CN113591820A - Driving data storage method capable of extracting hit-and-run license plate information - Google Patents
Driving data storage method capable of extracting hit-and-run license plate information Download PDFInfo
- Publication number
- CN113591820A CN113591820A CN202111165482.2A CN202111165482A CN113591820A CN 113591820 A CN113591820 A CN 113591820A CN 202111165482 A CN202111165482 A CN 202111165482A CN 113591820 A CN113591820 A CN 113591820A
- Authority
- CN
- China
- Prior art keywords
- license plate
- image
- driving
- vehicle
- extracting
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The invention relates to the technical field of digital information transmission, in particular to a driving data storage method capable of extracting hit-and-run license plate information. The method comprises the following steps of acquiring driving image data of a target vehicle; carrying out violation detection on vehicles around a target vehicle, receiving violation signals of the vehicles around, processing image data by adopting an image conversion and recognition algorithm, and extracting license plate pictures of the vehicles around; and receiving license plate pictures of vehicles around the violation, extracting license plate character data by adopting a computer vision technology, and storing the license plate character data in a license plate memory. The invention can capture the driving image data of the surrounding vehicles, so that the vehicles can be mutually monitored, the violation behaviors of the surrounding vehicles can be accurately and stably detected, a clearer license plate picture can be obtained, and the method is favorable for more accurate post-processing according to the violation information.
Description
Technical Field
The invention relates to the technical field of digital information transmission, in particular to a driving data storage method capable of extracting hit-and-run license plate information.
Background
The electronic eye realizes all-weather monitoring on the violation behaviors of red light running, backward running, overspeed running, line-crossing running and the like of the motor vehicle by a plurality of technologies such as vehicle detection, photoelectric imaging, automatic control and the like, captures vehicle violation image-text information and performs post-processing according to the violation information;
however, some road sections are not provided with electronic eyes, and the illegal vehicles cannot be found in time when encountering the illegal vehicles, so that the illegal vehicles escape, the management and control of road safety are not facilitated, a traffic control center is easy to delay to find the target vehicles causing the trouble in time, the practicability is not strong, and the safety performance is reduced in the driving process, however, some driving vehicles are provided with driving recorders to record driving images of the target vehicles and simultaneously capture image data of the driving of the surrounding vehicles, and the driving recorders do not detect the illegal behaviors of the surrounding vehicles, so that even if the illegal images of the surrounding vehicles are obtained, signals cannot be sent, the vehicles cannot be monitored mutually, and the road driving safety is limited;
in addition, when the existing electronic eye detects a violation vehicle, the method for capturing the image-text information of the violation vehicle has poor stability, the detection accuracy needs to be improved, and the image cannot be processed, so that the obtained license plate information of the violation vehicle is fuzzy, is not beneficial to subsequent processing, is easy to cause misjudgment, and has poor practicability.
Disclosure of Invention
The present invention aims to provide a driving data storage method capable of extracting hit-and-run license plate information, so as to solve the problems proposed in the background art.
In order to achieve the above object, the present invention provides a driving data storage method capable of extracting hit-and-run license plate information, comprising the following steps:
the driving image data of the target vehicle is obtained, so that the driving image data of the target vehicle can be obtained, and the driving image data of surrounding vehicles can be shot, so that each target vehicle can act as an illegal detector to monitor the surrounding vehicles, the road driving data can be conveniently and comprehensively extracted, and the safety performance of road driving is improved;
carrying out violation detection on vehicles around a target vehicle in a processor, acquiring the speed of the surrounding vehicles by adopting a spatial parameter movement speed detection algorithm, establishing data interaction comparison with a preset speed, acquiring lane change behaviors of the surrounding vehicles by adopting a spatial parameter vehicle lane change detection algorithm, and acquiring data of the surrounding vehicles crushing a white lane line;
when the speed of the surrounding vehicle is less than or equal to the preset speed and the data that the surrounding vehicle crushes the white lane line are not received, storing the acquired driving image data in an image memory, and when the speed of the surrounding vehicle is greater than the preset speed or the data that the surrounding vehicle crushes the white lane line are received, transmitting a surrounding vehicle violation signal;
receiving violation signals of surrounding vehicles, processing image data by adopting an image conversion and recognition algorithm, positioning license plates, and extracting license plate pictures of the surrounding vehicles;
the method comprises the following steps that the license plate position of a surrounding vehicle cannot be positioned or the license plate picture is blocked, the position of the surrounding vehicle is determined by adopting a GPS positioning technology, then abnormal information and position information of the surrounding vehicle are transmitted to a traffic control center, the traffic control center inquires the information of an illegal vehicle in time, and the illegal vehicle is prevented from escaping;
and receiving license plate pictures of vehicles around the violation, extracting license plate character data by adopting a computer vision technology, and storing the license plate character data in a license plate memory.
As a further improvement of the technical solution, the driving recorder is adopted to acquire the driving image data of the target vehicle, and the driving recorder not only can realize online monitoring of overspeed and fatigue driving and finally achieve the purposes of preventing traffic accidents and realizing safe driving, but also can acquire the images around the target vehicle, thereby acquiring the images of the surrounding vehicles in the surrounding environment.
As a further improvement of the technical solution, the spatial parameter motion velocity detection algorithm has the following calculation formula:
v is the movement speed of surrounding vehicles, fps is the sampling rate of an image sequence in background difference, D is the distance between two virtual measurement lines in influence data corresponding to actual road positions, namely the lane lines at two ends of a road, fra1 is the frame number of a track point on an upper virtual measurement line, fra2 is the frame number of a track point on a lower virtual measurement line, the movement speed of the surrounding vehicles can be calculated, and therefore whether the surrounding vehicles overspeed during running is judged.
As a further improvement of the technical solution, the calculation formula of the spatial parameter vehicle lane change detection algorithm is as follows:
wherein, DeltaX is the lane change detection value of the vehicle, XnIs the abscissa value, x, of the extreme point of the moving target area of the target vehicletnThe maximum value of the abscissa of the lane line sequence is shown, and T is the threshold value of the violation lane-changing line;
when the delta X is larger than or equal to 0, the vehicle does not change the lane to the left in a violation manner;
when the delta X is less than 0, the vehicle changes lanes illegally to the left, the position of a lane line is recorded in an image space parameter through the acquired surrounding vehicle driving image data by adopting a space parameter vehicle lane change detection algorithm, then whether the vehicle presses the line or not is judged, whether the surrounding vehicle changes lanes illegally or not is determined, the detection is more stable, the target vehicle is prevented from shaking during driving, the detection is not accurate, and the detection accuracy is improved.
As a further improvement of the technical solution, the image conversion recognition algorithm includes the following steps:
and (3) converting the color image of the image data into a gray-scale image for processing:
grayscale =0.229R +0.587G + 0.114B;
performing image enhancement by a median filtering method, firstly roaming a template in a picture, superposing the center of the template with a certain pixel position in the picture, reading the gray values of corresponding pixels under the template, arranging the gray values into a row from small to large, finding out the middle one of the gray values, and assigning the middle value to the pixel corresponding to the center position of the template;
automatically selecting a threshold value of the image data by adopting an Otsu method;
and extracting license plate pictures of surrounding vehicles by a key frame extraction algorithm.
As a further improvement of the technical scheme, the Otsu method specifically comprises:
frequency of gradation value:
grayscale mean of image:
accumulating the histograms:
class separation index:
optimal threshold value: t = s
Wherein T is the threshold of the image data, P (K) is the frequency of the gray-level value,
is the mean value of the gray levels of the image,
in order to accumulate the histograms in the image data,
for class separation index, K is the gray scale value, f (i, j) is the gray scale value at the image point (i, j), M N is the license plate area of the target vehicleThe area, s, is the maximum value of the class separation index.
