CN112183350A - Video-based illegal parking detection method - Google Patents
Video-based illegal parking detection method Download PDFInfo
- Publication number
- CN112183350A CN112183350A CN202011044589.7A CN202011044589A CN112183350A CN 112183350 A CN112183350 A CN 112183350A CN 202011044589 A CN202011044589 A CN 202011044589A CN 112183350 A CN112183350 A CN 112183350A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- detection
- illegal parking
- track
- video
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 73
- 230000003068 static effect Effects 0.000 claims abstract description 6
- 238000002360 preparation method Methods 0.000 claims abstract description 4
- 230000008034 disappearance Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims 1
- 230000006399 behavior Effects 0.000 abstract 1
- 230000000694 effects Effects 0.000 abstract 1
- 230000000903 blocking effect Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a video-based illegal parking detection method, which comprises the following steps: s1, detection preparation phase; setting a illegal parking detection area, and simultaneously carrying out background modeling on a scene; s2, extracting the target vehicle; respectively carrying out static detection, dynamic detection and block detection on a target vehicle, and carrying out matching judgment on the vehicle detected by a current frame and a vehicle track; s3, extracting the violation vehicle; and extracting the illegal parking information of the updated vehicle track information, and judging whether the vehicle violates the regulations. The video-based illegal parking detection method is applied to the fields of intelligent transportation and smart cities, is used for obtaining evidence of parking behaviors violating traffic rules, and can also be used for standardizing driving and parking regulations of drivers so as to create good traffic environment assistance. The invention is applied to traffic scenes, can achieve better effect under different light rays and scenes, and can effectively provide illegal parking evidence obtaining information.
Description
Technical Field
The invention belongs to the technical field of traffic monitoring, and particularly relates to a video-based illegal parking detection method.
Background
In the traffic field, drivers often have the defects of irregular driving and stopping, occupation of bus stops, parking in places such as sidewalks and fire hydrants and even long-time road occupation, which affects road traffic safety and even causes congestion or other unsafe influences.
Disclosure of Invention
In view of the above, the invention aims to provide a video-based illegal parking detection method, so as to solve the problems that a driver does not regulate the driving and parking, occupies a bus stop, parks in places such as a sidewalk, a fire hydrant and the like, even occupies a road for a long time, affects the road traffic safety, and even causes congestion or other unsafe problems.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a video-based illegal parking detection method comprises the following steps:
s1, detection preparation stage: setting a illegal parking detection area, and simultaneously carrying out background modeling on a scene;
s2, target vehicle extraction stage: respectively carrying out static detection, dynamic detection and block detection on a target vehicle, and carrying out matching judgment on the vehicle detected by a current frame and a vehicle track;
s3, violation vehicle extraction stage: and extracting the illegal parking information of the updated vehicle track information, and judging whether the vehicle violates the regulations.
Further, in step S1, the illegal parking detection area is set by the user or the traffic police, and if the parking time is long in the area, the illegal parking is collected as evidence.
Further, in step S1, the background modeling uses a mixed gaussian modeling scheme to perform background modeling on the scene, and performs foreground detection on each frame.
Further, the static detection adopts a network model of yoloV3 and a large-scale model of 832 × 480 to perform full-image detection; the dynamic monitoring adopts a network model of yoloV3 and a mesoscale model of 416 to carry out local dynamic detection; the block detection is carried out before the background modeling is finished or after the background modeling is finished but the number of the foreground lumps is more; matching and judging the vehicle detected by the current frame and the vehicle track, and judging whether the vehicle is the same vehicle according to the IOU and the CIOU; if the vehicle is a newly detected vehicle, new vehicle track information is created; and if the vehicle track is matched, updating the vehicle track.
Further, the step S3 is to extract the illegal parking information from the vehicle track update information obtained in the step S2, and the illegal vehicle extraction stage in the step S3 includes the steps of:
s301, judging whether the vehicle leaves;
s302, for the vehicle with the departure state being negative, whether the vehicle is a vehicle parked illegally is further judged.
Further, the determination process of whether the vehicle leaves in step S301 is as follows:
if the vehicle leaves during movement, namely the track of each frame of the vehicle is displaced, and finally the vehicle leaves the parking area, the track information of the vehicle is emptied;
otherwise, judging the vehicle track disappearance time.
Further, the process of judging the vehicle track disappearance time is as follows:
if the time is less than the set time, carrying out secondary detection near the position of the vehicle, matching the detected vehicle with the vehicle on the track, if the vehicle is matched with the track, setting the leaving state of the vehicle track as no, and if the vehicle is not matched with the track, continuing to carry out detection on each frame within the time less than the set time; and directly emptying the track information of the vehicle after the time is longer than the set time.
Further, in the step S302, for the vehicle whose leaving state is no, the determination process of whether the vehicle is a parking violation vehicle is as follows:
and if the displacement of the vehicle does not change greatly within the set time, determining that the vehicle stops for a long time, and outputting the vehicle information of the vehicle.
Compared with the prior art, the video-based illegal parking detection method has the following advantages:
(1) the video-based illegal parking detection method has the characteristics of complementation of various detection strategies and high detection rate;
(2) the video-based illegal parking detection method can better realize illegal parking evidence obtaining for vehicles which are illegally parked, and provides a guarantee for intelligent traffic, safe traffic, smart cities and intelligent travel.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is an overall flow chart of a video-based illegal parking detection method according to an embodiment of the present invention;
fig. 2 is an exemplary diagram of setting an illegal parking area of the video-based illegal parking detection method according to the embodiment of the present invention;
FIG. 3 is an exemplary view of a region being partitioned in a horizontal direction;
FIG. 4 is an exemplary diagram of blocking in a vertical direction of a region;
fig. 5 is an exemplary plot of regions 2 x 2;
FIG. 6 is a diagram of an example calculation of the IOU.
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1 to 6, a video-based illegal parking detection method includes the following steps:
step one, detection preparation stage
(1) The illegal parking detection area needs to be set, the user or the traffic police sets the illegal parking detection area, if the illegal parking detection area parks for a long time, the illegal parking is carried out, the area is shown as figure 2, the area for capturing the illegal parking is framed by a polygon, and the area is drawn according to actual needs in practical application.
(2) And in the background modeling stage, after the traffic video is acquired, modeling is carried out on the background of the scene. The implementation case adopts a mixed Gaussian modeling scheme, q Gaussian models are adopted, and the weight w of each modelq(k +1), mean value μq(k +1), variance
The learning rate ρ is updated as follows:
μq(k+1)＝(1-ρ)μq(k)+ρX(k+1)
judging pixel point Xk+1Matching with the qth model, the following formula is satisfied:
|Xk+1-μq(k)|≤2.5σq(k)
wherein, muq(k) Is the mean, σ, of the qth modelq(k) Is its variance;
m in matching modeqThe value of (k +1) is 1, and the value of 0 in the mismatch mode:
wherein, the number q of the Gaussian models is 3, k is the current frame/moment, k +1 is the next frame/moment, and the learning rate
In the case, the background modeling process is completed by setting T to 50 frames, after the background modeling is completed, foreground detection is performed on each frame, and each pixel point X isk+1And comparing the background points with the q Gaussian models respectively, and if one of the background points meets the matching condition, determining the background points as background points, and if the background points do not match with the q Gaussian models, determining the background points as foreground points.
|Xk+1-μq(k)|≤2.5σq(k)
Wherein, muq(k) Is the mean, σ, of the qth modelq(k) Is its variance.
Step two, target vehicle extraction stage
(1) Static detection: i.e. vehicle detection for a full video picture. In this embodiment, a network model of yoloV3 and a large-scale model of 832 × 480 are used to perform full-scale detection.
(2) Dynamic detection: after background modeling is completed, foreground information can be detected according to a background modeling result in each frame, coordinate areas of the blobs are output, and vehicle detection is carried out in the blob areas. The dynamic detection model adopts a network model of yoloV3 and a mesoscale model of 416 by 416 to perform local dynamic detection.
(3) Block detection: and (4) before the background modeling is finished, or after the background modeling is finished but the number of the foreground lumps is large, carrying out blocking detection. The block detection carries out split detection on the whole image/illegal parking area, the divided small areas are partially overlapped with each other, and the split mode is as follows: the width of the circumscribed rectangle of the detection area to be blocked is w, the height is h,
if w/h is greater than 2, the blocking mode is horizontal blocking, the number of blocks N is w/h, (N is greater than 1 and less than or equal to 4), as shown in fig. 3;
if h/w is greater than 2, the blocking mode is vertical blocking, the number of blocks N is h/w, (N is greater than 1 and less than or equal to 4), as shown in fig. 4;
in other cases, a 2 x 2 blocking strategy is followed, as shown in fig. 5.
(4) And matching and judging the vehicle detected by the current frame and the vehicle track, and judging whether the vehicle is the same vehicle according to the IOU and the CIOU. If the vehicle is a newly detected vehicle, new vehicle track information is created, and if the vehicle track matched with the new vehicle track information exists, the vehicle track is updated.
The calculation of the Intersection over Union IOU is shown in fig. 6, that is, the data obtained by dividing the area of the Intersection of the two regions by the area of the Union of the two regions.
Complete Intersection Over Union (CIOU) compares and analyzes the change of the overlap area, the distance of the central point and the length-width ratio of the track boxes comprehensively.
Wherein,
is a parameter for balancing the ratio, v is a parameter before the aspect ratio of the two track boxes is measured; the calculation method is as follows:
wherein (w)1，h1)(w2，h2) Representing the length and width of the two track boxes, respectively.
Step three, extracting the violation vehicle
(1) Judging whether the vehicle leaves: if the vehicle leaves in a moving way, namely the track of each frame of the vehicle is displaced, and finally the vehicle leaves the parking area, clearing the track information of the vehicle; otherwise, judging the disappearance time of the vehicle track, if the disappearance time is less than the set time, carrying out secondary detection near the vehicle position, matching the detected vehicle with the vehicle along the track, if the disappearance time is less than the set time, setting the leaving state of the vehicle track as no, and if the disappearance time is not more than the set time, continuing to carry out detection on each frame within the time less than the set time; directly emptying the track information of the vehicle after the time is longer than the set time; the role of this logic is to account for the temporary disappearance of the vehicle trajectory due to some occlusion.
(2) For the vehicle with the departure state being negative, further judging whether the vehicle is a vehicle for parking against the regulation rules; and if the displacement of the vehicle does not change greatly within the set time, determining that the vehicle stops for a long time, and outputting the vehicle information of the vehicle.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. The video-based illegal parking detection method is characterized by comprising the following steps of:
s1, detection preparation stage: setting a illegal parking detection area, and simultaneously carrying out background modeling on a scene;
s2, target vehicle extraction stage: respectively carrying out static detection, dynamic detection and block detection on a target vehicle, and carrying out matching judgment on the vehicle detected by a current frame and a vehicle track;
s3, violation vehicle extraction stage: and extracting the illegal parking information of the updated vehicle track information, and judging whether the vehicle violates the regulations.
2. The video-based illegal parking detection method according to claim 1, characterized in that: in step S1, the illegal parking detection area is set by the user or the traffic police, and if the parking time in the area is long, the illegal parking is collected.
3. The video-based illegal parking detection method according to claim 1, characterized in that: in step S1, the background modeling uses a gaussian mixture modeling scheme to perform background modeling on the scene, and performs foreground detection on each frame.
4. The video-based illegal parking detection method according to claim 1, characterized in that: the static detection adopts a network model of yoloV3 and a large-scale model of 832 × 480 to perform full-image detection; the dynamic monitoring adopts a network model of yoloV3 and a mesoscale model of 416 to carry out local dynamic detection; the block detection is carried out before the background modeling is finished or after the background modeling is finished but the number of foreground blocks is more; matching and judging the vehicle detected by the current frame and the vehicle track, and judging whether the vehicle is the same vehicle according to the IOU and the CIOU; if the vehicle is a newly detected vehicle, new vehicle track information is created; and if the vehicle track is matched, updating the vehicle track.
5. The video-based illegal parking detection method according to claim 1, characterized in that: the step S3 is to extract the illegal parking information of the vehicle track update information obtained in the step S2, and the illegal vehicle extraction stage in the step S3 includes the steps of:
s301, judging whether the vehicle leaves;
s302, for the vehicle with the departure state being negative, whether the vehicle is a vehicle parked illegally is further judged.
6. The video-based illegal parking detection method according to claim 5, wherein the judgment process of whether the vehicle leaves in the step S301 is as follows:
if the vehicle leaves during movement, namely the track of each frame of the vehicle is displaced, and finally the vehicle leaves the parking area, the track information of the vehicle is emptied;
otherwise, judging the vehicle track disappearance time.
7. The video-based illegal parking detection method according to claim 6, wherein the process of judging the disappearance time of the vehicle track is as follows:
if the time is less than the set time, carrying out secondary detection near the position of the vehicle, matching the detected vehicle with the vehicle on the track, if the vehicle is matched with the track, setting the leaving state of the vehicle track as no, and if the vehicle is not matched with the track, continuing to carry out detection on each frame within the time less than the set time; and directly emptying the track information of the vehicle after the time is longer than the set time.
8. The video-based illegal parking detection method according to claim 5, wherein the step S302 of judging whether the vehicle is an illegal parking vehicle for the vehicle with the no leaving state comprises the following steps:
and if the displacement of the vehicle does not change greatly within the set time, determining that the vehicle stops for a long time, and outputting the vehicle information of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011044589.7A CN112183350B (en) | 2020-09-28 | 2020-09-28 | Video-based illegal parking detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011044589.7A CN112183350B (en) | 2020-09-28 | 2020-09-28 | Video-based illegal parking detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112183350A true CN112183350A (en) | 2021-01-05 |
| CN112183350B CN112183350B (en) | 2023-07-14 |
Family
ID=73947310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011044589.7A Active CN112183350B (en) | 2020-09-28 | 2020-09-28 | Video-based illegal parking detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112183350B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112861701A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Illegal parking identification method and device, electronic equipment and computer readable medium |
| CN113096394A (en) * | 2021-03-29 | 2021-07-09 | 浙江大华技术股份有限公司 | Method and device for determining object of target type, storage medium and electronic device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646544A (en) * | 2013-11-15 | 2014-03-19 | 天津天地伟业数码科技有限公司 | Vehicle-behavior analysis and identification method based on holder and camera device |
| CN107330373A (en) * | 2017-06-02 | 2017-11-07 | 重庆大学 | A kind of parking offense monitoring system based on video |
| CN107491753A (en) * | 2017-08-16 | 2017-12-19 | 电子科技大学 | A kind of parking offense detection method based on background modeling |
| CN107730903A (en) * | 2017-06-13 | 2018-02-23 | 银江股份有限公司 | Parking offense and the car vision detection system that casts anchor based on depth convolutional neural networks |
| CN109635666A (en) * | 2018-11-16 | 2019-04-16 | 南京航空航天大学 | A kind of image object rapid detection method based on deep learning |
| CN111368687A (en) * | 2020-02-28 | 2020-07-03 | 成都市微泊科技有限公司 | Sidewalk vehicle illegal parking detection method based on target detection and semantic segmentation |
-
2020
- 2020-09-28 CN CN202011044589.7A patent/CN112183350B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646544A (en) * | 2013-11-15 | 2014-03-19 | 天津天地伟业数码科技有限公司 | Vehicle-behavior analysis and identification method based on holder and camera device |
| CN107330373A (en) * | 2017-06-02 | 2017-11-07 | 重庆大学 | A kind of parking offense monitoring system based on video |
| CN107730903A (en) * | 2017-06-13 | 2018-02-23 | 银江股份有限公司 | Parking offense and the car vision detection system that casts anchor based on depth convolutional neural networks |
| CN107491753A (en) * | 2017-08-16 | 2017-12-19 | 电子科技大学 | A kind of parking offense detection method based on background modeling |
| CN109635666A (en) * | 2018-11-16 | 2019-04-16 | 南京航空航天大学 | A kind of image object rapid detection method based on deep learning |
| CN111368687A (en) * | 2020-02-28 | 2020-07-03 | 成都市微泊科技有限公司 | Sidewalk vehicle illegal parking detection method based on target detection and semantic segmentation |
Non-Patent Citations (3)
| Title |
|---|
| 王雨翔 等: "基于混合高斯模型的高速公路违章停车检测方法", 《重庆交通大学学报（自然科学版）》 * |
| 程光 等著: "《僵尸网络检测技术》", 31 October 2014, 东南大学出版社 * |
| 赵逸如 等: "基于目标检测和语义分割的人行道违规停车检测", 《现代计算机》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112861701A (en) * | 2021-02-04 | 2021-05-28 | 北京百度网讯科技有限公司 | Illegal parking identification method and device, electronic equipment and computer readable medium |
| CN112861701B (en) * | 2021-02-04 | 2023-09-22 | 北京百度网讯科技有限公司 | Illegal parking identification method, device, electronic equipment and computer readable medium |
| CN113096394A (en) * | 2021-03-29 | 2021-07-09 | 浙江大华技术股份有限公司 | Method and device for determining object of target type, storage medium and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112183350B (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022206942A1 (en) | Laser radar point cloud dynamic segmentation and fusion method based on driving safety risk field | |
| WO2020000251A1 (en) | Method for identifying video involving violation at intersection based on coordinated relay of video cameras | |
| CN100583125C (en) | Vehicle intelligent back vision method | |
| CN109584571A (en) | Intersection pre-warning and control method and system and sensing device used | |
| CN112183350A (en) | Video-based illegal parking detection method | |
| CN103914688A (en) | Urban road obstacle recognition system | |
| CN108520635B (en) | Mixed reality road display system | |
| CN105741566A (en) | Traffic information display system controlled based on intelligent traffic management system | |
| CN101968924A (en) | High-resolution image-based real-time traffic flow detection method | |
| CN107705577B (en) | Real-time detection method and system for calibrating illegal lane change of vehicle based on lane line | |
| CN114419874B (en) | Target driving safety risk early warning method based on road side sensing equipment data fusion | |
| Odeh | Management of an intelligent traffic light system by using genetic algorithm | |
| CN108665556B (en) | Road indication display method based on mixed reality and storage medium | |
| Yang et al. | Road intersection identification from crowdsourced big trace data using Mask‐RCNN | |
| CN103927875A (en) | Traffic overflowing state recognition method based on video | |
| CN108711298B (en) | Mixed reality road display method | |
| US11209830B2 (en) | Safety aware automated governance of vehicles | |
| Gupta et al. | Concurrent visual multiple lane detection for autonomous vehicles | |
| CN104988818A (en) | Intersection multi-lane calibration method based on perspective transformation | |
| CN108648480B (en) | Road isolation model display method based on mixed reality and storage medium | |
| US11847834B2 (en) | Device and method for recognizing obstacle of vehicle | |
| Yu et al. | A traffic light detection method | |
| Yu et al. | MPP: A novel algorithm for estimating vehicle space headways from a single image | |
| CN105069407A (en) | Video-based traffic flow acquisition method | |
| CN105225480A (en) | Pass through data acquisition system (DAS) in crossing, signal lamp place |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230525 Address after: No. 8, Huake 2nd Road, Haitai, Huayuan Industrial Zone (Huanwai), Binhai New Area, Tianjin, 300392 Applicant after: TIANDY TECHNOLOGIES Co.,Ltd. Applicant after: TIANJIN TIANDY INFORMATION SYSTEMS INTEGRATION Co.,Ltd. Address before: No.8, Huake 2nd Road, Haitai, Huayuan Industrial Zone (outer ring), hi tech Zone, Binhai New Area, Tianjin Applicant before: TIANDY TECHNOLOGIES Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |