CN106875448B - A kind of vehicle-mounted monocular camera external parameter self-calibrating method - Google Patents
A kind of vehicle-mounted monocular camera external parameter self-calibrating method Download PDFInfo
- Publication number
- CN106875448B CN106875448B CN201710084212.6A CN201710084212A CN106875448B CN 106875448 B CN106875448 B CN 106875448B CN 201710084212 A CN201710084212 A CN 201710084212A CN 106875448 B CN106875448 B CN 106875448B
- Authority
- CN
- China
- Prior art keywords
- camera
- image
- vehicle
- point
- characteristic point
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30256—Lane; Road marking
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of vehicle-mounted monocular camera external parameter self-calibrating methods, comprising the following steps: 1) image sequence on the road surface of running car is shot by vehicle-mounted camera；The vehicle-mounted camera is mounted on Chinese herbaceous peony windshield middle position；2) it is based on acquired image sequence, lane markings characteristic point is extracted with image segmentation algorithm, is fitted to obtain two parallel lane lines according to characteristic point, establishes road markings model, determine end point；3) lane markings feature point motion vector is matched by characteristic point matching method, and extracts the point that vertical motion vector is zero and is fitted to obtain motion direction lines, calculate the yaw angle of camera；4) the extension focal length of image is determined；5) according to the external parameter for extending focal length and known image principal point calculating camera.The present invention realizes convenient and efficient without complicated artificial manipulation formality, it is only necessary to by vehicle driving certain time, the parameter calibration result of camera is obtained by calculating.
Description
Technical field
The present invention relates to automobile assistant driving technology more particularly to a kind of vehicle-mounted monocular camera external parameter self-calibration sides
Method.
Background technique
Traditional camera scaling method is a kind of relatively stringent scaling method, therefore its precision is higher, but calibration process
It is more complicated and computationally intensive, therefore for the more extensive vehicle-mounted camera of application, there is the limitation used.
For existing self-calibrating method, the scene of three vertical direction parallel lines pair is usually difficult to find, even if depositing
In such scene condition, but due to the influence of environmental factor, the extraction accuracy of linear edge can also have problem, Jin Erying
Ring the precision of camera calibration parameter calibration.
The present invention is not entirely dependent on specific scene identity object, and uses the multiple image in movable basis for reference,
In conjunction with the concept of confidence level, the inner parameter of camera more can be accurately obtained, and applicable surface is more extensive.
Camera self-calibrating method proposed by the invention does not need special technology people while guaranteeing enough accuracy
Member is demarcated, it is only necessary to which running car can conveniently obtain the outer ginseng calibration of camera in road a period of time
As a result.
Summary of the invention
The technical problem to be solved in the present invention is that for the defects in the prior art, providing a kind of vehicle-mounted monocular camera
External parameter self-calibrating method.
The technical solution adopted by the present invention to solve the technical problems is: a kind of vehicle-mounted monocular camera external parameter is from marking
Determine method, comprising the following steps:
1) image sequence on the road surface of running car is shot by vehicle-mounted camera；The vehicle-mounted camera is mounted on vehicle
Front windshield middle position；
2) it is based on acquired image sequence, extracts lane markings characteristic point, especially two with image segmentation algorithm
Parallel lane line identification characteristics point, is fitted to obtain two parallel lane lines according to characteristic point, establishes road markings model, determines
End point；
3) lane markings feature point motion vector is matched by characteristic point matching method, and extracts longitudinal movement arrow
The point that amount is zero is fitted to obtain motion direction lines, calculates the yaw angle of camera；
The specific method is as follows:
3.1) initial velocity of automobile is determined；
3.2) to any point P (X, Y, Z) on the known ground and its projection p (x, y) on image ψ, motion vector is introduced
(u, v) geometrical constraint:
In formula:F is the focal length of camera, and t is translational motion parameter, and w is
Yaw motion speed；T and w is obtained according to the initial velocity of step 3.1)；
3.3) according to successive frame illumination invariant the characteristics of introduces brightness constraint:
I (x, y, t)=I (x+u δ t, y+v δ t, t+ δ t)
3.4) noise jamming for considering real image, is constrained in conjunction with geometrical constraint and brightness, is searched for using gradient descent method
Optimal motion parameter, so that ash of the previous frame image to the compensation image and present frame real image corresponding coordinate of current frame object
Angle value is closest；Divide the image into multiple macro block WiIt is handled, then optiaml ciriterion are as follows:
In formula,The estimated value of kinematic parameter, M are the search range of kinematic parameter；