As a further improvement of the technical solution, the key frame extraction algorithm specifically includes:
calculating the change of visual attention between the i frame and the j frame:
the visual attention of a lens varies as:
calculating the number of key frames allocated to each shot according to the shot change:
clustering the video frames with similar colors so that the distance between the centers of the clusters meets the following inequality:
wherein D isijFor visual attention change between i and j frames, M is the total number of blocks in a frame, AmIs one of the blocks in a frame, m is the mth block number in a frame, D is the visual attention change of a shot, N is the number of video frames of the shot, C is the number of key frames, T is the total number of given key frames, DkeyFor each cluster center distance, DaveDistances of all frames within the shot to the extracted key frames, DdivIs the variance of the received signal and the received signal,
selecting the frame with the greatest attention as the key frame under the condition of satisfying the inequality as a constant, not only avoiding extracting the key frame which is too similar, but also extracting the key frameThe method has higher attention, and can effectively express the license plate information data, so that the obtained license plate pictures of surrounding vehicles are clearer.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the driving data storage method capable of extracting the hit-and-run license plate information, the driving image data of the target vehicle can be obtained by obtaining the driving image data of the target vehicle, the driving image data of surrounding vehicles can be captured, each target vehicle can be used as a violation detector to monitor the surrounding vehicles, mutual monitoring between the vehicles is facilitated, the driving data of a road can be comprehensively extracted conveniently, and the safety performance of road driving is improved.
2. According to the driving data storage method capable of extracting the information of the hit-and-run license plate, the speed of surrounding vehicles is obtained through a spatial parameter movement speed detection algorithm, data interaction comparison with preset speed is established, lane changing behaviors of the surrounding vehicles are obtained through a spatial parameter vehicle lane changing detection algorithm, data of white lane lines of the surrounding vehicles are obtained, violation behaviors of the surrounding vehicles can be accurately and stably detected, then image conversion recognition algorithm is adopted to process image data, the license plate is positioned, license plate pictures of the surrounding vehicles are extracted, clear violation license plate pictures can be obtained, post-processing according to violation information is facilitated to be more accurate, and misjudgment is avoided.
Drawings
FIG. 1 is an overall flow chart of example 1;
FIG. 2 is an overall algorithm block diagram of embodiment 1;
FIG. 3 is an overall schematic diagram of embodiment 1;
fig. 4 is a flowchart of an image conversion recognition algorithm of embodiment 1.
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.
Example 1
Referring to fig. 1-4, the present embodiment provides a driving data storage method capable of extracting hit plate information, which includes the following steps:
s1, acquiring the driving image data of the target vehicle, and capturing the driving image data of surrounding vehicles, so that each target vehicle can act as an illegal detector to monitor the surrounding vehicles, the road driving data can be conveniently and comprehensively extracted, and the safety performance of road driving is improved;
in this embodiment, the driving image data of the target vehicle is obtained by using a driving recorder, the driving recorder can not only realize online monitoring of overspeed and fatigue driving and finally achieve the purposes of preventing traffic accidents and realizing safe driving, but also obtain images around the target vehicle, thereby obtaining images of surrounding vehicles in the surrounding environment.
The target vehicle is used for acquiring surrounding vehicle images in the surrounding environment and storing the surrounding vehicle images in the storage, and the storage comprises an image storage and a license plate storage, so that data can be conveniently stored in a follow-up classification mode.
S2, violation detection is carried out on vehicles around the target vehicle in the processor, the speed of the surrounding vehicles is obtained by adopting a spatial parameter motion speed detection algorithm, data interaction comparison with a preset speed is established, lane change behaviors of the surrounding vehicles are obtained by adopting a spatial parameter vehicle lane change detection algorithm, and data of the surrounding vehicles crushing a white lane line are obtained;
when the speed of the surrounding vehicle is less than or equal to the preset speed and the data that the surrounding vehicle crushes the white lane line are not received, storing the acquired driving image data in an image memory, and when the speed of the surrounding vehicle is greater than the preset speed or the data that the surrounding vehicle crushes the white lane line are received, transmitting a surrounding vehicle violation signal;
it should be noted that the calculation formula of the spatial parameter motion velocity detection algorithm is as follows:
v is the movement speed of surrounding vehicles, fps is the sampling rate of an image sequence in background difference, D is the distance between two virtual measurement lines in influence data corresponding to actual road positions, namely the lane lines at two ends of a road, fra1 is the frame number of a track point on an upper virtual measurement line, fra2 is the frame number of a track point on a lower virtual measurement line, the movement speed of the surrounding vehicles can be calculated, and therefore whether the surrounding vehicles overspeed during running is judged.
