CN103679707A - Binocular camera disparity map based road obstacle detection system and method - Google Patents
Binocular camera disparity map based road obstacle detection system and method Download PDFInfo
- Publication number
- CN103679707A CN103679707A CN201310619180.7A CN201310619180A CN103679707A CN 103679707 A CN103679707 A CN 103679707A CN 201310619180 A CN201310619180 A CN 201310619180A CN 103679707 A CN103679707 A CN 103679707A
- Authority
- CN
- China
- Prior art keywords
- disparity map
- module
- image
- binocular
- binocular camera
- 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
Landscapes
- Image Processing (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a binocular camera disparity map based road obstacle detection system and method. The system mainly comprises a binocular stereo rectification module, a binocular stereo matching module, a Gaussian filter module, an image cropping module and a disparity map scanning module. The binocular stereo rectification module transforms one image according to positional relation (R, T) between two cameras to enable corresponding polar lines of left and right camera images to be parallel. The binocular stereo matching module performs binocular stereo matching by adopting a map partitioning algorithm, and calculates disparity between image points corresponding to the left and right cameras to obtain a disparity map of a scene. The Gaussian filter module performs Gaussian filter on the original disparity map to obtain a fuzzy disparity map. The image cropping module introduces prior information to crop the disparity map to a certain degree. The disparity map scanning module scans the disparity map line by line to determine the position of an obstacle on the disparity map, then performs three-dimensional reconstruction on an extracted area, and determines the position of the obstacle so as to provide decision-making bases for an on-board visual system.
Description
Technical field
This invention belongs to computer vision field, is mainly that Digital Image Processing and binocular solid are rebuild.Be specifically related to a kind of road barricade quality testing examining system and detection method based on binocular camera disparity map.
Background technology
In urban road environment, how intelligent vehicle system detects the barrier occurring exactly above, determining the position (being mainly range information) between barrier and intelligent vehicle, thereby provide decision-making foundation for evading pedestrian, vehicle etc., is a very urgent and very important problem.Due to the detection of obstacles measuring method based on radar or laser, be subject to actual environment and disturb, and data volume is large, in recent years, the road barricade object detecting method based on stereoscopic vision starts to get more and more people's extensive concerning, and application is more and more.Binocular stereo vision can carry out three-dimensional reconstruction to target, but need to first obtain the matching relationship of relevant target in the camera image of left and right, and disparity map is a kind of visual representation of this relation.In complex scene, how accurately to obtain the matching relationship of target, disparity map is the major issue that computer vision field is paid close attention to always.In actual engineering application, after obtaining disparity map, also should consider how to extract the barriers such as pedestrian, vehicle, and it is carried out to three-dimensional reconstruction, calculate the distance between these barriers and camera.
Summary of the invention
For addressing the above problem, the invention provides a kind of road barricade quality testing examining system and detection method based on binocular camera disparity map, this system and method can detect the barrier occurring accurately above, thereby determine the position between barrier and intelligent vehicle, thereby for evading pedestrian, vehicle provides decision-making foundation.
For achieving the above object, the present invention is by the following technical solutions:
A road barricade quality testing examining system based on binocular camera disparity map, comprises binocular solid correction module, binocular solid matching module, gaussian filtering module, image cropping module, and disparity map scan module; Described binocular solid correction module converts piece image wherein according to the position relationship between two cameras, makes the corresponding polar curve of two camera images in left and right parallel; Described binocular solid matching module calculates the parallax between the camera corresponding diagram picture point of left and right, obtains the disparity map of scene; Described gaussian filtering module is carried out after gaussian filtering disparity map, and image cropping module is carried out cutting to filtered image, and the image of last disparity map scan module after to cutting scans by column, and determines the position of barrier according to the variation of disparity map gray scale.
In described image cropping module, store prior imformation, according to this prior imformation, filtered disparity map is carried out to cutting.
A road barricade object detecting method based on binocular camera disparity map, utilizes binocular camera to gather respectively piece image, according to the position relationship between two cameras, piece image is wherein converted, and makes the corresponding polar curve of the image that two cameras gather parallel; Then, adopt image segmentation algorithm to mate binocular camera, obtain the disparity map of scene, this disparity map is carried out to gaussian filtering, obtain the disparity map after fuzzy, then, the disparity map after fuzzy is carried out after cutting, disparity map is scanned by column to the position of acquired disturbance thing on disparity map.
Before detecting, first binocular camera is adjusted, guarantee that the optical axis of two cameras is parallel.
