CN110174088A - A kind of target ranging method based on monocular vision - Google Patents
A kind of target ranging method based on monocular vision Download PDFInfo
- Publication number
- CN110174088A CN110174088A CN201910359973.7A CN201910359973A CN110174088A CN 110174088 A CN110174088 A CN 110174088A CN 201910359973 A CN201910359973 A CN 201910359973A CN 110174088 A CN110174088 A CN 110174088A
- Authority
- CN
- China
- Prior art keywords
- camera
- observation point
- coordinate system
- pixel
- formula
- 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
- G01C3/00—Measuring distances in line of sight; Optical rangefinders
- G01C3/10—Measuring distances in line of sight; Optical rangefinders using a parallactic triangle with variable angles and a base of fixed length in the observation station, e.g. in the instrument
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Abstract
The present invention discloses a kind of target ranging methods based on monocular vision.First according to camera calibration principle, the internal reference matrix of video camera is obtained;Then, the single-frame images containing target is acquired, and identifies target region in image, calculates the average value of the area pixel coordinate ordinate maximum value and its corresponding abscissa, the coordinate that combination is obtained is as observation point;Finally, three-dimensional information of the observation point under body coordinate system is obtained based on image slices vegetarian refreshments, according to the distance of three-dimensional information calculating observation point of the observation point under body coordinate system.The present invention more accurately can carry out ranging to observation point.
Description
Technical field
The present invention relates to target ranging method, specifically a kind of target ranging method based on monocular vision.
Background technique
Currently, mainly studying monocular vision, binocular and multi-vision visual system when studying the range-measurement system of view-based access control model
System.The bad control of interoperability issues in binocular and more mesh systems between video camera, single camera vision system can overcome above-mentioned take the photograph
Interoperability issues between camera.From production cost, monocular vision more saves cost than binocular and more mesh systems.Due to
The advantages that monocular vision ranging has structure simple, and arithmetic speed is fast, at low cost, the invention proposes one kind to be based on monocular vision
Target ranging method.
Summary of the invention
The purpose of the present invention is to provide a kind of methods for realizing target distance measurement based on monocular vision.
The technical scheme is that obtaining the internal reference matrix of video camera according to camera calibration principle first;Then, it adopts
Collect the single-frame images containing target, and identify target region in image, calculates the area pixel coordinate ordinate most
The average value of big value and its corresponding abscissa, using obtained coordinate as observation point;Finally, being obtained based on image slices vegetarian refreshments
Three-dimensional information of the observation point under world coordinate system, according to three-dimensional information calculating observation point of the observation point under body coordinate system away from
From.The following steps are included:
Step 1: demarcating to monocular-camera, the internal reference matrix [f of video camera is obtainedx,0,u0;0,fy,v0;0,0,
1];
Step 2: by calibrated monocular-camera shoot the single-frame images containing target, and to the image of acquisition into
Row processing, extracts target area, calculates being averaged for the area pixel coordinate ordinate maximum value and its corresponding abscissa
Value, the coordinate that combination is obtained is as observation point P;
Step 3: according to camera calibration principle, by the pixel coordinate P of observation pointp(u, v) can obtain observation point in body
D coordinates value P under coordinate systemb(xb,yb,zb), and then the distance of observation point can be calculated, it is shown that the specific method is as follows:
Step 3.1, the internal reference matrix that video camera can be obtained by step 1, the pixel of observation point can be obtained by step 2
Point, then
Wherein λ indicates that light and camera optical axis angle at observation point, y indicate vertical seat of the observation point under image coordinate system
Mark, y0Camera optical center is indicated in the ordinate of image coordinate system, f indicates focal length of camera.
Further abbreviation is to pixel coordinate system, and relationship is as follows:
Wherein v indicates ordinate of the observation point under pixel coordinate system, v0Indicate camera optical center in pixel coordinate system
Ordinate, dy indicate that the physical size of each pixel in y-direction, fy indicate the normalization focal length in y-axis;
Step 3.2, in triangle geometrical relationship, O1P2Distance is expressed as follows:
In formula (3), O1O2For the height of video camera distance ranging plane, P1It is P in the subpoint of camera optical axis2,
O1P2Indicating depth information i.e. indicates observation point in camera coordinate system midpoint Pc(xc,yc,zc) in zcValue.
Pixel coordinate is transformed under camera coordinates by step 3.3, and pixel coordinate system and camera coordinate system conversion are closed
System, as shown in formula (4):
By depth information z of the observation point obtained in the pixel coordinate and step 3.2 of observation point under camera coordinate systemc
It brings formula (4) into, coordinate P of the observation point in camera coordinate system can be acquiredc(xc,yc,zc);
Formula (5) is camera coordinate system to the conversion formula of body coordinate system, wherein RcbIt is sat for camera coordinate system to body
Mark the spin matrix of system, TcbFor camera coordinate system to the translation matrix of body coordinate system.
Step 3.4, the distance D calculating such as formula (6) of observation point are shown:
Detailed description of the invention
The present invention is based on the ranging models of the target ranging method of monocular vision by Fig. 1.
Specific embodiment
In order to deepen the understanding of the present invention, the present invention is described in further detail below with reference to embodiment.But
The present invention can realize in different forms, however it is not limited to example described herein.
In Fig. 1, xOy is image coordinate system, and Zc indicates that the Z axis and optical axis of camera coordinates system, XbO2Yb indicate body coordinate system
Lower Z=0 plane (i.e. ranging plane), O1 indicate that camera lens, two dotted lines of a, b indicate field of vision range, and θ indicates camera pitching
Angle, H indicate camera to the height of ranging plane, and P1 point is observation point, and observation point P1 point is P in plane of delineation imaging point, in light
Subpoint on axis is P2, and the subpoint in X-axis is P3, and P3 point is P0 in plane of delineation imaging point.
Step 1: demarcating to monocular-camera, the internal reference matrix of video camera is obtained;
Step 2: shooting the list containing waterborne target by the calibrated monocular-camera being fixed on unmanned water surface ship
Frame image, and the image of acquisition is handled, waterborne target region is extracted, the pixel nearest apart from unmanned water surface ship is calculated
Point, using the point as observation point P;
Step 3: according to camera calibration principle, by the pixel coordinate P of observation pointI(u, v) can obtain observation point in body
D coordinates value P under coordinate systemb(xb,yb,zb), and then distance of the observation point to unmanned water surface ship, specific side can be calculated
Method is as follows:
Step 3.1, the internal reference matrix that video camera can be obtained by step 1, the pixel of observation point can be obtained by step 2
Point, then
Wherein λ indicates that light and camera optical axis angle at observation point, y indicate vertical seat of the observation point under image coordinate system
Mark, y0Camera optical center is indicated in the ordinate of image coordinate system, f indicates focal length of camera.
Further abbreviation is to pixel coordinate system, and relationship is as follows:
Wherein λ indicates that light and camera optical axis angle at observation point, v indicate vertical seat of the observation point under pixel coordinate system
Mark, v0Camera optical center is indicated in the ordinate of pixel coordinate system, dy indicates the physical size of each pixel in y-direction, fy
Indicate the normalization focal length in y-axis;
Step 3.2, in triangle geometrical relationship, O1P2 distance is expressed as follows:
In formula (3), O1O2 is the height of video camera distance ranging plane, and P1 is P2 in the subpoint of camera optical axis,
O1P2, which indicates depth information i.e., indicates observation point in camera coordinate system midpoint Pc(xc,yc,zc) in zcValue.
Pixel coordinate is transformed under camera coordinates by step 3.3, and pixel coordinate system and camera coordinate system conversion are closed
System, as shown in formula (4):
By depth information z of the observation point obtained in the pixel coordinate and step 3.2 of observation point under camera coordinate systemc
It brings formula (4) into, coordinate P of the observation point in camera coordinate system can be acquiredc(xc,yc,zc);
Formula (5) is camera coordinate system to the conversion formula of body coordinate system, wherein RcbIt is sat for camera coordinate system to body
Mark the spin matrix of system, TcbFor camera coordinate system to the translation matrix of body coordinate system.Camera coordinate system and body herein
The relationship of coordinate system is that camera coordinates system rotates θ degree around X-axis counterclockwise, and Y direction translates downwards H unit after negating, it may be assumed that
By the R in formula (6)cbAnd TcbBring formula (5) into
The three-dimensional coordinate obtained by formula (7) is three-dimensional coordinate P of the observation point under body coordinate systemS;
Step 3.4, the distance of observation point are calculated as shown in formula (8):
Claims (1)
1. a kind of method based on monocular vision real-time measurement observation point distance, it is characterised in that the following steps are included:
Step 1: demarcating to monocular-camera, the internal reference matrix [f of video camera is obtainedx,0,u0;0,fy,v0;0,0,1];
Step 2: by calibrated monocular-camera shoot the single-frame images containing target, and to the image of acquisition at
Reason extracts target area, calculates the average value of the area pixel coordinate ordinate maximum value and its corresponding abscissa, will
Obtained coordinate is combined as observation point P;
Step 3: according to camera calibration principle, by the pixel coordinate P of observation pointp(u, v) can obtain observation point in body coordinate
D coordinates value P under systemb(xb,yb,zb), and then the distance of observation point can be calculated, it is shown that the specific method is as follows:
Step 3.1, the internal reference matrix that video camera can be obtained by step 1, the pixel of observation point can be obtained by step 2,
Then
Wherein λ indicates that light and camera optical axis angle at observation point, y indicate ordinate of the observation point under image coordinate system, y0
Camera optical center is indicated in the ordinate of image coordinate system, f indicates focal length of camera;
Further abbreviation is to pixel coordinate system, and relationship is as follows:
Wherein v indicates ordinate of the observation point under pixel coordinate system, v0Indicate camera optical center in the vertical seat of pixel coordinate system
Mark, dy indicate that the physical size of each pixel in y-direction, fy indicate the normalization focal length in y-axis;
Step 3.2, in triangle geometrical relationship, O1P2Distance is expressed as follows:
In formula (3), O1O2For the height of video camera distance ranging plane, P1It is P in the subpoint of camera optical axis2, O1P2Table
Showing depth information i.e. indicates observation point in camera coordinate system midpoint Pc(xc,yc,zc) in zcValue;
Pixel coordinate is transformed under camera coordinates by step 3.3, pixel coordinate system and camera coordinate system transformational relation, such as
Shown in formula (4):
By depth information z of the observation point obtained in the pixel coordinate and step 3.2 of observation point under camera coordinate systemcIt brings into
Formula (4) can acquire coordinate P of the observation point in camera coordinate systemc(xc,yc,zc);
Formula (5) is camera coordinate system to the conversion formula of body coordinate system, wherein RcbFor camera coordinate system to body coordinate system
Spin matrix, TcbFor camera coordinate system to the translation matrix of body coordinate system.
