CN103714533A - Method for automatically detecting obstacles based on binocular vision - Google Patents
Method for automatically detecting obstacles based on binocular vision Download PDFInfo
- Publication number
- CN103714533A CN103714533A CN201310658205.4A CN201310658205A CN103714533A CN 103714533 A CN103714533 A CN 103714533A CN 201310658205 A CN201310658205 A CN 201310658205A CN 103714533 A CN103714533 A CN 103714533A
- Authority
- CN
- China
- Prior art keywords
- disparity map
- binocular vision
- image information
- barrier
- relation line
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method for automatically detecting obstacles based on binocular vision. The method comprises the following steps: receiving image information from two paths of binocular vision cameras; comparing image information that identical time codes of the received image information correspond to, and obtaining a disparity map; and obtaining related lines of the disparity map according to the disparity map, and obtaining the position information of an obstacle. The method provided by the invention can utilize binocular vision to simulate eyes of humans and the process of stereoscopic perception of humans, and automatically detect the obstacles for road driving.
Description
Technical field
The present invention relates to a kind of method that barrier detects automatically, a kind of method that particularly barrier based on binocular vision detects automatically.
Background technology
In recent years, along with construction and socioeconomic development, the especially growth of automobile quantity of China's quickening road transport infrastructure, Road network capacity can not meet the needs that the volume of traffic increases, particularly urban traffic congestion and obstruction are very serious, cause road traffic accident continuous rise.On the one hand, continue to add the development of rope-race network infrastructure, on the other hand, the fast development of infotech, for road traffic problem provides the more solution of reliable and economic, Europe, other developed countries such as U.S. design function path that begins one's study from the eighties in 20th century, the aspects such as intelligent vehicle and Road Transportation process, what form transportation modernization can only traffic system (Intellingent Transportation System, be called for short ITS), the application of ITS can improve road ability greatly, road traffic accident also declines to some extent, alleviate traffic pressure, and speed is entered economic development, guarantee the name masses' life and the safety of property.
At present, detection of obstacles, as study hotspot that can only field of transportation system, realizes safe driving of vehicle both at home and abroad.Remind in time the danger of driver's vehicle periphery, can reduce carelessness or the tired collision accident of printing and distributing due to driver, improve traffic safety.Particularly since nineteen eighty, the traffic hazard on highway increases year by year, and the reason of a lot of accident development and driver's fatigue driving or hypervelocity exist direct relation.Therefore, in order to reduce the generation of road traffic accident, most countries is all carried out a lot of policies, and to reduce the generation of driver's fatigue phenomenon, but actual policy does not produce extraordinary effect, does not especially also deal with problems in itself.Therefore, minimizing traffic hazard generation is imperative.And in many traffic hazards, more by thinking what factor caused, as driver's irregular driving, the fatigue of driving over a long distance, the restriction of human response's ability, only depends on standard driver's behavior more limitedly to overcome, and auxiliary driving of automotive safety is the fundamental way addressing these problems.
Binocular vision is an important branch of computer vision, and binocular vision can apish eyes and the process of mankind's stereoscopic vision perception, are one of core themes of computer vision research.In recent years, binocular vision technology in detection of obstacles, industrial automation, produce, can only safety-protection system etc. field be widely used.
Inventor finds in the process of research, adopt binocular vision technology to obtain left and right image, it is being carried out to polar curve correction and adopting the solid matching method of belief propagation to obtain on the basis of dense disparity map, the detection of obstacles algorithm of research based on U-V disparity map, and improve for the shortcoming of the barrier object detection method of U-parallax after first V-parallax, V-parallax barrier object detection method after U-parallax has been proposed after a kind of first U-parallax, first by disparity map, calculate U-disparity map, road parallax in U-disparity map one place's disparity map of employing bivalve value, disparity map after one place's road parallax is calculated respectively to V-disparity map and U-disparity map, on V-disparity map and U-disparity map, extract respectively barrier relation line, the relation line that employing gets carries out barrier location, the method has better detection effect.
Summary of the invention
The invention provides a kind of method that barrier based on binocular vision detects automatically, it can overcome the deficiencies in the prior art, can utilize the process of the three-dimensional perception of the apish eyes of binocular vision and the mankind, and the barrier of road driving is detected automatically.
The method that a kind of barrier based on binocular vision that the embodiment of the present invention provides detects automatically, comprises the following steps:
Reception is from the image information of two-way binocular vision video camera;
The image information that the identical timing code of the described image information receiving is corresponding contrasts, and obtains disparity map;
According to described disparity map, obtain disparity map relation line, obtain the positional information of barrier.
Described image information comprises V-disparity map and U-disparity map.
Described U-disparity map obtains prior to described V-disparity map.
The described disparity map relation line that obtains, comprises the step that the relation line of V-disparity map and U-disparity map is extracted.
Described disparity map relation line represents the information in real scene.
Adopt binocular vision technology to obtain left and right image, it is being carried out to polar curve correction and adopting the solid matching method of belief propagation to obtain on the basis of dense disparity map, the detection of obstacles algorithm of research based on U-V disparity map, and improve for the shortcoming of the barrier object detection method of U-parallax after first V-parallax, V-parallax barrier object detection method after U-parallax has been proposed after a kind of first U-parallax, first by disparity map, calculate U-disparity map, road parallax in U-disparity map one place's disparity map of employing bivalve value, disparity map after one place's road parallax is calculated respectively to V-disparity map and U-disparity map, on V-disparity map and U-disparity map, extract respectively barrier relation line, the relation line that employing gets carries out barrier location, the method has better detection effect.
The method that a kind of barrier based on binocular vision provided by the invention detects automatically, by utilizing the process of the three-dimensional perception of the apish eyes of binocular vision and the mankind, detects automatically to the barrier of road driving.
?
Embodiment
Below the embodiment of the embodiment of the present invention is described in detail:
The method that a kind of barrier based on binocular vision that the embodiment of the present invention provides detects automatically, comprises the following steps:
S101, receive the image information from two-way binocular vision video camera;
S102, image information corresponding to the identical timing code of the described image information receiving contrasted, obtain disparity map;
S103, according to described disparity map, obtain disparity map relation line, obtain the positional information of barrier.
S1011, described image information comprise V-disparity map and U-disparity map.
S1012, described U-disparity map obtain prior to described V-disparity map.
S1013, described in obtain disparity map relation line, comprise the step that the relation line of V-disparity map and U-disparity map is extracted.
S1014, described disparity map relation line represent the information in real scene.
Adopt binocular vision technology to obtain left and right image, it is being carried out to polar curve correction and adopting the solid matching method of belief propagation to obtain on the basis of dense disparity map, the detection of obstacles algorithm of research based on U-V disparity map, and improve for the shortcoming of the barrier object detection method of U-parallax after first V-parallax, V-parallax barrier object detection method after U-parallax has been proposed after a kind of first U-parallax, first by disparity map, calculate U-disparity map, road parallax in U-disparity map one place's disparity map that employing bivalve is planted, disparity map after one place's road parallax is calculated respectively to V-disparity map and U-disparity map, on V-disparity map and U-disparity map, extract respectively barrier relation line, the relation line that employing gets carries out barrier location, the method has better detection effect.
The method that a kind of barrier based on binocular vision provided by the invention detects automatically, by utilizing the process of the three-dimensional perception of the apish eyes of binocular vision and the mankind, detects automatically to the barrier of road driving.
Through the above description of the embodiments, those skilled in the art can be well understood to the mode that the present invention can add essential general hardware platform by software and realize, and can certainly pass through hardware, but in a lot of situation, the former is better embodiment.Understanding based on such, the part that technical scheme of the present invention contributes to prior art in essence in other words can embody with the form of software product, this computer software product is stored in a storage medium, comprise that some instructions are with so that a computer equipment (can be personal computer, server, or the network equipment etc.) carry out the method described in each embodiment of the present invention.
Disclosed is above only several specific embodiment of the present invention, and still, the present invention is not limited thereto, and the changes that any person skilled in the art can think of all should fall into protection scope of the present invention.
Claims (5)
1. the method that the barrier based on binocular vision detects automatically, is characterized in that, comprises the following steps:
Reception is from the image information of two-way binocular vision video camera;
The image information that the identical timing code of the described image information receiving is corresponding contrasts, and obtains disparity map;
According to described disparity map, obtain disparity map relation line, obtain the positional information of barrier.
2. the method that a kind of barrier based on binocular vision according to claim 1 detects automatically, is characterized in that, described image information comprises V-disparity map and U-disparity map.
3. the method that a kind of barrier based on binocular vision according to claim 2 detects automatically, is characterized in that, described U-disparity map obtains prior to described V-disparity map.
4. the method that a kind of barrier based on binocular vision according to claim 3 automatically detects, is characterized in that, described in obtain disparity map relation line, comprise the step that the relation line of V-disparity map and U-disparity map is extracted.
5. the method that a kind of barrier based on binocular vision according to claim 1 detects automatically, is characterized in that, described disparity map relation line represents the information in real scene.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310658205.4A CN103714533A (en) | 2013-12-09 | 2013-12-09 | Method for automatically detecting obstacles based on binocular vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310658205.4A CN103714533A (en) | 2013-12-09 | 2013-12-09 | Method for automatically detecting obstacles based on binocular vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103714533A true CN103714533A (en) | 2014-04-09 |
Family
ID=50407476
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310658205.4A Pending CN103714533A (en) | 2013-12-09 | 2013-12-09 | Method for automatically detecting obstacles based on binocular vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103714533A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107909010A (en) * | 2017-10-27 | 2018-04-13 | 北京中科慧眼科技有限公司 | A kind of road barricade object detecting method and device |
CN110667474A (en) * | 2018-07-02 | 2020-01-10 | 北京四维图新科技股份有限公司 | General obstacle detection method and device and automatic driving system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102435174A (en) * | 2011-11-01 | 2012-05-02 | 清华大学 | Method and device for detecting barrier based on hybrid binocular vision |
CN103231708A (en) * | 2013-04-12 | 2013-08-07 | 安徽工业大学 | Intelligent vehicle obstacle avoiding method based on binocular vision |
-
2013
- 2013-12-09 CN CN201310658205.4A patent/CN103714533A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102435174A (en) * | 2011-11-01 | 2012-05-02 | 清华大学 | Method and device for detecting barrier based on hybrid binocular vision |
CN103231708A (en) * | 2013-04-12 | 2013-08-07 | 安徽工业大学 | Intelligent vehicle obstacle avoiding method based on binocular vision |
Non-Patent Citations (2)
Title |
---|
王荣本等: "《基于双目视觉的智能车辆障碍物探测技术研究》", 《中国图象图形学报》 * |
陈雪等: "《基于双目立体视觉的障碍物检测方法》", 《软件导刊》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107909010A (en) * | 2017-10-27 | 2018-04-13 | 北京中科慧眼科技有限公司 | A kind of road barricade object detecting method and device |
CN110667474A (en) * | 2018-07-02 | 2020-01-10 | 北京四维图新科技股份有限公司 | General obstacle detection method and device and automatic driving system |
CN110667474B (en) * | 2018-07-02 | 2021-02-26 | 北京四维图新科技股份有限公司 | General obstacle detection method and device and automatic driving system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103714532A (en) | Method for automatically detecting obstacles based on binocular vision | |
KR102225006B1 (en) | Vehicle braking energy recovery method and device | |
US11345335B1 (en) | Handling sensor occlusions for autonomous vehicles | |
CN103763517B (en) | Vehicle-mounted around view display method and system | |
HRP20201328T1 (en) | Image decoding apparatus | |
US20200066147A1 (en) | Method, system and emergency control device for traffic management of autonomous vehicles in emergency situations | |
CN103712602A (en) | Binocular vision based method for automatic detection of road obstacle | |
CN203134149U (en) | Vehicle auxiliary driving system based on different wave band imaging fusion image processing | |
CN103144633A (en) | Rear end collision early warning method based on vehicular networking technology | |
CN103489314B (en) | Real-time road display packing and device | |
CN103696652A (en) | Electric folding door and protecting method and system thereof | |
CN104417553A (en) | Vehicle safety control apparatus and method using cameras | |
CN106274644A (en) | A kind of automobiles indicator lamp control method and device | |
CN105185141A (en) | Vehicle automatic driving guidance method based on gravitational field | |
Hayashi et al. | Development of pre-crash safety system with pedestrian collision avoidance assist | |
CN103714533A (en) | Method for automatically detecting obstacles based on binocular vision | |
CN106961583A (en) | Dual camera outdoor scene intelligent travelling crane method and system | |
CN109598927A (en) | Right of way distribution method, system, equipment and storage medium based on V2X technology | |
CN105616116A (en) | Intelligent blind guiding rod | |
CN103729840A (en) | Automatic coach barrier detection method based on binocular vision | |
CN107878380A (en) | A kind of automobile car slipping based reminding method and device | |
WO2011083929A3 (en) | Method, system, and computer-readable recording medium for providing information on an object using a viewing frustum | |
CN104318761B (en) | Highway-scene-based detection and vehicle detection tracking optimization method | |
CN110712699B (en) | Rear projection method for bicycle and related product | |
CN103377372A (en) | Looking-around composite graph overlapping region dividing method and looking-around composite graph representing method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20140409 |