Further, the calculation formula of the spatial parameter vehicle lane change detection algorithm is as follows:
wherein, DeltaX is the lane change detection value of the vehicle, XnIs the abscissa value, x, of the extreme point of the moving target area of the target vehicletnThe maximum value of the abscissa of the lane line sequence is shown, and T is the threshold value of the violation lane-changing line;
when the delta X is larger than or equal to 0, the vehicle does not change the lane to the left in a violation manner;
when the delta X is less than 0, the vehicle changes lanes illegally to the left, the position of a lane line is recorded in an image space parameter through the acquired surrounding vehicle driving image data by adopting a space parameter vehicle lane change detection algorithm, then whether the vehicle presses the line or not is judged, whether the surrounding vehicle changes lanes illegally or not is determined, the detection is more stable, the target vehicle is prevented from shaking during driving, the detection is not accurate, and the detection accuracy is improved.
S3, receiving violation signals of surrounding vehicles, processing image data by adopting an image conversion recognition algorithm, positioning license plates, and extracting license plate pictures of the surrounding vehicles;
the method comprises the following steps that the license plate position of a surrounding vehicle cannot be positioned or the license plate picture is blocked, the position of the surrounding vehicle is determined by adopting a GPS positioning technology, then abnormal information and position information of the surrounding vehicle are transmitted to a traffic control center, the traffic control center inquires the information of an illegal vehicle in time, and the illegal vehicle is prevented from escaping;
further, the image conversion recognition algorithm comprises the following steps:
and (3) converting the color image of the image data into a gray-scale image for processing:
grayscale =0.229R +0.587G + 0.114B;
performing image enhancement by a median filtering method, firstly roaming a template in a picture, superposing the center of the template with a certain pixel position in the picture, reading the gray values of corresponding pixels under the template, arranging the gray values into a row from small to large, finding out the middle one of the gray values, and assigning the middle value to the pixel corresponding to the center position of the template;
automatically selecting a threshold value of the image data by adopting an Otsu method;
and extracting license plate pictures of surrounding vehicles by a key frame extraction algorithm.
It is worth to say that the Otsu method specifically includes:
frequency of gradation value:
grayscale mean of image:
accumulating the histograms:
class separation index:
optimal threshold value: t = s
Wherein T is the threshold of the image data, P (K) is the frequency of the gray-level value,
is the mean value of the gray levels of the image,
in order to accumulate the histograms in the image data,
the image point is a class separation index, K is a gray value, f (i, j) is a gray value at the image point (i, j), M x N is the area of the license plate area of the target vehicle, and s is the maximum value of the class separation index;
therefore, the frequency of the gray value of the image data, the gray average value of the image, the accumulated histogram and the class separation index can be calculated by the Otsu method, the threshold value of the image data is determined, the obtained image data is more accurate and clear, and the subsequent key frame extraction is convenient.
Specifically, the key frame extraction algorithm specifically includes:
calculating the change of visual attention between the i frame and the j frame:
the visual attention of a lens varies as:
calculating the number of key frames allocated to each shot according to the shot change:
clustering the video frames with similar colors so that the distance between the centers of the clusters meets the following inequality:
wherein D isijFor visual attention change between i and j frames, M is the total number of blocks in a frame, AmIs one of the blocks in a frame, m is the mth block number in a frame, D is the visual attention change of a shot, N is the number of video frames of the shot, C is the number of key frames, T is the total number of given key frames, DkeyFor each cluster center distance, DaveDistances of all frames within the shot to the extracted key frames, DdivIs the variance of the received signal and the received signal,
the frame with the maximum attention is selected as the key frame under the condition of meeting the inequality, extraction of the key frame which is too similar is avoided, the extracted key frame has high attention (accuracy), license plate information data can be effectively expressed, license plate pictures of surrounding vehicles are clearer, license plate information can be extracted according to image data when the surrounding vehicles are detected to be illegal, the license plate information can be conveniently fed back to a traffic control center for processing, and the practicability is higher.
S4, receiving license plate pictures of vehicles around the violation, extracting license plate character data by adopting a computer vision technology, and storing the license plate character data in a license plate memory.
In summary, the invention obtains the driving image data of the target vehicle, detects the violation of the vehicle around the target vehicle in the processor, transmits the violation signal of the surrounding vehicle when the surrounding vehicle violates the rule, processes the image data by adopting an image conversion recognition algorithm, positions the license plate, extracts the license plate picture of the surrounding vehicle, cannot position the license plate position of the surrounding vehicle or the license plate picture is shielded, determines the position of the surrounding vehicle by adopting a GPS positioning technology, then transmits the abnormal information and the position information of the surrounding vehicle to a traffic control center, receives the license plate picture of the violation surrounding vehicle, extracts the license plate character data by adopting a computer vision technology, stores the license plate character data in a license plate memory, the traffic control center can influence the video content corresponding to the license plate character data stored in the memory in advance, and is convenient for a traffic management department to check the violation of the vehicle around the violation of the violation, powerful image evidence is provided for the violation of rules and regulations, the practicability is stronger, mutual monitoring between vehicles is facilitated, road driving data can be conveniently and comprehensively extracted, and the safety performance of road driving is improved.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. A driving data storage method capable of extracting hit-and-run license plate information is characterized by comprising the following steps:
acquiring driving image data of a target vehicle;
carrying out violation detection on vehicles around a target vehicle in a processor, acquiring the speed of the surrounding vehicles by adopting a spatial parameter movement speed detection algorithm, establishing data interaction comparison with a preset speed, acquiring lane change behaviors of the surrounding vehicles by adopting a spatial parameter vehicle lane change detection algorithm, and acquiring data of the surrounding vehicles crushing a white lane line;
when the speed of the surrounding vehicle is less than or equal to the preset speed and the data that the surrounding vehicle crushes the white lane line are not received, storing the acquired driving image data in an image memory, and when the speed of the surrounding vehicle is greater than the preset speed or the data that the surrounding vehicle crushes the white lane line are received, transmitting a surrounding vehicle violation signal;
receiving violation signals of surrounding vehicles, processing image data by adopting an image conversion and recognition algorithm, positioning license plates, and extracting license plate pictures of the surrounding vehicles;
the method comprises the following steps that the license plate position of surrounding vehicles cannot be positioned or license plate pictures are shielded, the position of the surrounding vehicles is determined by adopting a GPS positioning technology, and then abnormal information and position information of the surrounding vehicles are transmitted to a traffic control center;
and receiving license plate pictures of vehicles around the violation, extracting license plate character data by adopting a computer vision technology, and storing the license plate character data in a license plate memory.
2. The driving data storage method capable of extracting hit plate information according to claim 1, wherein: and the driving image data of the target vehicle is acquired by adopting a driving recorder.
3. The driving data storage method capable of extracting hit plate information according to claim 1, wherein: the calculation formula of the spatial parameter motion speed detection algorithm is as follows:
wherein V is the moving speed of the surrounding vehicles, fps is the sampling rate of the image sequence in the background difference, D is the distance between the two virtual measuring lines in the influence data corresponding to the actual road positions, namely the two road lines at the two ends of the road, fra1 is the frame number of the virtual measuring line with the track point at the upper part, and fra2 is the frame number of the virtual measuring line with the track point at the lower part.
4. The driving data storage method capable of extracting hit plate information according to claim 1, wherein: the calculation formula of the space parameter vehicle lane change detection algorithm is as follows:
wherein, Delta X is a vehicleLane change detection value, xnIs the abscissa value, x, of the extreme point of the moving target area of the target vehicletnThe maximum value of the abscissa of the lane line sequence is shown, and T is the threshold value of the violation lane-changing line.
5. The driving data storage method capable of extracting hit plate information according to claim 1, wherein: the image conversion recognition algorithm comprises the following steps:
and (3) converting the color image of the image data into a gray-scale image for processing:
grayscale =0.229R +0.587G + 0.114B;
performing image enhancement by a median filtering method, firstly roaming a template in a picture, superposing the center of the template with a certain pixel position in the picture, reading the gray values of corresponding pixels under the template, arranging the gray values into a row from small to large, finding out the middle one of the gray values, and assigning the middle value to the pixel corresponding to the center position of the template;
automatically selecting a threshold value of the image data by adopting an Otsu method;
and extracting license plate pictures of surrounding vehicles by a key frame extraction algorithm.