Step 3.4, the distance D calculating such as formula (6) of observation point are shown:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910359973.7A CN110174088A (en) | 2019-04-30 | 2019-04-30 | A kind of target ranging method based on monocular vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910359973.7A CN110174088A (en) | 2019-04-30 | 2019-04-30 | A kind of target ranging method based on monocular vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110174088A true CN110174088A (en) | 2019-08-27 |
Family
ID=67690250
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910359973.7A Pending CN110174088A (en) | 2019-04-30 | 2019-04-30 | A kind of target ranging method based on monocular vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110174088A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110866951A (en) * | 2019-10-08 | 2020-03-06 | 华南农业大学 | Correction method for inclination of optical axis of monocular camera |
CN111192235A (en) * | 2019-12-05 | 2020-05-22 | 中国地质大学(武汉) | Image measuring method based on monocular vision model and perspective transformation |
CN111380503A (en) * | 2020-05-29 | 2020-07-07 | 电子科技大学 | Monocular camera ranging method adopting laser-assisted calibration |
CN111623776A (en) * | 2020-06-08 | 2020-09-04 | 昆山星际舟智能科技有限公司 | Method for measuring distance of target by using near infrared vision sensor and gyroscope |
CN111982072A (en) * | 2020-07-29 | 2020-11-24 | 西北工业大学 | Target ranging method based on monocular vision |
CN112557390A (en) * | 2019-09-10 | 2021-03-26 | 惠州旭鑫智能技术有限公司 | Monocular visual inspection method for dislocation defect of bare cell tab of power battery |
CN112781562A (en) * | 2020-12-29 | 2021-05-11 | 中国北方车辆研究所 | Multi-target reconnaissance and ranging method based on monocular camera |
CN112965052A (en) * | 2021-02-07 | 2021-06-15 | 中国科学院长春光学精密机械与物理研究所 | Monocular camera target ranging method |
CN113091693A (en) * | 2021-04-09 | 2021-07-09 | 天津大学 | Monocular vision long-range distance measurement method based on image super-resolution technology |
CN113124819A (en) * | 2021-06-17 | 2021-07-16 | 中国空气动力研究与发展中心低速空气动力研究所 | Monocular distance measuring method based on plane mirror |
CN114018212A (en) * | 2021-08-03 | 2022-02-08 | 广东省国土资源测绘院 | Monocular distance measurement-oriented pitch angle correction method and system for dome camera |
CN115096196A (en) * | 2022-08-25 | 2022-09-23 | 中国科学院西安光学精密机械研究所 | Visual height and speed measuring method and system for rocket recovery and storage medium |
CN115507752A (en) * | 2022-09-29 | 2022-12-23 | 苏州大学 | Monocular vision distance measurement method and system based on parallel environment elements |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105203034A (en) * | 2015-07-29 | 2015-12-30 | 四川大学 | Height and area measurement method based on monocular camera three-dimensional distance measurement model |
CN106153000A (en) * | 2016-06-17 | 2016-11-23 | 合肥工业大学 | A kind of front vehicles distance detection method |
CN108180888A (en) * | 2017-12-29 | 2018-06-19 | 三英精控(天津)仪器设备有限公司 | A kind of distance detection method based on rotating pick-up head |
-
2019
- 2019-04-30 CN CN201910359973.7A patent/CN110174088A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105203034A (en) * | 2015-07-29 | 2015-12-30 | 四川大学 | Height and area measurement method based on monocular camera three-dimensional distance measurement model |
CN106153000A (en) * | 2016-06-17 | 2016-11-23 | 合肥工业大学 | A kind of front vehicles distance detection method |
CN108180888A (en) * | 2017-12-29 | 2018-06-19 | 三英精控(天津)仪器设备有限公司 | A kind of distance detection method based on rotating pick-up head |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112557390B (en) * | 2019-09-10 | 2023-02-24 | 惠州旭鑫智能技术有限公司 | Monocular visual inspection method for dislocation defect of bare cell tab of power battery |
CN112557390A (en) * | 2019-09-10 | 2021-03-26 | 惠州旭鑫智能技术有限公司 | Monocular visual inspection method for dislocation defect of bare cell tab of power battery |
CN110866951A (en) * | 2019-10-08 | 2020-03-06 | 华南农业大学 | Correction method for inclination of optical axis of monocular camera |
CN111192235A (en) * | 2019-12-05 | 2020-05-22 | 中国地质大学(武汉) | Image measuring method based on monocular vision model and perspective transformation |
CN111192235B (en) * | 2019-12-05 | 2023-05-26 | 中国地质大学(武汉) | Image measurement method based on monocular vision model and perspective transformation |