4) it determines the extension focal length of image: confidence level is determined according to pavement texture feature, exclude the characteristic point on non-road surface, and
Extract multiple characteristic points that horizontal direction motion vector is zero and the characteristic point that vector collects；
5) according to the pitch angle (Picth) for extending focal length and known image principal point calculating camera, comprehensively consider extension
Focal length and end point introduce confidence weight, if the comprehensive confidence level of the two is greater than threshold value T1, it is determined that the pixel of skyline is vertical
Coordinate y, and then the ordinate v of one of inner parameter for combining camera principal point0, the pitch angle of camera can be calculated:
6) motion direction lines are determined by multiple points that horizontal motion vector is zero, seeks its slope kα, become based on inverse perspective
Get the slope K of world coordinates line direction line in returnα, and then can be in the hope of yaw angle:
α=tan-1(Kα)
7) deflection angle (Roll) of camera is calculated according to the vertical edge in image
It is determined perpendicular to the Edge Feature Points and its horizontal coordinate x of level roadi, and be fitted and obtain linear equation, it determines
Its slope kβ, the deflection angle of camera can be obtained:
β=tan-1(kβ)
8) according to movement velocity and time and matched characteristic point calculate the mounting height of camera.
Based on skyline ordinate y, camera self moving parameter (translational velocity tZ) and corresponding characteristic point coordinate A
(x1,y1) and B (x2,y2), the mounting height h of camera is solved by following formula:
According to the above scheme, hot-tempered point is reduced by image filtering method in the step 1), image is carried out smooth.
According to the above scheme, the Feature Points Matching algorithm of the step 3) is the relevant Feature Points Matching algorithm of light stream.
According to the above scheme, the lane markings characteristic point in the step 2) is two parallel lane line identification characteristics points.
The beneficial effect comprise that: a kind of vehicle-mounted camera external parameter self-calibration side according to the present invention
Method, without complicated artificial manipulation formality, is realized convenient and efficient, it is only necessary to by vehicle compared with traditional scaling board scaling method
Certain time on road is travelled on, by calculating the autonomous parameter calibration result for obtaining camera.With existing self-calibrating method phase
Than scene required for the present invention is easier to obtain, and the present invention is handled by multiple image, improves calibration result
Precision, be more advantageous to functionization.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the method flow diagram of the embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, is not used to limit
The fixed present invention.
As shown in Figure 1, a kind of vehicle-mounted camera method for calibrating external parameters, the specific implementation steps are as follows:
Step 1: by running car in (preferably including the lane markings of straight route in driving process, but not on road surface
Be limited to this road surface), shoot image sequence using vehicle-mounted camera, and by image filtering method, reduce hot-tempered point, to image into
Row is smooth.
Step 2: being based on acquired image sequence, extract lane markings characteristic point with image segmentation algorithm, especially
Two parallel lane line identification characteristics points, can be fitted to obtain two parallel lane lines according to these characteristic points:
Its intersection point is end point, and coordinate representation is (x0, y0)。
Step 3: lane markings characteristic point being moved by characteristic point matching method (the preferably relevant method of light stream) and is sweared
Amount is matched, and is extracted the point that vertical motion vector is zero and be fitted to obtain motion direction lines, and the yaw angle of camera is calculated；
This step determines the characteristic point met the requirements by the relevant Feature Points Matching algorithm of light stream, and is obtained based on this
The light stream vector of characteristic point and the self moving parameter of camera.The specific method is as follows:
(1) determine initial velocity: automobile on straight road surface from static to the motion continuation regular hour, therefore initial speed
Degree is 0, if it is not 0 that automobile travels initial velocity on straight road, can refer to automobile OBD output speed or GPS output speed
Degree.
(2) a point P (X, Y, Z) and its projection p (x, y) on image ψ on ground known to, in addition translational motion parameter t,
Yaw motion speed w introduces motion vector (u, v) geometrical constraint:
In formula:F is the focal length of camera.
(3) according to successive frame illumination invariant the characteristics of, introduces brightness constraint:
I (x, y, t)=I (x+u δ t, y+v δ t, t+ δ t) (3)
(4) noise jamming for considering real image, constrains in conjunction with geometrical constraint and brightness, most using gradient descent method search
Excellent kinematic parameter, so that gray scale of the previous frame image to the compensation image and present frame real image corresponding coordinate of current frame object
It is worth closest.If dividing the image into multiple macro block WiIt is handled, then optiaml ciriterion are as follows:
In formula,The estimated value of kinematic parameter, M are the search range of kinematic parameter.
(5) consider pavement texture feature, introduce confidence level, exclude the characteristic point on non-road surface, and extract horizontal direction movement arrow
The point (i.e. extension focal length, FOE) that the multiple points and vector that amount is zero collect
Step 4: comprehensively considering FOE and end point, introduce confidence weight, if the comprehensive confidence level of the two is greater than threshold value
T1, it is determined that the pixel ordinate y of skyline, and then the ordinate v of one of inner parameter for combining camera principal point0, Bian Keji
Calculate the pitch angle of camera；Wherein, v0It is the known quantity demarcated.Belong to the inner parameter of camera；
Step 5: determining motion direction lines by multiple points that horizontal motion vector is zero, seek its slope kα, based on inverse saturating
The slope K of world coordinates line direction line is obtained depending on transformationα, and then can be in the hope of yaw angle:
α=tan-1(Kα) (6)
Step 6: being based on skyline ordinate y, camera self moving parameter (translational velocity tZ) and corresponding characteristic point
Coordinate A (x1,y1) and B (x2,y2), wherein A, B two o'clock are subpoint of the same point in different moments two field pictures on ground；
The mounting height h of camera is solved by following formula:
Step 7: being determined perpendicular to the Edge Feature Points and its horizontal coordinate x of level roadi, and be fitted and obtain straight line side
Journey determines its slope kβ, the deflection angle of camera can be obtained:
β=tan-1(kβ) (8)
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (8)
1. a kind of vehicle-mounted monocular camera external parameter self-calibrating method, which comprises the following steps:
1) image sequence on the road surface of running car is acquired by vehicle-mounted camera；
2) it is based on acquired image sequence, lane markings characteristic point is extracted with image segmentation algorithm, is fitted according to characteristic point
Two parallel lane lines are obtained, road markings model is established, determines end point；
3) lane markings feature point motion vector is matched by characteristic point matching method, and extracts vertical motion vector and is
Zero point is fitted to obtain motion direction lines, calculates the kinematic parameter of camera；
4) it determines the extension focal length of image: confidence level being determined according to pavement texture feature, excludes the characteristic point on non-road surface, and is extracted
The characteristic point that the multiple characteristic points and vector that horizontal direction motion vector is zero are collected；
5) according to the pitch angle for extending focal length and known image principal point calculating camera；
6) motion direction lines are determined by multiple points that horizontal motion vector is zero, seeks its slope kα, obtained based on inverse perspective mapping
The slope K of world coordinates line direction lineα, and then can be in the hope of yaw angle:
α=tan-1(Kα)；
7) according in image vertical edge calculate camera deflection angle be determined perpendicular to level road Edge Feature Points and
Its horizontal coordinate xi, and be fitted and obtain linear equation, determine its slope kβ, the deflection angle of camera can be obtained:
β=tan-1(kβ)；
8) according to movement velocity and time and matched characteristic point calculate the mounting height of camera；
Based on skyline ordinate y, camera self moving parameter translational velocity tZAnd corresponding characteristic point coordinate A (x1,y1) and
B(x2,y2), the mounting height h of camera is solved by following formula:
Wherein, f is the focal length of camera.
2. vehicle-mounted monocular camera external parameter self-calibrating method according to claim 1, which is characterized in that the step
1) by image filtering method in, hot-tempered point is reduced, image is carried out smooth.
3. vehicle-mounted monocular camera external parameter self-calibrating method according to claim 1, which is characterized in that the step
3) Feature Points Matching algorithm is the relevant Feature Points Matching algorithm of light stream.
4. vehicle-mounted monocular camera external parameter self-calibrating method according to claim 1, which is characterized in that the step
3) the specific method is as follows for the kinematic parameter of calculating camera:
3.1) initial velocity of automobile is determined；
3.2) it to any point P (X, Y, Z) on the known ground and its projection p (x, y) on image ψ, introduces motion vector (u, v)
Geometrical constraint:
In formula:F is the focal length of camera, and t is translational motion parameter, and w is deflection
Movement velocity；T and w is obtained according to the initial velocity of step 3.1)；
3.3) according to successive frame illumination invariant the characteristics of introduces brightness constraint:
I (x, y, t)=I (x+u δ t, y+v δ t, t+ δ t)
3.4) noise jamming for considering real image, constrains in conjunction with geometrical constraint and brightness, is searched for using gradient descent method optimal
Kinematic parameter, so that gray value of the previous frame image to the compensation image and present frame real image corresponding coordinate of current frame object
It is closest；Divide the image into multiple macro block WiIt is handled, then optiaml ciriterion are as follows:
In formula,The estimated value of kinematic parameter, M are the search range of kinematic parameter.
5. vehicle-mounted monocular camera external parameter self-calibrating method according to claim 1, which is characterized in that the step
2) the lane markings characteristic point in is two parallel lane line identification characteristics points.
6. vehicle-mounted monocular camera external parameter self-calibrating method according to claim 1, which is characterized in that the step
1) vehicle-mounted camera described in is mounted on Chinese herbaceous peony windshield middle position.
7. vehicle-mounted monocular camera external parameter self-calibrating method according to claim 1, which is characterized in that the step
It 1) further include being pre-processed by image sequence of the image filtering method to acquisition in.
8. vehicle-mounted monocular camera external parameter self-calibrating method according to claim 7, which is characterized in that the step
1) pretreatment includes dropping hot-tempered processing and smoothing processing in.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710084212.6A CN106875448B (en) | 2017-02-16 | 2017-02-16 | A kind of vehicle-mounted monocular camera external parameter self-calibrating method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710084212.6A CN106875448B (en) | 2017-02-16 | 2017-02-16 | A kind of vehicle-mounted monocular camera external parameter self-calibrating method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106875448A CN106875448A (en) | 2017-06-20 |
| CN106875448B true CN106875448B (en) | 2019-07-23 |
Family
ID=59167496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710084212.6A Active CN106875448B (en) | 2017-02-16 | 2017-02-16 | A kind of vehicle-mounted monocular camera external parameter self-calibrating method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106875448B (en) |
Families Citing this family (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107703747B (en) * | 2017-10-09 | 2020-01-03 | 东南大学 | Friction stir welding application-oriented dynamic parameter self-calibration method for heavy-load robot |
| US10635116B2 (en) * | 2017-10-19 | 2020-04-28 | Ford Global Technologies, Llc | Video calibration with illumination invariant image |
| CN110322513B (en) * | 2018-03-30 | 2022-03-04 | 杭州海康威视数字技术股份有限公司 | Camera external parameter calibration method and device and electronic equipment |
| CN110555885B (en) * | 2018-05-31 | 2023-07-04 | 海信集团有限公司 | Calibration method and device of vehicle-mounted camera and terminal |
| CN110858405A (en) * | 2018-08-24 | 2020-03-03 | 北京市商汤科技开发有限公司 | Attitude estimation method, device and system of vehicle-mounted camera and electronic equipment |
| CN109345593B (en) * | 2018-09-04 | 2022-04-26 | 海信集团有限公司 | Camera posture detection method and device |
| CN109410284A (en) * | 2018-10-31 | 2019-03-01 | 百度在线网络技术（北京）有限公司 | A kind of method for parameter estimation, device, electronic equipment, vehicle and storage medium |
| CN109685858B (en) * | 2018-12-29 | 2020-12-04 | 北京茵沃汽车科技有限公司 | Monocular camera online calibration method |
| CN109859278B (en) * | 2019-01-24 | 2023-09-01 | 惠州市德赛西威汽车电子股份有限公司 | Calibration method and calibration system for camera external parameters of vehicle-mounted camera system |
| CN112184821B (en) * | 2019-07-01 | 2023-03-10 | 上海安亭地平线智能交通技术有限公司 | Method and device for adjusting roll angle of camera, storage medium and electronic equipment |
| CN110490936B (en) * | 2019-07-15 | 2021-09-07 | 杭州飞步科技有限公司 | Calibration method, device and equipment of vehicle camera and readable storage medium |
| CN111275768A (en) * | 2019-12-11 | 2020-06-12 | 深圳市德赛微电子技术有限公司 | Lens calibration method and system based on convolutional neural network |
| CN113033253B (en) * | 2019-12-24 | 2024-07-12 | 北京车和家信息技术有限公司 | Camera calibration method and device |
| CN111223150A (en) * | 2020-01-15 | 2020-06-02 | 电子科技大学 | Vehicle-mounted camera external parameter calibration method based on double vanishing points |
| CN111429527B (en) * | 2020-03-24 | 2023-12-01 | 广东星舆科技有限公司 | Automatic external parameter calibration method and system for vehicle-mounted camera |
| CN111612849A (en) * | 2020-05-12 | 2020-09-01 | 深圳市哈工大交通电子技术有限公司 | Camera calibration method and system based on mobile vehicle |
| CN111491140B (en) * | 2020-05-15 | 2021-05-11 | 深圳金三立视频科技股份有限公司 | Power transmission cable video line patrol method and terminal |
| CN111806354A (en) * | 2020-06-05 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Visual angle adjusting method, storage medium and system for automobile data recorder |
| CN111696160B (en) * | 2020-06-22 | 2023-08-18 | 江苏中天安驰科技有限公司 | Automatic calibration method and equipment for vehicle-mounted camera and readable storage medium |
| CN111862234B (en) * | 2020-07-22 | 2023-10-20 | 中国科学院上海微系统与信息技术研究所 | Binocular camera self-calibration method and system |
| CN111973134A (en) * | 2020-08-06 | 2020-11-24 | 江苏势通生物科技有限公司 | Method for aligning test body to channel to be tested based on vision, navigation method and system |
| CN113490967A (en) * | 2020-09-22 | 2021-10-08 | 深圳市锐明技术股份有限公司 | Camera calibration method and device and electronic equipment |
| CN112150559A (en) * | 2020-09-24 | 2020-12-29 | 深圳佑驾创新科技有限公司 | Calibration method of image acquisition device, computer equipment and storage medium |
| CN112348752B (en) * | 2020-10-28 | 2022-08-16 | 武汉极目智能技术有限公司 | Lane line vanishing point compensation method and device based on parallel constraint |
| CN112529968A (en) * | 2020-12-22 | 2021-03-19 | 上海商汤临港智能科技有限公司 | Camera equipment calibration method and device, electronic equipment and storage medium |
| CN112348493A (en) * | 2021-01-07 | 2021-02-09 | 北京电信易通信息技术股份有限公司 | Intelligent conference recording system and method |
| CN114792341A (en) * | 2021-01-25 | 2022-07-26 | 阿里巴巴集团控股有限公司 | Method and device for obtaining camera parameters and electronic equipment |
| CN112800986B (en) * | 2021-02-02 | 2021-12-07 | 深圳佑驾创新科技有限公司 | Vehicle-mounted camera external parameter calibration method and device, vehicle-mounted terminal and storage medium |
| CN112862899B (en) * | 2021-02-07 | 2023-02-28 | 黑芝麻智能科技(重庆)有限公司 | External parameter calibration method, device and system for image acquisition equipment |
| CN113160322A (en) * | 2021-03-17 | 2021-07-23 | 地平线(上海)人工智能技术有限公司 | Camera calibration method and device, medium and electronic device |
| CN112927309B (en) * | 2021-03-26 | 2024-04-09 | 苏州欧菲光科技有限公司 | Vehicle-mounted camera calibration method and device, vehicle-mounted camera and storage medium |
| CN114332241B (en) * | 2021-12-29 | 2022-09-09 | 元橡科技(苏州)有限公司 | External reference calibration method, three-dimensional reconstruction method and storage medium |
| CN115103123A (en) * | 2022-07-07 | 2022-09-23 | 上海智能交通有限公司 | Automatic vehicle-mounted holder camera distribution and control method and system based on lane line identification |
| CN116193108B (en) * | 2023-04-24 | 2023-07-07 | 知行汽车科技(苏州)股份有限公司 | Online self-calibration method, device, equipment and medium for camera |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103499337A (en) * | 2013-09-26 | 2014-01-08 | 北京航空航天大学 | Vehicle-mounted monocular camera distance and height measuring device based on vertical target |
| CN103985118A (en) * | 2014-04-28 | 2014-08-13 | 无锡观智视觉科技有限公司 | Parameter calibration method for cameras of vehicle-mounted all-round view system |
| CN104008548A (en) * | 2014-06-04 | 2014-08-27 | 无锡观智视觉科技有限公司 | Feature point extraction method for vehicle-mounted around view system camera parameter calibration |
| CN104050669A (en) * | 2014-06-18 | 2014-09-17 | 北京博思廷科技有限公司 | On-line calibration method based on vanishing point and monocular camera image-forming principle |
| CN105513056A (en) * | 2015-11-30 | 2016-04-20 | 天津津航技术物理研究所 | Vehicle-mounted monocular infrared camera external parameter automatic calibration method |
| CN105551020A (en) * | 2015-12-03 | 2016-05-04 | 浙江大华技术股份有限公司 | Method and device for detecting dimensions of target object |
-
2017
- 2017-02-16 CN CN201710084212.6A patent/CN106875448B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103499337A (en) * | 2013-09-26 | 2014-01-08 | 北京航空航天大学 | Vehicle-mounted monocular camera distance and height measuring device based on vertical target |