6. The driving data storage method capable of extracting hit plate information according to claim 5, wherein: the Otsu method specifically comprises the following steps:
frequency of gradation value:
grayscale mean of image:
accumulating the histograms:
class separation index:
optimal threshold value: t = s
Wherein T is the threshold of the image data, P (K) is the frequency of the gray-level value,
is the mean value of the gray levels of the image,
in order to accumulate the histograms in the image data,
the image point is a class separation index, K is a gray value, f (i, j) is a gray value at the image point (i, j), M N is the area of the license plate area of the target vehicle, and s is the maximum value of the class separation index.
7. The driving data storage method capable of extracting hit plate information according to claim 5, wherein: the key frame extraction algorithm specifically comprises:
calculating the change of visual attention between the i frame and the j frame:
the visual attention of a lens varies as:
calculating the number of key frames allocated to each shot according to the shot change:
clustering the video frames with similar colors so that the distance between the centers of the clusters meets the following inequality:
wherein D isijFor visual attention change between i and j frames, M is the total number of blocks in a frame, AmIs one of the blocks in a frame, m is the mth block number in a frame, D is the visual attention change of a shot, N is the number of video frames of the shot, C is the number of key frames, T is the total number of given key frames, DkeyFor each cluster center distance, DaveDistances of all frames within the shot to the extracted key frames, DdivIs the variance of the received signal and the received signal,
is a constant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111165482.2A CN113591820A (en) | 2021-09-30 | 2021-09-30 | Driving data storage method capable of extracting hit-and-run license plate information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111165482.2A CN113591820A (en) | 2021-09-30 | 2021-09-30 | Driving data storage method capable of extracting hit-and-run license plate information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113591820A true CN113591820A (en) | 2021-11-02 |
Family
ID=78242859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111165482.2A Pending CN113591820A (en) | 2021-09-30 | 2021-09-30 | Driving data storage method capable of extracting hit-and-run license plate information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113591820A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105632175A (en) * | 2016-01-08 | 2016-06-01 | 上海微锐智能科技有限公司 | Vehicle behavior analysis method and system |
| CN105702048A (en) * | 2016-03-23 | 2016-06-22 | 武汉理工大学 | Automobile-data-recorder-based illegal lane occupation identification system and method for automobile on highway |
| CN106023596A (en) * | 2016-07-21 | 2016-10-12 | 北京奇虎科技有限公司 | Vehicle violation detection method, device and system based on driving video |
| CN106652468A (en) * | 2016-12-09 | 2017-05-10 | 武汉极目智能技术有限公司 | Device and method for detection of violation of front vehicle and early warning of violation of vehicle on road |
| CN107481526A (en) * | 2017-09-07 | 2017-12-15 | 公安部第三研究所 | System and method for drive a vehicle lane change detection record and lane change violating the regulations report control |
| KR20190040658A (en) * | 2017-10-11 | 2019-04-19 | 최혁재 | automatic Illegal driving shooting, analysis, reporting and transmission system |
| CN109740420A (en) * | 2018-11-22 | 2019-05-10 | 深圳市华尊科技股份有限公司 | Vehicle illegal recognition methods and Related product |
| WO2020000251A1 (en) * | 2018-06-27 | 2020-01-02 | 潍坊学院 | Method for identifying video involving violation at intersection based on coordinated relay of video cameras |
| CN110782485A (en) * | 2019-10-31 | 2020-02-11 | 广东泓胜科技股份有限公司 | Vehicle lane change detection method and device |
| CN111340003A (en) * | 2020-03-26 | 2020-06-26 | 公安部交通管理科学研究所 | Evidence obtaining method and system for illegal lane change behavior in electronic police blind area |
| CN112687103A (en) * | 2020-12-23 | 2021-04-20 | 安徽中科美络信息技术有限公司 | Vehicle lane change detection method and system based on Internet of vehicles technology |
-
2021
- 2021-09-30 CN CN202111165482.2A patent/CN113591820A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105632175A (en) * | 2016-01-08 | 2016-06-01 | 上海微锐智能科技有限公司 | Vehicle behavior analysis method and system |
| CN105702048A (en) * | 2016-03-23 | 2016-06-22 | 武汉理工大学 | Automobile-data-recorder-based illegal lane occupation identification system and method for automobile on highway |
| CN106023596A (en) * | 2016-07-21 | 2016-10-12 | 北京奇虎科技有限公司 | Vehicle violation detection method, device and system based on driving video |
| CN106652468A (en) * | 2016-12-09 | 2017-05-10 | 武汉极目智能技术有限公司 | Device and method for detection of violation of front vehicle and early warning of violation of vehicle on road |
| CN107481526A (en) * | 2017-09-07 | 2017-12-15 | 公安部第三研究所 | System and method for drive a vehicle lane change detection record and lane change violating the regulations report control |
| KR20190040658A (en) * | 2017-10-11 | 2019-04-19 | 최혁재 | automatic Illegal driving shooting, analysis, reporting and transmission system |
| WO2020000251A1 (en) * | 2018-06-27 | 2020-01-02 | 潍坊学院 | Method for identifying video involving violation at intersection based on coordinated relay of video cameras |
| CN109740420A (en) * | 2018-11-22 | 2019-05-10 | 深圳市华尊科技股份有限公司 | Vehicle illegal recognition methods and Related product |
| CN110782485A (en) * | 2019-10-31 | 2020-02-11 | 广东泓胜科技股份有限公司 | Vehicle lane change detection method and device |
| CN111340003A (en) * | 2020-03-26 | 2020-06-26 | 公安部交通管理科学研究所 | Evidence obtaining method and system for illegal lane change behavior in electronic police blind area |
| CN112687103A (en) * | 2020-12-23 | 2021-04-20 | 安徽中科美络信息技术有限公司 | Vehicle lane change detection method and system based on Internet of vehicles technology |
Non-Patent Citations (6)
| Title |
|---|
| HEE-SIN LEE等: "A Real-Time System for Detecting Illegal Changes-of-Lane Based on Tracking of Feature Points", 《2010 IEEE 71ST VEHICULAR TECHNOLOGY CONFERENCE》 * |
| 刘琦琪等: "《汽车美容与装潢》", 31 August 2016, 重庆：重庆大学出版社 * |
| 周伯萌: "基于高清视频的道路车辆违章行为检测算法实现和优化", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 姜代红著: "《复杂环境下监控图像拼接与识别》", 28 February 2017, 徐州：中国矿业大学出版社 * |
| 李袁秀: "基于连续视频流的交通状况与违章行为模式识别研究与实现", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 蒋鹏: "基于语义的视频内容提取与分析关键技术研究", 《万方》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102348128B (en) | Surveillance camera system having camera malfunction detection function | |
| KR101935399B1 (en) | Wide Area Multi-Object Monitoring System Based on Deep Neural Network Algorithm | |
| Bas et al. | Automatic vehicle counting from video for traffic flow analysis | |
| CN112800860B (en) | High-speed object scattering detection method and system with coordination of event camera and visual camera | |
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| US20090174773A1 (en) | Camera diagnostics | |
| CN105744232A (en) | Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology | |
| Bedruz et al. | Real-time vehicle detection and tracking using a mean-shift based blob analysis and tracking approach | |
| CN109918971B (en) | Method and device for detecting number of people in monitoring video | |
| CN110781853B (en) | Crowd abnormality detection method and related device | |
| KR101492473B1 (en) | Context-aware cctv intergrated managment system with user-based | |
| CN112528861A (en) | Foreign matter detection method and device applied to track bed in railway tunnel | |
| CN112769877A (en) | Group fog early warning method, cloud server, vehicle and medium | |
| CN110544271B (en) | Parabolic motion detection method and related device | |
| Reddy et al. | Traffic rules violation detection using machine learning techniques | |
| CN111860210A (en) | Method and device for detecting separation of hands from steering wheel, electronic equipment and storage medium | |
| CN115035564A (en) | Face recognition method, system and related components based on intelligent patrol car camera | |
| CN115346197A (en) | Driver distraction behavior identification method based on bidirectional video stream | |
| CN110728212A (en) | Road well lid monitoring device and method based on computer vision | |
| CN114530042A (en) | Urban traffic brain monitoring system based on internet of things technology | |
| CN111241918B (en) | Vehicle tracking prevention method and system based on face recognition | |
| CN109726750B (en) | Passenger fall detection device, passenger fall detection method and passenger conveying device | |
| CN113591820A (en) | Driving data storage method capable of extracting hit-and-run license plate information | |
| WO2022267266A1 (en) | Vehicle control method based on visual recognition, and device | |
| CN113378803A (en) | Road traffic accident detection method, device, computer and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211102 |