CN111380503A (en) * | 2020-05-29 | 2020-07-07 | 电子科技大学 | Monocular camera ranging method adopting laser-assisted calibration |
CN111623776A (en) * | 2020-06-08 | 2020-09-04 | 昆山星际舟智能科技有限公司 | Method for measuring distance of target by using near infrared vision sensor and gyroscope |
CN111982072A (en) * | 2020-07-29 | 2020-11-24 | 西北工业大学 | Target ranging method based on monocular vision |
CN112781562A (en) * | 2020-12-29 | 2021-05-11 | 中国北方车辆研究所 | Multi-target reconnaissance and ranging method based on monocular camera |
CN112965052A (en) * | 2021-02-07 | 2021-06-15 | 中国科学院长春光学精密机械与物理研究所 | Monocular camera target ranging method |
CN113091693A (en) * | 2021-04-09 | 2021-07-09 | 天津大学 | Monocular vision long-range distance measurement method based on image super-resolution technology |
CN113091693B (en) * | 2021-04-09 | 2022-08-05 | 天津大学 | Monocular vision long-range distance measurement method based on image super-resolution technology |
CN113124819A (en) * | 2021-06-17 | 2021-07-16 | 中国空气动力研究与发展中心低速空气动力研究所 | Monocular distance measuring method based on plane mirror |
CN114018212A (en) * | 2021-08-03 | 2022-02-08 | 广东省国土资源测绘院 | Monocular distance measurement-oriented pitch angle correction method and system for dome camera |
CN115096196A (en) * | 2022-08-25 | 2022-09-23 | 中国科学院西安光学精密机械研究所 | Visual height and speed measuring method and system for rocket recovery and storage medium |
CN115507752A (en) * | 2022-09-29 | 2022-12-23 | 苏州大学 | Monocular vision distance measurement method and system based on parallel environment elements |
CN115507752B (en) * | 2022-09-29 | 2023-07-07 | 苏州大学 | Monocular vision ranging method and system based on parallel environment elements |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110174088A (en) | A kind of target ranging method based on monocular vision | |
CN107389026B (en) | A kind of monocular vision distance measuring method based on fixed point projective transformation | |
CN111951305B (en) | Target detection and motion state estimation method based on vision and laser radar | |
CN106529495B (en) | Obstacle detection method and device for aircraft | |
CN104880176B (en) | Moving object posture measurement method based on prior knowledge model optimization | |
WO2017080108A1 (en) | Flying device, flying control system and method | |
CN107703951B (en) | A kind of unmanned plane barrier-avoiding method and system based on binocular vision | |
CN111243033B (en) | Method for optimizing external parameters of binocular camera | |
CN106934809A (en) | Unmanned plane based on binocular vision autonomous oiling rapid abutting joint air navigation aid in the air | |
CN108801135B (en) | Nuclear fuel rod pose automatic identification equipment | |
CN110889829B (en) | Monocular distance measurement method based on fish eye lens | |
CN113196007B (en) | Camera system applied to vehicle | |
CN106127115B (en) | hybrid visual target positioning method based on panoramic vision and conventional vision | |
CN108805910A (en) | More mesh Train-borne recorders, object detection method, intelligent driving system and automobile | |
CN102567989A (en) | Space positioning method based on binocular stereo vision | |
CN106570904A (en) | Multi-target relative posture recognition method based on Xtion camera | |
CN105631859B (en) | Three-degree-of-freedom bionic stereo visual system | |
CN110555878A (en) | Method and device for determining object space position form, storage medium and robot | |
CN110288659A (en) | A kind of Depth Imaging and information acquisition method based on binocular vision | |
CN113525631B (en) | Underwater terminal docking system and method based on optical visual guidance | |
CN110099268B (en) | Blind area perspective display method with natural color matching and natural display area fusion | |
CN108154536A (en) | The camera calibration method of two dimensional surface iteration | |
CN109855602A (en) | Move the monocular visual positioning method under visual field | |
CN110136047A (en) | Static target 3 D information obtaining method in a kind of vehicle-mounted monocular image | |
CN116385504A (en) | Inspection and ranging method based on unmanned aerial vehicle acquisition point cloud and image registration |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190827 |