The local matching algorithm of employing based on similar area mates binocular camera, obtains the disparity map of scene.
Before detecting, first, under off-line state, by using gridiron pattern scaling board, adopt the plane reference algorithm of Zhang Zhengyou, obtain internal reference separately of binocular camera and the outer ginseng between two cameras, thereby realize the structure of binocular vision system.
The coupling of binocular camera image obtains corresponding match point along polar curve search and realizes.
The disparity map of described binocular camera obtains according to following methods: with polar curve, be constrained to basis, the energy function of matching relationship between structure reflection pixel, then by solving the extreme value of energy function, obtain the matching relationship between each pixel on binocular camera image, thereby realize the Stereo matching of binocular vision system, its output is the disparity map of binocular image.
Compared with prior art, the road barricade quality testing examining system and the detection method that the present invention is based on binocular camera disparity map at least have following beneficial effect: first the present invention obtains the disparity map of binocular camera by Stereo matching, then the mode scanning based on disparity map, determine conspicuousness target, and main target is carried out to three-dimensional reconstruction, thereby realize the identification of the barrier in urban road environment and detection.
Accompanying drawing explanation
Fig. 1 is overall framework of the present invention: the road barricade thing overhaul flow chart based on disparity map
Fig. 2 is the general configuration of disparity map analysis module in the present invention
Fig. 3 is a testing result of the present invention: pedestrian target, wherein, (a) and (b) be respectively the image of left and right collected by camera, and (c) disparity map for obtaining, is (d) disparity map showing by pseudo-colours, (e) is the result of detection of obstacles.
Fig. 4 is another testing result of the present invention: vehicle target, wherein, (a) and (b) be respectively the image of left and right collected by camera, and (c) disparity map for obtaining, is (d) disparity map showing by pseudo-colours, (e) is the result of detection of obstacles.
The present invention is described in more detail for the embodiment providing below in conjunction with accompanying drawing and inventor.
Embodiment
First the present invention obtains the disparity map (i.e. the disparity map of two resulting images of binocular camera) of binocular camera by Stereo matching, then the mode scanning based on disparity map, determine conspicuousness target, and main target is carried out to three-dimensional reconstruction, thereby realize the identification of the barrier in urban road environment and detection.In order to realize above-mentioned functions, the technical solution that the present invention adopts is divided into two parts, respectively:
The one, based on Stereo Matching Algorithm, obtain the disparity map of binocular camera.Specifically comprise:
Binocular solid correction module, because the optical axis of binocular camera is inner at camera, cannot directly determine, therefore between two camera optical axises, cannot guarantee strictly parallel, but be subject to the impact of the factors such as putting position, angle, have certain deviation, the position relationship between two cameras can represent with rotation matrix R and translation vector T.By introducing Epipolar geometric constraint, between the upper matching double points of two collected by cameras, there is polar curve constraint, i.e. the match point of any on left camera image, on certain straight line fixing on right camera image, this straight line is called polar curve.In order to simplify calculating, the time complexity that reduces coupling, will carry out three-dimensional correction to the image of left and right collected by camera, conventionally according to the position relationship (R between two cameras, T) piece image is wherein converted, make the corresponding polar curve of left and right camera image parallel.
Binocular solid matching module owing to binocular camera having been carried out to three-dimensional correction, thereby can directly be searched for and obtain matching relationship between points on corresponding parallel lines.In the present invention, employing figure partitioning algorithm carries out binocular solid coupling, and this algorithm is a kind of local matching algorithm based on similar area, can calculate accurately the parallax between the camera corresponding diagram picture point of left and right, thereby obtains the disparity map of binocular camera.
The 2nd, the method based on disparity map scanning is determined barrier and position thereof.Specifically comprise:
Gaussian filtering module, because Binocular Stereo Matching Algorithm exists matching error, thus on original disparity map, just there is noise to a certain degree, and may there is situation about cannot mate between some part.These factors all can affect to disparity map scanning, first original disparity map are carried out to gaussian filtering for this reason, obtain the disparity map after fuzzy, thereby realize the object that reduces noise, smoothed image.
Image cropping module, because the barrier in urban road environment is positioned on the road in the place ahead, corresponds on disparity map: barrier appears at the lower middle portion of disparity map, and the backgrounds such as sky, leaf appear at the part on the upper side of disparity map.Therefore, during actual treatment, can introduce this prior imformation, disparity map upper section is carried out to cutting to a certain degree, thereby reduce, disturb, improve the accuracy detecting.
Disparity map scan module, because disparity map has reflected the depth information in scene, target identical gray-scale value of correspondence on disparity map with same depth, therefore,, for the place ahead flat road, what in disparity map horizontal direction, present should be the shape of approximate ripple, and the increase along with the degree of depth, brightness of image reduces gradually, and in certain distance while there is barrier, the bellows-shaped of this position just significant variation can occur.By disparity map is scanned by column, just can determine the position that disparity map changes, be the position of barrier on disparity map, thereby realize the detection of barrier, then three-dimensional reconstruction is carried out in the region of extracting, just can determine the position of barrier, thereby provide decision-making foundation for vehicle-mounted vision system.
The present invention proposes a kind of effectively obstacle detection method based on disparity map.First use binocular camera, calculate disparity map, then from disparity map, extract specific objective (barrier), and rebuild.Concrete technology comprises:
1), by the inside and outside ginseng of binocular camera calibration technique, realize the structure of binocular vision system.
2) by image rectification technology, realize binocular camera image correction function.
3) by Stereo Matching Technology, realize Stereo matching function.
4), by disparity map scanning technique, realize barrier and extract and three-dimensional reconstruction.
The inside and outside ginseng of described binocular camera calibration technique, refers to by using gridiron pattern scaling board, adopts the plane reference algorithm of Zhang Zhengyou, obtains exactly internal reference separately of binocular camera and the outer ginseng between two cameras, thereby realizes the structure of binocular vision system.This technology completes under off-line state, can first calibrate binocular camera internal reference separately, and then carries out the demarcation of outer ginseng; Also can demarcate binocular camera entire system, obtain the inside and outside ginseng of binocular camera simultaneously.
Described image rectification technology, refer to the algorithm based on Bouquet, utilize and demarcate the inside and outside ginseng of the binocular camera obtaining, the correct image that binocular camera is gathered, target is to make the polar curve of binocular camera image parallel, and corresponding polar curve is adjusted on same level line.Adopt the binocular image after image rectification technology, because corresponding polar curve has passed through adjustment, thereby can along polar curve search, obtain corresponding match point easily, realize the coupling of binocular camera image.
Described Stereo Matching Technology, refer to the algorithm based on Graph Cut, with polar curve, be constrained to basis, adopt the relevant thought of non-directed graph in graph theory, structure can reflect the energy function of matching relationship between pixel, then by solving the extreme value of energy function, obtains on binocular camera image, matching relationship between each pixel, thus realize the Stereo matching of binocular vision system.This technology export is the disparity map of binocular image, and disparity map has shown the matching relationship between binocular image intuitively.
Described disparity map scanning technique, refers to disparity map is carried out to column scan, determines the region of parallax generation marked change in disparity map.Because disparity map has reflected the depth information of scene, therefore, for the disparity map on desirable clear road, the gray-scale value on column direction should be even increasing or decreasing, does not have the region that marked change occurs.And while there is barrier on road, disparity map is no longer just even variation on column direction, so scan by disparity map, just can determine the region of gray-scale value generation marked change in disparity map, thereby realizes the extraction of barrier.By adjusting gray-value variation threshold value, just can extract the barrier of different depth scope.For the barrier region extracting, calculate it with respect to the degree of depth of binocular vision system, thereby realize the three-dimensional reconstruction to barrier.
According to technique scheme, provided following embodiment.
Fig. 1 has provided the overall flow figure of the road barricade quality testing survey technology based on binocular camera disparity map.Comprise binocular camera image capture module, binocular correction module, Stereo matching module, disparity map scan module, finally provide the barrier and the corresponding depth information that in image, exist.General frame is a kind of serial structure, and every two field picture that binocular camera is collected is analyzed simultaneously, finally provides barrier is carried out to the result after three-dimensional reconstruction.
Fig. 2 has provided the concrete implementing procedure of disparity map scan module.For the disparity map obtaining through Stereo Matching Technology, first carry out Gaussian Blur, to reduce noise level, then according to prior imformation, disparity map is carried out to cutting to a certain degree, to reduce complexity and the time loss of disparity map scanning, finally disparity map is scanned by column, obtain testing result.
Fig. 3 has provided a testing result of the road barricade quality testing survey technology based on binocular camera disparity map, and in image, major obstacle thing is pedestrian target.In figure, the first row is respectively the image of left and right collected by camera, the disparity map that the second behavior calculates and the disparity map showing by pseudo-colours, the result that last column is detection of obstacles.From figure, obviously find out, this technology can realize and detecting the barrier on road, and can carry out three-dimensional reconstruction to it, provides the depth information of barrier.
Fig. 4 has provided another testing result of the road barricade quality testing survey technology based on binocular camera disparity map, and in image, major obstacle thing is vehicle target.In figure, the first row is respectively the image of left and right collected by camera, the disparity map that the second behavior calculates and the disparity map showing by pseudo-colours, the result that last column is detection of obstacles.
Claims (8)
1. the road barricade quality testing examining system based on binocular camera disparity map, is characterized in that: comprise binocular solid correction module, binocular solid matching module, gaussian filtering module, image cropping module, and disparity map scan module; Described binocular solid correction module converts piece image wherein according to the position relationship between two cameras, makes the corresponding polar curve of two camera images in left and right parallel; Described binocular solid matching module calculates the parallax between the camera corresponding diagram picture point of left and right, obtains the disparity map of binocular camera; Described gaussian filtering module is carried out after gaussian filtering disparity map, and image cropping module is carried out cutting to filtered image, and the image of last disparity map scan module after to cutting scans by column, and determines the position of barrier according to the variation of disparity map gray scale.
2. detection system as claimed in claim 1, is characterized in that: in described image cropping module, store prior imformation, according to this prior imformation, filtered disparity map is carried out to cutting.
3. the road barricade object detecting method based on binocular camera disparity map, it is characterized in that: utilize binocular camera to gather respectively piece image, according to the position relationship between two cameras, piece image is wherein converted, make the corresponding polar curve of the image that two cameras gather parallel; Then, adopt image segmentation algorithm to mate binocular camera, obtain the disparity map of binocular camera, this disparity map is carried out to gaussian filtering, obtain the disparity map after fuzzy, then, the disparity map after fuzzy is carried out after cutting, disparity map is scanned by column to the position of acquired disturbance thing on disparity map.
4. detection method as claimed in claim 3, is characterized in that: before detecting, first binocular camera is adjusted, guaranteed that the optical axis of two cameras is parallel.
5. detection method as claimed in claim 3, is characterized in that: adopt the local matching algorithm based on similar area to mate binocular camera, obtain the disparity map of binocular camera.
6. detection method as claimed in claim 3, it is characterized in that: before detecting, first under off-line state, by using gridiron pattern scaling board, adopt the plane reference algorithm of Zhang Zhengyou, obtain internal reference separately of binocular camera and the outer ginseng between two cameras, thereby realize the structure of binocular vision system.
7. detection method as claimed in claim 3, is characterized in that: the coupling of binocular camera image obtains corresponding match point along polar curve search and realizes.
8. detection method as claimed in claim 3, it is characterized in that: the disparity map of described binocular camera obtains according to following methods: with polar curve, be constrained to basis, the energy function of matching relationship between structure reflection pixel, then by solving the extreme value of energy function, obtain the matching relationship between each pixel on binocular camera image, thereby realize the Stereo matching of binocular vision system, its output is the disparity map of binocular image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310619180.7A CN103679707A (en) | 2013-11-26 | 2013-11-26 | Binocular camera disparity map based road obstacle detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310619180.7A CN103679707A (en) | 2013-11-26 | 2013-11-26 | Binocular camera disparity map based road obstacle detection system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103679707A true CN103679707A (en) | 2014-03-26 |
Family
ID=50317158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310619180.7A Pending CN103679707A (en) | 2013-11-26 | 2013-11-26 | Binocular camera disparity map based road obstacle detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103679707A (en) |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104121891A (en) * | 2014-07-07 | 2014-10-29 | 北京理工大学 | Five-camera-based intelligent robot visual device |
| CN106156748A (en) * | 2016-07-22 | 2016-11-23 | 浙江零跑科技有限公司 | Traffic scene participant's recognition methods based on vehicle-mounted binocular camera |
| CN106228110A (en) * | 2016-07-07 | 2016-12-14 | 浙江零跑科技有限公司 | A kind of barrier based on vehicle-mounted binocular camera and drivable region detection method |
| CN106327465A (en) * | 2015-06-18 | 2017-01-11 | 深圳超多维光电子有限公司 | Method and device for determining object position |
| CN106529495A (en) * | 2016-11-24 | 2017-03-22 | 腾讯科技（深圳）有限公司 | Obstacle detection method of aircraft and device |
| CN106683174A (en) * | 2016-12-23 | 2017-05-17 | 上海斐讯数据通信技术有限公司 | 3D reconstruction method, apparatus of binocular visual system, and binocular visual system |
| CN106708084A (en) * | 2016-11-24 | 2017-05-24 | 中国科学院自动化研究所 | Method for automatically detecting and avoiding obstacles for unmanned aerial vehicle under complicated environments |
| CN107091643A (en) * | 2017-06-07 | 2017-08-25 | 旗瀚科技有限公司 | A kind of indoor navigation method based on many 3D structure lights camera splicings |
| CN107169418A (en) * | 2017-04-18 | 2017-09-15 | 海信集团有限公司 | A kind of obstacle detection method and device |
| CN107590444A (en) * | 2017-08-23 | 2018-01-16 | 深圳市易成自动驾驶技术有限公司 | Detection method, device and the storage medium of static-obstacle thing |
| CN107702674A (en) * | 2017-08-23 | 2018-02-16 | 六六房车有限公司 | A kind of vehicle travels limit for height disorder detection method |
| 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 |
| CN107909009A (en) * | 2017-10-27 | 2018-04-13 | 北京中科慧眼科技有限公司 | A kind of obstacle detection method and device based on road surface study |
| CN108292441A (en) * | 2015-12-04 | 2018-07-17 | 奥托立夫开发公司 | The method of vision system and control vision system for motor vehicles |
| CN108520536A (en) * | 2018-03-27 | 2018-09-11 | 海信集团有限公司 | A kind of generation method of disparity map, device and terminal |
| CN109523528A (en) * | 2018-11-12 | 2019-03-26 | 西安交通大学 | A kind of transmission line of electricity extracting method based on unmanned plane binocular vision SGC algorithm |
| CN109522847A (en) * | 2018-11-20 | 2019-03-26 | 中车株洲电力机车有限公司 | A kind of track and road barricade object detecting method based on depth map |
| CN109753858A (en) * | 2017-11-07 | 2019-05-14 | 北京中科慧眼科技有限公司 | A kind of road barricade object detecting method and device based on binocular vision |
| CN110490117A (en) * | 2019-08-14 | 2019-11-22 | 智慧互通科技有限公司 | A kind of Parking based on image depth information determines method and system |
| CN110569704A (en) * | 2019-05-11 | 2019-12-13 | 北京工业大学 | Multi-strategy self-adaptive lane line detection method based on stereoscopic vision |
| CN110738618A (en) * | 2019-10-14 | 2020-01-31 | 河海大学常州校区 | irregular windrow volume measurement method based on binocular camera |
| WO2020134229A1 (en) * | 2018-12-29 | 2020-07-02 | 北京市商汤科技开发有限公司 | Image processing method, device, electronic apparatus, and computer readable storage medium |
| CN111738971A (en) * | 2019-03-19 | 2020-10-02 | 北京伟景智能科技有限公司 | Circuit board stereo scanning detection method based on line laser binocular stereo vision |
| CN111951339A (en) * | 2020-07-15 | 2020-11-17 | 苏州易航远智智能科技有限公司 | Image processing method for performing parallax calculation by using heterogeneous binocular cameras |
| CN112419389A (en) * | 2020-11-25 | 2021-02-26 | 中科融合感知智能研究院(苏州工业园区)有限公司 | Method and device for realizing binocular increment parallax matching algorithm |
| US10942529B2 (en) | 2016-11-24 | 2021-03-09 | Tencent Technology (Shenzhen) Company Limited | Aircraft information acquisition method, apparatus and device |
| CN112686835A (en) * | 2019-10-18 | 2021-04-20 | 丰田自动车株式会社 | Road obstacle detection device, method and computer-readable storage medium |
| CN112700486A (en) * | 2019-10-23 | 2021-04-23 | 阿里巴巴集团控股有限公司 | Method and device for estimating depth of road lane line in image |
| CN112758067A (en) * | 2021-01-22 | 2021-05-07 | 北京中科慧眼科技有限公司 | Emergency braking method and system based on binocular stereo camera and intelligent terminal |
| CN113686264A (en) * | 2021-08-02 | 2021-11-23 | 中国科学院长春光学精密机械与物理研究所 | Three-dimensional measurement method and system based on polar line geometry |
| CN113781543A (en) * | 2021-11-10 | 2021-12-10 | 北京中科慧眼科技有限公司 | Binocular camera-based height limiting device detection method and system and intelligent terminal |
| CN114241047A (en) * | 2021-12-02 | 2022-03-25 | 广西大学 | Binocular vision identification and positioning method for garden hedgerow trimming |
| CN117689718A (en) * | 2024-02-02 | 2024-03-12 | 北京友友天宇系统技术有限公司 | Visual quick three-dimensional positioning method and device for target object |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020061132A1 (en) * | 2000-11-22 | 2002-05-23 | Nec Corporation | Stereo image processing apparatus and method of processing stereo image |
| CN101537618A (en) * | 2008-12-19 | 2009-09-23 | 北京理工大学 | Visual system for ball picking robot in stadium |
| CN101557534A (en) * | 2009-05-19 | 2009-10-14 | 无锡景象数字技术有限公司 | Method for generating disparity map from video close frames |
| CN102024275A (en) * | 2010-12-21 | 2011-04-20 | 南京大学 | Automatic ticket checking device |
| CN102426704A (en) * | 2011-10-28 | 2012-04-25 | 清华大学深圳研究生院 | Rapid detection method for salient objects |
| CN103123722A (en) * | 2011-11-18 | 2013-05-29 | 株式会社理光 | Road object detection method and system |
| CN103198477A (en) * | 2013-03-25 | 2013-07-10 | 沈阳理工大学 | Apple fruitlet bagging robot visual positioning method |
| CN103231708A (en) * | 2013-04-12 | 2013-08-07 | 安徽工业大学 | Intelligent vehicle obstacle avoiding method based on binocular vision |
-
2013
- 2013-11-26 CN CN201310619180.7A patent/CN103679707A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020061132A1 (en) * | 2000-11-22 | 2002-05-23 | Nec Corporation | Stereo image processing apparatus and method of processing stereo image |
| CN101537618A (en) * | 2008-12-19 | 2009-09-23 | 北京理工大学 | Visual system for ball picking robot in stadium |
| CN101557534A (en) * | 2009-05-19 | 2009-10-14 | 无锡景象数字技术有限公司 | Method for generating disparity map from video close frames |
| CN102024275A (en) * | 2010-12-21 | 2011-04-20 | 南京大学 | Automatic ticket checking device |
| CN102426704A (en) * | 2011-10-28 | 2012-04-25 | 清华大学深圳研究生院 | Rapid detection method for salient objects |
| CN103123722A (en) * | 2011-11-18 | 2013-05-29 | 株式会社理光 | Road object detection method and system |
| CN103198477A (en) * | 2013-03-25 | 2013-07-10 | 沈阳理工大学 | Apple fruitlet bagging robot visual positioning method |
| CN103231708A (en) * | 2013-04-12 | 2013-08-07 | 安徽工业大学 | Intelligent vehicle obstacle avoiding method based on binocular vision |
Cited By (49)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104121891B (en) * | 2014-07-07 | 2016-04-27 | 北京理工大学 | Based on the intelligent robot sighting device of 5 cameras |
| CN104121891A (en) * | 2014-07-07 | 2014-10-29 | 北京理工大学 | Five-camera-based intelligent robot visual device |
| CN106327465B (en) * | 2015-06-18 | 2019-08-06 | 深圳超多维光电子有限公司 | Object space determines method and device |
| CN106327465A (en) * | 2015-06-18 | 2017-01-11 | 深圳超多维光电子有限公司 | Method and device for determining object position |
| CN108292441B (en) * | 2015-12-04 | 2022-05-24 | 维宁尔瑞典公司 | Vision system for a motor vehicle and method for controlling a vision system |
| CN108292441A (en) * | 2015-12-04 | 2018-07-17 | 奥托立夫开发公司 | The method of vision system and control vision system for motor vehicles |
| CN106228110A (en) * | 2016-07-07 | 2016-12-14 | 浙江零跑科技有限公司 | A kind of barrier based on vehicle-mounted binocular camera and drivable region detection method |
| CN106228110B (en) * | 2016-07-07 | 2019-09-20 | 浙江零跑科技有限公司 | A kind of barrier and drivable region detection method based on vehicle-mounted binocular camera |
| CN106156748A (en) * | 2016-07-22 | 2016-11-23 | 浙江零跑科技有限公司 | Traffic scene participant's recognition methods based on vehicle-mounted binocular camera |
| CN106708084A (en) * | 2016-11-24 | 2017-05-24 | 中国科学院自动化研究所 | Method for automatically detecting and avoiding obstacles for unmanned aerial vehicle under complicated environments |
| CN106708084B (en) * | 2016-11-24 | 2019-08-02 | 中国科学院自动化研究所 | The automatic detection of obstacles of unmanned plane and barrier-avoiding method under complex environment |
| CN106529495A (en) * | 2016-11-24 | 2017-03-22 | 腾讯科技（深圳）有限公司 | Obstacle detection method of aircraft and device |
| US10942529B2 (en) | 2016-11-24 | 2021-03-09 | Tencent Technology (Shenzhen) Company Limited | Aircraft information acquisition method, apparatus and device |
| CN106683174A (en) * | 2016-12-23 | 2017-05-17 | 上海斐讯数据通信技术有限公司 | 3D reconstruction method, apparatus of binocular visual system, and binocular visual system |
| CN107169418A (en) * | 2017-04-18 | 2017-09-15 | 海信集团有限公司 | A kind of obstacle detection method and device |
| CN107091643A (en) * | 2017-06-07 | 2017-08-25 | 旗瀚科技有限公司 | A kind of indoor navigation method based on many 3D structure lights camera splicings |
| CN107702674A (en) * | 2017-08-23 | 2018-02-16 | 六六房车有限公司 | A kind of vehicle travels limit for height disorder detection method |
| CN107590444A (en) * | 2017-08-23 | 2018-01-16 | 深圳市易成自动驾驶技术有限公司 | Detection method, device and the storage medium of static-obstacle thing |
| CN107590444B (en) * | 2017-08-23 | 2020-05-22 | 深圳市易成自动驾驶技术有限公司 | Method and device for detecting static obstacle and storage medium |
| CN107909009A (en) * | 2017-10-27 | 2018-04-13 | 北京中科慧眼科技有限公司 | A kind of obstacle detection method and device based on road surface study |
| 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 |
| CN107909009B (en) * | 2017-10-27 | 2021-09-17 | 北京中科慧眼科技有限公司 | Obstacle detection method and device based on road surface learning |
| CN109753858A (en) * | 2017-11-07 | 2019-05-14 | 北京中科慧眼科技有限公司 | A kind of road barricade object detecting method and device based on binocular vision |
| CN108520536A (en) * | 2018-03-27 | 2018-09-11 | 海信集团有限公司 | A kind of generation method of disparity map, device and terminal |
| CN108520536B (en) * | 2018-03-27 | 2022-01-11 | 海信集团有限公司 | Disparity map generation method and device and terminal |
| CN109523528B (en) * | 2018-11-12 | 2021-07-13 | 西安交通大学 | Power transmission line extraction method based on unmanned aerial vehicle binocular vision SGC algorithm |
| CN109523528A (en) * | 2018-11-12 | 2019-03-26 | 西安交通大学 | A kind of transmission line of electricity extracting method based on unmanned plane binocular vision SGC algorithm |
| CN109522847A (en) * | 2018-11-20 | 2019-03-26 | 中车株洲电力机车有限公司 | A kind of track and road barricade object detecting method based on depth map |
| WO2020134229A1 (en) * | 2018-12-29 | 2020-07-02 | 北京市商汤科技开发有限公司 | Image processing method, device, electronic apparatus, and computer readable storage medium |
| CN111738971A (en) * | 2019-03-19 | 2020-10-02 | 北京伟景智能科技有限公司 | Circuit board stereo scanning detection method based on line laser binocular stereo vision |
| CN111738971B (en) * | 2019-03-19 | 2024-02-27 | 北京伟景智能科技有限公司 | Circuit board stereoscopic scanning detection method based on line laser binocular stereoscopic vision |
| CN110569704A (en) * | 2019-05-11 | 2019-12-13 | 北京工业大学 | Multi-strategy self-adaptive lane line detection method based on stereoscopic vision |
| CN110569704B (en) * | 2019-05-11 | 2022-11-22 | 北京工业大学 | Multi-strategy self-adaptive lane line detection method based on stereoscopic vision |
| CN110490117A (en) * | 2019-08-14 | 2019-11-22 | 智慧互通科技有限公司 | A kind of Parking based on image depth information determines method and system |
| CN110738618A (en) * | 2019-10-14 | 2020-01-31 | 河海大学常州校区 | irregular windrow volume measurement method based on binocular camera |
| CN110738618B (en) * | 2019-10-14 | 2023-05-16 | 河海大学常州校区 | Irregular stacking volume measuring method based on binocular camera |
| CN112686835B (en) * | 2019-10-18 | 2024-05-14 | 丰田自动车株式会社 | Road obstacle detection device, method and computer readable storage medium |
| CN112686835A (en) * | 2019-10-18 | 2021-04-20 | 丰田自动车株式会社 | Road obstacle detection device, method and computer-readable storage medium |
| CN112700486B (en) * | 2019-10-23 | 2024-05-07 | 浙江菜鸟供应链管理有限公司 | Method and device for estimating depth of road surface lane line in image |
| CN112700486A (en) * | 2019-10-23 | 2021-04-23 | 阿里巴巴集团控股有限公司 | Method and device for estimating depth of road lane line in image |
| CN111951339A (en) * | 2020-07-15 | 2020-11-17 | 苏州易航远智智能科技有限公司 | Image processing method for performing parallax calculation by using heterogeneous binocular cameras |
| CN112419389B (en) * | 2020-11-25 | 2024-01-23 | 中科融合感知智能研究院(苏州工业园区)有限公司 | Method and device for realizing binocular incremental parallax matching algorithm |
| CN112419389A (en) * | 2020-11-25 | 2021-02-26 | 中科融合感知智能研究院(苏州工业园区)有限公司 | Method and device for realizing binocular increment parallax matching algorithm |
| CN112758067A (en) * | 2021-01-22 | 2021-05-07 | 北京中科慧眼科技有限公司 | Emergency braking method and system based on binocular stereo camera and intelligent terminal |
| CN113686264B (en) * | 2021-08-02 | 2022-08-02 | 中国科学院长春光学精密机械与物理研究所 | Three-dimensional measurement method and system based on polar line geometry |
| CN113686264A (en) * | 2021-08-02 | 2021-11-23 | 中国科学院长春光学精密机械与物理研究所 | Three-dimensional measurement method and system based on polar line geometry |
| CN113781543A (en) * | 2021-11-10 | 2021-12-10 | 北京中科慧眼科技有限公司 | Binocular camera-based height limiting device detection method and system and intelligent terminal |
| CN114241047A (en) * | 2021-12-02 | 2022-03-25 | 广西大学 | Binocular vision identification and positioning method for garden hedgerow trimming |
| CN117689718A (en) * | 2024-02-02 | 2024-03-12 | 北京友友天宇系统技术有限公司 | Visual quick three-dimensional positioning method and device for target object |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103679707A (en) | Binocular camera disparity map based road obstacle detection system and method | |
| CA3157194C (en) | Systems and methods for augmentation of sensor systems and imaging systems with polarization | |
| CN105225482B (en) | Vehicle detecting system and method based on binocular stereo vision | |
| CN107738612B (en) | Automatic parking space detection and identification system based on panoramic vision auxiliary system | |
| EP3438777B1 (en) | Method, apparatus and computer program for a vehicle | |
| CN101887589B (en) | Stereoscopic vision-based real low-texture image reconstruction method | |
| CN110569704A (en) | Multi-strategy self-adaptive lane line detection method based on stereoscopic vision | |
| CN109472831A (en) | Obstacle recognition range-measurement system and method towards road roller work progress | |
| KR101285106B1 (en) | Obstacle detection method using image data fusion and apparatus | |
| CN103868460A (en) | Parallax optimization algorithm-based binocular stereo vision automatic measurement method | |
| CN110288659B (en) | Depth imaging and information acquisition method based on binocular vision | |
| CN110197173B (en) | Road edge detection method based on binocular vision | |
| CN104063882B (en) | Vehicle video speed measuring method based on binocular camera | |
| WO2024114119A1 (en) | Sensor fusion method based on binocular camera guidance | |
| CN111476762B (en) | Obstacle detection method and device of inspection equipment and inspection equipment | |
| CN109961417A (en) | Image processing method, device and mobile device control method | |
| CN113643345A (en) | Multi-view road intelligent identification method based on double-light fusion | |
| Goga et al. | Fusing semantic labeled camera images and 3D LiDAR data for the detection of urban curbs | |
| CN114820474A (en) | Train wheel defect detection method based on three-dimensional information | |
| CN116029996A (en) | Stereo matching method and device and electronic equipment | |
| CN114973028A (en) | Aerial video image real-time change detection method and system | |
| US20210150745A1 (en) | Image processing method, device, electronic apparatus, and computer readable storage medium | |
| KR100508763B1 (en) | System for detecting and recognizing a car plate area by using stereo vision and method thereof | |
| CN114463303A (en) | Road target detection method based on fusion of binocular camera and laser radar | |
| Raguraman et al. | Intelligent drivable area detection system using camera and LiDAR sensor for autonomous vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | 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 |
Application publication date: 20140326 |
|
| RJ01 | Rejection of invention patent application after publication |