vehicle center point as a center point of a camera drawing frame, marking coordinates of the center point as (x, y), setting the width and the height of the vehicle after drawing the frame, and pushing the camera forwards, wherein the width and the height of the vehicle after drawing the frame are 1.4 times of the width and the height of the vehicle before drawing the frame;
step four: carrying out video screenshot on the video recorded by the video, carrying out vehicle snapshot comparison, namely comparing the video screenshot of the subsequent snapshot with the original image, not retrieving repeated data, executing the fifth step, retrieving the repeated data, and executing the ninth step, wherein the repeated data refers to the structured data of the same vehicle;
step five: intercepting a middle scene picture, analyzing the picture into data through a structured analysis method, finding position information of a license plate, taking the center point of the license plate as the center point of a pull frame of the camera again, marking coordinates of the center point as (x1, y1), setting the width and height of the license plate after pulling the frame, and pushing the camera forwards, wherein the width and height of the license plate after pulling the frame are both 1.4 times of the width and height of the license plate before pulling the frame;
step six: intercepting a close-range picture, identifying the license plate number of the vehicle in the picture by an OCR image character recognition technology, judging whether the license plate number is a compliant license plate number, and executing the step eight if the license plate number is compliant; if not, executing step seven; in the embodiment, judging whether the license plate number of the vehicle is a compliant license plate number takes the example of whether the license plate number of the vehicle is a Beijing license plate number or not;
step seven: closing the original video and restarting the video;
step eight: setting the width and the height to be half of the width and the height of a current screen by taking the central point of a license plate as a center, pulling the camera backwards, and staying for 3-5 s;
step nine: setting the width and the height to be half of the width and the height of a current screen by taking the central point of the vehicle as a center, pulling the camera backwards, and staying for 3-5 s;
step ten: swinging the camera;
step eleven: and adjusting the camera to return to a preset position, and stopping recording.
The staying time after the camera is pulled in the eighth step and the ninth step can be properly prolonged according to the judgment that the license plate number of the vehicle is a non-compliant vehicle, and the evidence obtaining time is increased.
The camera is a high-definition camera with more than 200 ten thousand pixels and can be a high-definition ball machine, a ball moving gun machine or a high-point ball machine. The ratio of the width and the height of the vehicle after the camera is pulled is set according to the size of a display screen of the video monitoring system, a picture corresponding to the center of the screen is taken as an original point, the image is sequentially amplified to a medium view effect and a long-distance view effect in proportion, and the proportion can be 1.4 to achieve the best effect.
The invention relates to an automatic control whole-process scheduling method for finding illegal vehicles from a distant view to a close view and locking illegal vehicles through videos based on artificial intelligence. Presetting a preset position of a monitoring camera, performing pre-analysis on a code stream, reading a video, setting an illegal region, namely a forbidden parking region, triggering a video labeling function and monitoring a vehicle in real time when a target appears in the illegal region, and focusing the swinging camera in a 3D (three-dimensional) frame pulling mode after the allowable time is exceeded.
The working process is as follows: monitoring is carried out on a real-time video, a vehicle is found to be invaded to start video snapshot, the vehicle is searched for the first time and the camera is drawn close, the repeatability of the vehicle is judged and recognized (if the repeatability is repeated, the camera is directly drawn far to a distant view position, a preset position is turned back), the camera is drawn close to the license plate position for the second time, license plate recognition is carried out, whether the license plate is in compliance or not is judged, the camera is drawn far for the third time, the camera enters a middle view position and stops for a few seconds, the camera is drawn far for the fourth time, the camera enters the distant view position and stops for a few seconds, the camera is swung for the fifth time.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that various changes in the embodiments and/or modifications of the invention can be made, and equivalents and modifications of some features of the invention can be made without departing from the spirit and scope of the invention.
Claims (8)
1. The vehicle snapshot accurate control method is characterized by comprising the following steps: the method comprises the following steps:
the method comprises the following steps: initializing a preset bit, a historical video path and a coding library;
step two: the system detects a vehicle staying in a no-parking area for more than the allowable time through intrusion detection, and pushes the structured data of the vehicle into kafka;
step three: consuming the kafka message, starting video recording, snapshotting subsequent behavior actions of the vehicle through a camera, analyzing structural data, acquiring frame position information of the vehicle, setting the width and height of the vehicle after frame pulling by taking the center point of the vehicle as the center point of a pull frame of the camera, and pushing the camera forwards;
step four: carrying out video screenshot on the video of the video, carrying out vehicle snapshot comparison, not retrieving repeated data, executing the fifth step, retrieving the repeated data, and executing the ninth step;
step five: intercepting a middle scene picture, analyzing the picture into data through a structured analysis method, finding the position information of the license plate, setting the width and the height of the license plate after the license plate is pulled by taking the center point of the license plate as the center point of the pull frame of the camera, and pushing the camera forwards;
step six: intercepting a close-range picture, identifying the license plate number of the vehicle in the picture, judging whether the license plate number is a compliant license plate number, and if so, executing the step eight; if not, executing step seven;
step seven: closing the original video and restarting the video;
step eight: setting the width and the height to be half of the width and the height of a current screen by taking the central point of a license plate as a center, and pulling a camera backwards;
step nine: setting the width and the height to be half of the width and the height of a current screen by taking a central point of a vehicle as a center, and pulling the camera backwards;
step ten: swinging the camera;
step eleven: and adjusting the camera to return to a preset position, and stopping recording.
2. The vehicle snapshot precision control method according to claim 1, characterized in that: the permission time in the second step may be set to 30 s.
3. The vehicle snapshot precision control method according to claim 1, characterized in that: and in the second step, the intrusion detection is realized through a video annotation function.
4. The vehicle snapshot precision control method according to claim 1, characterized in that: and in the third step, the width and the height of the vehicle behind the pull frame are 1.4 times of those of the vehicle before the pull frame.
5. The vehicle snapshot precision control method according to claim 1, characterized in that: and in the fifth step, the width and the height of the license plate after the frame is pulled are both 1.4 times of the width and the height of the license plate before the frame is pulled.
6. The vehicle snapshot precision control method according to claim 1, characterized in that: and sixthly, recognizing the license plate number of the vehicle by adopting an OCR image character recognition technology.
7. The vehicle snapshot precision control method according to claim 1, characterized in that: and in the step eight and the step nine, the camera is pulled backwards and then stays for 3-5s respectively.
8. The vehicle snapshot precision control method according to claim 1, characterized in that: the camera is a high-definition camera with more than 200 ten thousand pixels and can be a high-definition ball machine, a ball moving gun machine or a high-point ball machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911004975.0A CN110728846B (en) | 2019-10-22 | 2019-10-22 | Vehicle snapshot accurate control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911004975.0A CN110728846B (en) | 2019-10-22 | 2019-10-22 | Vehicle snapshot accurate control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110728846A CN110728846A (en) | 2020-01-24 |
| CN110728846B true CN110728846B (en) | 2021-02-05 |
Family
ID=69220593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911004975.0A Active CN110728846B (en) | 2019-10-22 | 2019-10-22 | Vehicle snapshot accurate control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110728846B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112950950A (en) * | 2021-01-26 | 2021-06-11 | 上海启迪睿视智能科技有限公司 | Parking auxiliary device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198657A (en) * | 2013-03-19 | 2013-07-10 | 杨熙增 | Implementation method and system of mobile vehicle-mounted parking-violation capturing |
| CN103824454B (en) * | 2014-02-21 | 2015-10-21 | 南京莱斯信息技术股份有限公司 | The illegal automatic grasp shoot method of multizone based on video frequency event examines |
| CN105894817B (en) * | 2015-01-26 | 2019-04-30 | 杭州海康威视数字技术股份有限公司 | The evidence collecting method and its device of vehicle violation parking |
| CN205194072U (en) * | 2015-05-07 | 2016-04-27 | 吴柯维 | Linkage snapshot system and integration camera are detected to violating regulations parking |
| CN106920396A (en) * | 2015-12-24 | 2017-07-04 | 天津市军联科技有限公司 | Illegal parking intelligent candid system |
| CN107705574A (en) * | 2017-10-09 | 2018-02-16 | 荆门程远电子科技有限公司 | A kind of precisely full-automatic capturing system of quick road violation parking |
| CN107945521A (en) * | 2017-11-20 | 2018-04-20 | 青岛比特信息技术有限公司 | A kind of rifle ball linkage trackside is parked detecting system and method |
-
2019
- 2019-10-22 CN CN201911004975.0A patent/CN110728846B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110728846A (en) | 2020-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jazayeri et al. | Vehicle detection and tracking in car video based on motion model | |
| Yao et al. | When, where, and what? A new dataset for anomaly detection in driving videos | |
| JPH0795598A (en) | Object tracking device | |
| CN111507232B (en) | Stranger identification method and system based on multi-mode multi-strategy fusion | |
| CN110532937B (en) | Method for accurately identifying forward targets of train based on identification model and classification model | |
| CN103729861A (en) | Multiple object tracking method | |
| CN111008608B (en) | Night vehicle detection method based on deep learning | |
| CN111932590B (en) | Object tracking method and device, electronic equipment and readable storage medium | |
| CN115841649A (en) | Multi-scale people counting method for urban complex scene | |
| Liu et al. | Accelerating vanishing point-based line sampling scheme for real-time people localization | |
| CN110728846B (en) | Vehicle snapshot accurate control method | |
| CN110544268B (en) | Multi-target tracking method based on structured light and SiamMask network | |
| CN114359333A (en) | Moving object extraction method and device, computer equipment and storage medium | |
| CN114422720A (en) | Video concentration method, system, device and storage medium | |
| CN113869258A (en) | Traffic incident detection method and device, electronic equipment and readable storage medium | |
| CN116824549B (en) | Target detection method and device based on multi-detection network fusion and vehicle | |
| CN116824641A (en) | Gesture classification method, device, equipment and computer storage medium | |
| CN113095345A (en) | Data matching method and device and data processing equipment | |
| Evans et al. | Suppression of detection ghosts in homography based pedestrian detection | |
| CN111860100B (en) | Pedestrian number determining method and device, electronic equipment and readable storage medium | |
| CN104754248A (en) | Method and device for acquiring target snapshot | |
| JPH06169458A (en) | Automatic tracking device for moving body | |
| CN112001252A (en) | Multi-target tracking method based on heteromorphic graph network | |
| Peng et al. | Continuous vehicle detection and tracking for non-overlapping multi-camera surveillance system | |
| Zhou et al. | Static object tracking in road panoramic videos |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |