CN108592885A - A kind of list binocular fusion positioning distance measuring algorithm - Google Patents
A kind of list binocular fusion positioning distance measuring algorithm Download PDFInfo
- Publication number
- CN108592885A CN108592885A CN201810200565.2A CN201810200565A CN108592885A CN 108592885 A CN108592885 A CN 108592885A CN 201810200565 A CN201810200565 A CN 201810200565A CN 108592885 A CN108592885 A CN 108592885A
- Authority
- CN
- China
- Prior art keywords
- barrier
- visual field
- overlapping region
- demarcation
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Measurement Of Optical Distance (AREA)
Abstract
A kind of list binocular fusion positioning distance measuring algorithm, includes the following steps：A, Ladybug camera calibrations are completed, accurate camera inside and outside parameter is obtained；B, range images pre-process, and enhance contrast, median filter process noise using histogram equalization；C, the overlapping region for calculating two camera lenses, determines the position in visual field line of demarcation, and according to visual field line of demarcation, disturbance in judgement object whether there is overlapping region；If D, barrier is located at overlapping region, binocular ranging mechanism is opened, according to the triangle relation equation of perspective transform, derives the three-dimensional coordinate of spatial point；If E, barrier is located at Non-overlapping Domain, monocular ranging mechanism is opened, using data nonlinear regression modeling method；F, it is obtained in Dome Projection pattern panoramic pictures in Ladybug panorama cameras, calculates the azimuth of barrier.The present invention proposes a kind of single binocular fusion positioning distance measuring algorithm for more mesh panorama cameras.
Description
Technical field
The present invention relates to the image ranging technology field in computer vision field, more particularly to a kind of single binocular fusion is fixed
Position location algorithm.
Background technology
In robot research field, robot using sensor as obstacle avoidance apparatus be always research field hot spot you,
But multiple equipment using sensor, when working in same environment, there may be interference between each other, are surveyed relative to vision
Still there is certain deficiency in amount, sensor.
Therefore, most research institutions has started the research of overall view visual system.But current panoramic vision is positioning
Ranging field cannot complete alternative sensor, need to be used in combination with sensor, in this case, both increased the weight of device,
Also without reducing use cost, and there is also certain deficiencies in reaction speed.
Invention content
In view of the foregoing drawbacks, the present invention proposes a kind of single binocular fusion positioning distance measuring algorithm for more mesh panorama cameras,
Camera fields of view is divided into overlapping region and Non-overlapping Domain, establishes selection mechanism, if disturbance in judgement object is opened in overlapping region
Binocular distance measurement mode；If disturbance in judgement object opens monocular distance measurement mode in Non-overlapping Domain.
For this purpose, the present invention uses following technical scheme：
A kind of list binocular fusion positioning distance measuring algorithm, includes the following steps：
A, Ladybug camera calibrations are completed, accurate camera inside and outside parameter is obtained；
B, range images pre-process, and enhance contrast, median filter process noise using histogram equalization；
C, the overlapping region for calculating two camera lenses, determines the position in visual field line of demarcation, according to visual field line of demarcation, disturbance in judgement object
With the presence or absence of overlapping region；
If D, barrier is located at overlapping region, binocular ranging mechanism is opened, according to the triangle relation equation of perspective transform,
Derive the three-dimensional coordinate of spatial point；
If E, barrier is located at Non-overlapping Domain, monocular ranging mechanism is opened, using data nonlinear regression modeling side
Method；
F, it is obtained in Dome Projection pattern panoramic pictures in Ladybug panorama cameras, calculates the side of barrier
Parallactic angle.
Further, in the step C, β is angle formed by two video cameras (90 ° of 180 ° of ＜ β ＜),It is video camera
The maximum visual angle at maximum horizontal visual angle, two video cameras is equal, when the boundary line of video camera appears in adjacent cameras visual field, claims
Boundary line is the visual field line of demarcation under corresponding video camera；
The calculation formula of the angle of adjacent camera overlapping region is：
If the width for collecting single image is W, the formula of visual field overlapping region width b between two adjacent cameras is calculated
For：
After finding out the width b of overlapping region, you can determine the position in visual field line of demarcation.According to visual field line of demarcation, judge
Barrier whether there is overlapping region, to determine using binocular ranging or monocular ranging；
If there are barrier (x, y) in the visual field of video camera, it is tested barrier and visual field line of demarcation to define G (x, y)
Whether relation function judges its barrier in overlapping region with this, and function is as follows：
According to G (x, y) value, you can judge that being tested barrier is in position in the visual field of video camera.
Further, in the step F, if full-view image is circle, it is origin that image coordinate system XOY, which defines the upper left corner,
Panorama influence is tangent with X-axis and Y-axis, and image coordinate system is converted to x ', o ', y ' coordinate systems, o ' (x in image coordinateo,
yo), the range barrier of barrier and the angle of x ' axis indicate；
The pixel coordinate of barrier is (x, y), and the size and x of abscissa are pressed by itoRelationship, orientation angle formula is divided into two
Kind situation, formula are as follows：
After the distance D and azimuth φ that obtain barrier by above-mentioned principle formula, the location information of barrier
It is indicated with a binary array (D, φ).
Beneficial effects of the present invention：It proposes single binocular fusion positioning distance measuring algorithm, solves to use mesh panorama camera more than one
Realize positioning distance measuring.The visual field of more mesh panorama cameras is divided into overlapping region and Non-overlapping Domain, binocular is used in overlapping region
Vision range finding；Monocular nonlinear regression modeling ranging is used in Non-overlapping Domain.And using in Ladybug series cameras
Dome Projection pattern acquiring panoramic pictures, calculate the azimuth of barrier.
Description of the drawings
Fig. 1 is the operational flowchart of one embodiment of the present of invention；
Fig. 2 is the distribution of Ladybug system camera lenses and the floor map of measurement range of one embodiment of the present of invention；
Fig. 3 is the visual field boundary schematic diagram on the plane of delineation of one embodiment of the present of invention；
Fig. 4 is the angle schematic diagram of the video camera of one embodiment of the present of invention；
Fig. 5 is that the Dome projection panoramic pictures of one embodiment of the present of invention measure barrier orientation schematic diagram.
Specific implementation mode
Technical solution to further illustrate the present invention below with reference to the accompanying drawings and specific embodiments.
As shown in Figs. 1-5, a kind of single binocular fusion positioning distance measuring algorithm, includes the following steps：
A, Ladybug camera calibrations are completed, accurate camera inside and outside parameter is obtained；
B, range images pre-process, and enhance contrast, median filter process noise using histogram equalization；
C, the overlapping region for calculating two camera lenses, determines the position in visual field line of demarcation, according to visual field line of demarcation, disturbance in judgement object
With the presence or absence of overlapping region；
If D, barrier is located at overlapping region, binocular ranging mechanism is opened, according to the triangle relation equation of perspective transform,
Derive the three-dimensional coordinate of spatial point；
If E, barrier is located at Non-overlapping Domain, monocular ranging mechanism is opened, using data nonlinear regression modeling side
Method；
F, it is obtained in Dome Projection pattern panoramic pictures in Ladybug panorama cameras, calculates the side of barrier
Parallactic angle.
Wherein, in the step C, β is angle formed by two video cameras (90 ° of 180 ° of ＜ β ＜),It is the maximum of video camera
The maximum visual angle of horizontal view angle, two video cameras is equal, when the boundary line of video camera appears in adjacent cameras visual field, claims boundary
Line is the visual field line of demarcation under corresponding video camera；
The calculation formula of the angle of adjacent camera overlapping region is：
If the width for collecting single image is W, the formula of visual field overlapping region width b between two adjacent cameras is calculated
For：
After finding out the width b of overlapping region, you can determine the position in visual field line of demarcation.According to visual field line of demarcation, judge
Barrier whether there is overlapping region, to determine using binocular ranging or monocular ranging；
Assuming that cam0One of visual angle boundary l0It is overlapped with x-axis, l2For leftmost border；l1For cam1Rightmost circle, l3
For leftmost border.
α in the angle schematic diagram 4 of video camera0For the non-overlapping visual field of cam0, α1For the overlapped fov of cam0 and cam1, α2
For the non-overlapping visual field of cam1.By formula 1,2 formula of formula can obtain：
If there are barrier (x, y) in the visual field of video camera, it is tested barrier and visual field line of demarcation to define G (x, y)
Whether relation function judges its barrier in overlapping region with this, and function is as follows：
According to G (x, y) value, you can judge that being tested barrier is in position in the visual field of video camera.
In addition, in the step F,
If full-view image is circle, it is origin that image coordinate system XOY, which defines the upper left corner, and panorama influences and X-axis and Y-axis phase
It cuts, image coordinate system is converted to x ', o ', y ' coordinate systems, o ' (x in image coordinateo,yo), the range obstacle of barrier
The angle of object and x ' axis indicates；
The pixel coordinate of barrier is (x, y), and the size and x of abscissa are pressed by itoRelationship, orientation angle formula is divided into two
Kind situation, formula are as follows：
After the distance D and azimuth φ that obtain barrier by above-mentioned principle formula, the location information of barrier
It is indicated with a binary array (D, φ).
The technical principle of the present invention is described above in association with specific embodiment.These descriptions are intended merely to explain the present invention's
Principle, and it cannot be construed to limiting the scope of the invention in any way.Based on the explanation herein, the technology of this field
Personnel would not require any inventive effort the other specific implementation modes that can associate the present invention, these modes are fallen within
Within protection scope of the present invention.
Claims (3)
1. a kind of list binocular fusion positioning distance measuring algorithm, which is characterized in that include the following steps：
A, Ladybug camera calibrations are completed, accurate camera inside and outside parameter is obtained；
B, range images pre-process, and enhance contrast, median filter process noise using histogram equalization；
C, the overlapping region for calculating two camera lenses, determines the position in visual field line of demarcation, according to visual field line of demarcation, whether is disturbance in judgement object
There are overlapping regions；
If D, barrier is located at overlapping region, binocular ranging mechanism is opened, according to the triangle relation equation of perspective transform, is derived
Go out the three-dimensional coordinate of spatial point；
If E, barrier is located at Non-overlapping Domain, monocular ranging mechanism is opened, using data nonlinear regression modeling method；
F, it is obtained in Dome Projection pattern panoramic pictures in Ladybug panorama cameras, calculates the orientation of barrier
Angle.
2. list binocular fusion positioning distance measuring algorithm according to claim 1, which is characterized in that in the step C, β is two
Angle formed by video camera (90 ° of 180 ° of ＜ β ＜),It is the maximum horizontal visual angle of video camera, the maximum visual angle phase of two video cameras
Deng when the boundary line of video camera appears in adjacent cameras visual field, boundary line is referred to as the visual field line of demarcation under corresponding video camera；
The calculation formula of the angle of adjacent camera overlapping region is：
If the width for collecting single image is W, the formula of visual field overlapping region width b is between two adjacent cameras of calculating：
After finding out the width b of overlapping region, you can the position for determining visual field line of demarcation, according to visual field line of demarcation, disturbance in judgement
Object whether there is overlapping region, to determine using binocular ranging or monocular ranging；
If there are barrier (x, y) in the visual field of video camera, the relationship that G (x, y) is tested barrier and visual field line of demarcation is defined
Whether function judges its barrier in overlapping region with this, and function is as follows：
According to G (x, y) value, you can judge that being tested barrier is in position in the visual field of video camera.
3. list binocular fusion positioning distance measuring algorithm according to claim 1, which is characterized in that in the step F,
If full-view image is circle, it is origin that image coordinate system XOY, which defines the upper left corner, and panorama influence is tangent with X-axis and Y-axis, will
Image coordinate system is converted to x ', o ', y ' coordinate systems, o ' (x in image coordinateo,yo), the range barrier of barrier with
The angle of x ' axis indicates；
The pixel coordinate of barrier is (x, y), and the size and x of abscissa are pressed by itoRelationship, orientation angle formula is divided into two kinds of feelings
Condition, formula are as follows：
After the distance D and azimuth φ that obtain barrier by above-mentioned principle formula, location information i.e. available one of barrier
A binary array (D, φ) indicates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810200565.2A CN108592885A (en) | 2018-03-12 | 2018-03-12 | A kind of list binocular fusion positioning distance measuring algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810200565.2A CN108592885A (en) | 2018-03-12 | 2018-03-12 | A kind of list binocular fusion positioning distance measuring algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108592885A true CN108592885A (en) | 2018-09-28 |
Family
ID=63626061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810200565.2A Pending CN108592885A (en) | 2018-03-12 | 2018-03-12 | A kind of list binocular fusion positioning distance measuring algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108592885A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109633662A (en) * | 2018-12-28 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Barrier localization method, device and terminal |
| CN109982058A (en) * | 2019-04-03 | 2019-07-05 | 贵安新区新特电动汽车工业有限公司 | Automatically projecting method, device, electronic equipment and storage medium are followed |
| CN110084851A (en) * | 2019-04-19 | 2019-08-02 | 湖北亿咖通科技有限公司 | A kind of binocular point cloud generation method and system |
| CN110926408A (en) * | 2019-12-04 | 2020-03-27 | 北京中科慧眼科技有限公司 | Short-distance measuring method, device and system based on characteristic object and storage medium |
| CN112509061A (en) * | 2020-12-14 | 2021-03-16 | 济南浪潮高新科技投资发展有限公司 | Multi-camera visual positioning method, system, electronic device and medium |
| CN113103228A (en) * | 2021-03-29 | 2021-07-13 | 航天时代电子技术股份有限公司 | Teleoperation robot |
| CN113343907A (en) * | 2021-06-28 | 2021-09-03 | 深圳市银星智能科技股份有限公司 | Obstacle detection method, obstacle detection module and self-moving equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102160385A (en) * | 2008-07-23 | 2011-08-17 | 阿特里尔视象有限公司 | The compositional structure, mechanisms and processes for the inclusion of binocular stereo information into representational media |
| CN106643667A (en) * | 2016-12-14 | 2017-05-10 | 中国石油天然气集团公司 | Distance measurement method and device |
-
2018
- 2018-03-12 CN CN201810200565.2A patent/CN108592885A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102160385A (en) * | 2008-07-23 | 2011-08-17 | 阿特里尔视象有限公司 | The compositional structure, mechanisms and processes for the inclusion of binocular stereo information into representational media |
| CN106643667A (en) * | 2016-12-14 | 2017-05-10 | 中国石油天然气集团公司 | Distance measurement method and device |
Non-Patent Citations (2)
| Title |
|---|
| 曹文君，赵祚喜，刘 雄，李叶林: "一种单双目结合的全景避障测距方法", 《现代电子技术》 * |
| 曹文君: "全景视觉环境避障测距方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109633662A (en) * | 2018-12-28 | 2019-04-16 | 百度在线网络技术（北京）有限公司 | Barrier localization method, device and terminal |
| US11532166B2 (en) | 2018-12-28 | 2022-12-20 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Obstacle positioning method, device and terminal |
| CN109982058A (en) * | 2019-04-03 | 2019-07-05 | 贵安新区新特电动汽车工业有限公司 | Automatically projecting method, device, electronic equipment and storage medium are followed |
| CN110084851A (en) * | 2019-04-19 | 2019-08-02 | 湖北亿咖通科技有限公司 | A kind of binocular point cloud generation method and system |
| CN110084851B (en) * | 2019-04-19 | 2020-12-04 | 湖北亿咖通科技有限公司 | Binocular point cloud generation method and system |
| CN110926408A (en) * | 2019-12-04 | 2020-03-27 | 北京中科慧眼科技有限公司 | Short-distance measuring method, device and system based on characteristic object and storage medium |
| CN112509061A (en) * | 2020-12-14 | 2021-03-16 | 济南浪潮高新科技投资发展有限公司 | Multi-camera visual positioning method, system, electronic device and medium |
| CN112509061B (en) * | 2020-12-14 | 2024-03-22 | 山东浪潮科学研究院有限公司 | Multi-camera visual positioning method, system, electronic device and medium |
| CN113103228A (en) * | 2021-03-29 | 2021-07-13 | 航天时代电子技术股份有限公司 | Teleoperation robot |
| CN113103228B (en) * | 2021-03-29 | 2023-08-15 | 航天时代电子技术股份有限公司 | Teleoperation robot |
| CN113343907A (en) * | 2021-06-28 | 2021-09-03 | 深圳市银星智能科技股份有限公司 | Obstacle detection method, obstacle detection module and self-moving equipment |
| CN113343907B (en) * | 2021-06-28 | 2024-03-26 | 深圳银星智能集团股份有限公司 | Obstacle detection method, obstacle detection module and self-moving device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108592885A (en) | A kind of list binocular fusion positioning distance measuring algorithm | |
| US10260862B2 (en) | Pose estimation using sensors | |
| EP3517997B1 (en) | Method and system for detecting obstacles by autonomous vehicles in real-time | |
| US9607227B2 (en) | Boundary detection apparatus and boundary detection method | |
| CN106960454B (en) | Depth of field obstacle avoidance method and equipment and unmanned aerial vehicle | |
| US10909395B2 (en) | Object detection apparatus | |
| CN108369743A (en) | Use multi-directional camera map structuring space | |
| JP6171593B2 (en) | Object tracking method and system from parallax map | |
| JP2004086779A (en) | Obstacle detection device and its method | |
| Nienaber et al. | A comparison of low-cost monocular vision techniques for pothole distance estimation | |
| US9098750B2 (en) | Gradient estimation apparatus, gradient estimation method, and gradient estimation program | |
| CN105205459B (en) | A kind of recognition methods of characteristics of image vertex type and device | |
| CN106033614B (en) | A kind of mobile camera motion object detection method under strong parallax | |
| CN113034586B (en) | Road inclination angle detection method and detection system | |
| US11004211B2 (en) | Imaging object tracking system and imaging object tracking method | |
| JP5501084B2 (en) | Planar area detection apparatus and stereo camera system | |
| Petrovai et al. | A stereovision based approach for detecting and tracking lane and forward obstacles on mobile devices | |
| CN101782386B (en) | Non-visual geometric camera array video positioning method and system | |
| KR20100066952A (en) | Apparatus for tracking obstacle using stereo vision and method thereof | |
| US20150063630A1 (en) | Apparatus and method for detecting obstacle | |
| CN112146620B (en) | Target object ranging method and device | |
| CN104471436A (en) | Method and device for calculating a change in an image scale of an object | |
| CN103688289A (en) | Method and system for estimating a similarity between two binary images | |
| US20130142388A1 (en) | Arrival time estimation device, arrival time estimation method, arrival time estimation program, and information providing apparatus | |
| JP3700681B2 (en) | Traveling path detection device |
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 |
Application publication date: 20180928 |
|
| RJ01 | Rejection of invention patent application after publication |