| CN103985118A (en) * | 2014-04-28 | 2014-08-13 | 无锡观智视觉科技有限公司 | Parameter calibration method for cameras of vehicle-mounted all-round view system |
| CN104008548A (en) * | 2014-06-04 | 2014-08-27 | 无锡观智视觉科技有限公司 | Feature point extraction method for vehicle-mounted around view system camera parameter calibration |
| CN104050669A (en) * | 2014-06-18 | 2014-09-17 | 北京博思廷科技有限公司 | On-line calibration method based on vanishing point and monocular camera image-forming principle |
| CN105513056A (en) * | 2015-11-30 | 2016-04-20 | 天津津航技术物理研究所 | Vehicle-mounted monocular infrared camera external parameter automatic calibration method |
| CN105551020A (en) * | 2015-12-03 | 2016-05-04 | 浙江大华技术股份有限公司 | Method and device for detecting dimensions of target object |
Non-Patent Citations (3)
| Title |
|---|
| Monocular Visual-Inertial State Estimation With Online Initialization and Camera-IMU Extrinsic Calibration;Zhenfei Yang et al;《IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING》;20170131;第14卷(第1期);第39-51页 |
| 一种改进的单视图相机标定算法;石晶 等;《系统仿真学报》;20130831;第25卷;第278-281页 |
| 基于环形镜面的相机外部参数自动标定方法;付生鹏 等;《机器人》;20150531;第37卷(第3期);第277-285页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106875448A (en) | 2017-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106875448B (en) | A kind of vehicle-mounted monocular camera external parameter self-calibrating method | |
| CN110569704B (en) | Multi-strategy self-adaptive lane line detection method based on stereoscopic vision | |
| CN105260699B (en) | A kind of processing method and processing device of lane line data | |
| CN102999759B (en) | A kind of state of motion of vehicle method of estimation based on light stream | |
| CN113903011B (en) | Semantic map construction and positioning method suitable for indoor parking lot | |
| CN107463890B (en) | A kind of Foregut fermenters and tracking based on monocular forward sight camera | |
| JP4363295B2 (en) | Plane estimation method using stereo images | |
| CN107590438A (en) | A kind of intelligent auxiliary driving method and system | |
| JP5023186B2 (en) | Object motion detection system based on combination of 3D warping technique and proper object motion (POM) detection | |
| US20140204205A1 (en) | Method for measuring the height profile of a vehicle passing on a road | |
| CN103149939A (en) | Dynamic target tracking and positioning method of unmanned plane based on vision | |
| KR101261409B1 (en) | System for recognizing road markings of image | |
| CN108961342B (en) | Calibration method and system of optical flow sensor | |
| CN106530328B (en) | A method of it is followed based on video image to moving object detection and smoothly | |
| CN105444741B (en) | Route characteristic identification, deviation measurement based on double vision open country window and accurate positioning method | |
| CN113781562B (en) | Lane line virtual-real registration and self-vehicle positioning method based on road model | |
| CN111723778B (en) | Vehicle distance measuring system and method based on MobileNet-SSD | |
| CN108021857B (en) | Building detection method based on unmanned aerial vehicle aerial image sequence depth recovery | |
| CN104331907B (en) | A kind of method based on ORB feature detections measurement bearer rate | |
| CN108416798A (en) | A kind of vehicle distances method of estimation based on light stream | |
| CN114399748A (en) | Agricultural machinery real-time path correction method based on visual lane detection | |
| CN114719873B (en) | Low-cost fine map automatic generation method and device and readable medium | |
| Braut et al. | Estimating OD matrices at intersections in airborne video-a pilot study | |
| CN108846363A (en) | A kind of subregion vehicle bottom shadow detection method based on divergence expression scanning | |
| CN112164037A (en) | MEMS device in-plane motion measurement method based on optical flow tracking |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |