CN102629381A - Calibration parameter real-time monitoring method of unmanned surface vessel vision system - Google Patents
Calibration parameter real-time monitoring method of unmanned surface vessel vision system Download PDFInfo
- Publication number
- CN102629381A CN102629381A CN2012100549344A CN201210054934A CN102629381A CN 102629381 A CN102629381 A CN 102629381A CN 2012100549344 A CN2012100549344 A CN 2012100549344A CN 201210054934 A CN201210054934 A CN 201210054934A CN 102629381 A CN102629381 A CN 102629381A
- Authority
- CN
- China
- Prior art keywords
- vision system
- coordinate
- image
- real
- parameter
- 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.)
- Granted
Links
Images
Landscapes
- Image Processing (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a calibration parameter real-time monitoring method of an unmanned surface vessel vision system. The method comprises the following steps of: fixedly installing a marker with an obvious feature point on a vessel such that the vision system shoots that an image of the marker is positioned in a parameter monitoring area of a frame of image; by using a calibration image of the vision system, extracting a coordinate of a marker image feature point in the parameter monitoring area, and taking a coordinate average value of a corresponding feature point in all calibration images as a calibration image coordinate of the feature point; in an actual working condition of the vision system, every time a frame of image is collected, carrying out real-time extraction on the feature point of the marker image in the parameter monitoring area; comparing a feature point coordinate extracted from each frame of image in real time with the calibration coordinate of the feature point, and determining whether carrying out calibration again is needed or not. According to the invention, the parameter of the vision system can be monitored without carrying out on-line calibration, thus the vision system carries out real-time monitoring on a camera parameter, and sends a request of needing calibration again or an alarm signal when the calibration parameter changes greatly.
Description
Technical field
The present invention relates to a kind of unmanned water surface ship vision system technology; Be specifically related to the calibrating parameters method of real-time of unmanned water surface ship vision system; Be applicable to the real-time monitoring of used camera interior and exterior parameter in the vision guided navigation that is installed on the unmanned boat or the supervisory system, also can be used for unmanned car and unmanned aerial vehicle vision vision system.
Background technology
Vision guided navigation existing successful application in unmanned car in ground and aerial unmanned plane; People attempt the vision guided navigation technology is applied to unmanned water surface ship in recent years; But the good vision system of land demarcation through the transportation of unmanned boat, lift, lay or receive that wave causes jolts, calibrating parameters can change; In addition, vision system receives the reflective influence of the water surface, and actual working environment is different with land demarcation environment, and also there is deviation in calibrating parameters; Therefore, people hope and can monitor in real time the Camera calibration parameter, when bigger variation appears in calibrating parameters, send request or the alerting signal that need demarcate again.
To the monitoring problem of vision system calibrating parameters, people such as Fitzgibbon propose a kind of method based on on-line proving (Online camera calibration, United States Patent; US7671891B2,2010), but this method need demarcating than multiple-camera same model; Estimate the prior probability distribution of intrinsic parameter; This is the work of a difficulty, and the result of on-line proving is a maximum likelihood estimator, is not the result who directly demarcates.In addition, this method needs ceaselessly carry out on-line proving to vision system, when the parameter constant of vision system, and the resource of waste vision system.
Therefore, people hope to have and a kind ofly need not carry out the method that on-line proving just can be monitored the vision system parameter, have only when monitoring calibrating parameters when bigger variation occurring, just send request or the alerting signal that need demarcate again.
Summary of the invention
The object of the invention is to need on-line proving to the monitoring method of the calibrating parameters of existing unmanned water surface ship vision system; Be prone to cause the problem of the vision system wasting of resources; And a kind of calibrating parameters method of real-time of unmanned water surface ship vision system is provided; Need not carry out the parameter that on-line proving just can be monitored vision system, vision system is monitored camera parameters when under actual sea conditions, working in real time; When bigger variation appears in calibrating parameters, send request or the alerting signal that to demarcate again.
To achieve these goals, technical scheme of the present invention is:
A kind of calibrating parameters method of real-time of unmanned water surface ship vision system, said monitoring method comprises the steps:
(1) on water surface ship corresponding stationkeeping at least one have the mark of obvious characteristic point, and the image that makes vision system photograph this mark is arranged in a FX of a two field picture, and takes this zone as far as possible; Said FX is called the parameter monitoring district, normally is positioned at a middle zonule of a two field picture bottom; Because the relative position of vision system and mark immobilizes, every shooting one two field picture of vision system always has the image of mark to be positioned at the parameter monitoring district;
(2) carrying out the vision system timing signal, utilize uncalibrated image, extract the unique point coordinate of mark image in the said parameter monitoring district, get the demarcation coordinate of the coordinate average of character pair point in whole uncalibrated images as unique point;
(3) under the condition of vision system real work, every collection one two field picture carries out extract real-time to the unique point coordinate of mark image in the parameter monitoring district wherein;
The demarcation coordinate of the unique point that (4) will be from each two field picture obtains in the real-time coordinate of unique point and the step (2) of extract real-time compares, and chooses the decision content that the mould sum of the real-time coordinate of all unique points and the difference of demarcating coordinate changes as critical parameter in each two field picture;
(5) decision content and the preset threshold that obtain in the step (4) are compared, when said decision content during more than or equal to said threshold value, send the alerting signal that calibrating parameters changes to system, request is demarcated again; When said decision content less than said threshold value, explain that the calibrating parameters of vision system does not change, vision system works on, and need not to demarcate.
According to such scheme obtain the invention enables vision system under actual sea conditions, to work in; Camera parameters is monitored in real time; When bigger variation appears in calibrating parameters; Send request or the alerting signal that to demarcate again, effective like this problem of avoiding not stop that vision system is carried out on-line proving.
Description of drawings
Further specify the present invention below in conjunction with accompanying drawing and embodiment.
A kind of mark of Fig. 1 for adopting among the present invention.
Fig. 2 is the synoptic diagram of the two field picture taken in one embodiment of the invention.
The systematic schematic diagram that Fig. 3 implements for the present invention.
Embodiment
For technological means, creation characteristic that the present invention is realized, reach purpose and effect and be easy to understand and understand, below in conjunction with concrete diagram, further set forth the present invention.
In order to realize need not carrying out the method that on-line proving just can be monitored the vision system parameter; Method provided by the invention need be made one or more marks with obvious characteristic point; As shown in Figure 1; This mark is fixedly mounted on the appropriate location of unmanned boat, and makes the image of this mark be arranged in the parameter monitoring district 401 (as shown in Figure 2) that vision system is gathered a two field picture.
Under actual operating conditions, vision system carries out real time characteristic points to the image in this parameter monitoring district and extracts, and when the change in location of unique point exceeds setting threshold, sends parameter and changes alerting signal, and the demarcation of vision system is carried out in application again.
Based on above-mentioned principle, the practical implementation process of unmanned water surface ship vision system calibrating parameters method of real-time provided by the invention is following:
The first step; Referring to Fig. 3; Unmanned water surface ship 200 all is positioned at surface level 600 with sensation target 500, makes the mark 100 with obvious characteristic point, and this mark 100 is fixedly mounted on appropriate location on the unmanned boat 200; The image 402 that makes video camera 300 in the vision system photograph this mark is positioned at the parameter monitoring district 401 of a two field picture 400, and takes this parameter monitoring district (as shown in Figure 2) as far as possible.Entire image 400 is made up of with vision reconstruction area 403 parameter monitoring district 401.
Referring to Fig. 3; Mark 100 can adopt in the existing camera calibration technology is convenient to the structure that unique point is extracted automatically; The mark that in instance shown in Figure 1, adopts is sticked on the one flat plate and processed by a Chinese red and the alternate colored square paper of white, but it is not limited to this structure.
Second step, vision system is demarcated, at timing signal, to each frame uncalibrated image, the characteristics of image point coordinate of mark in the extracting parameter monitoring section, referring to Fig. 1, the unique point of mark is the angle point of colored grid.
Suppose to have m frame uncalibrated image, n unique point arranged on the mark.For i frame uncalibrated image, wherein the image coordinate of j unique point does
I=1 wherein, 2 ..., m, j=1,2 ..., n then gets the demarcation coordinate P of j unique point
OjBe the average of j unique point image coordinate in all m frame uncalibrated images, promptly
In the 3rd step, when the vision system real work, every collection one two field picture of vision system carries out feature point extraction to the image in the parameter monitoring district wherein.The mark characteristics of image point coordinate that extracts when supposing moment t does
J=1,2 ..., n.
The 4th step is with the real-time coordinate P of unique point that extracts
TjDemarcation coordinate P with unique point
OjCompare, error of calculation absolute value with
And with this decision content that changes as critical parameter.
If do not carry out zoom operation, in most cases, the inside and outside parameter of video camera can not change, and the coordinate of image characteristic point can not change in the parameter monitoring district, but since noise, the variation of ambient lighting condition and the vibration of hull, Δ P
tCan maintain a very little value.Under the typical environment condition of real work, to Δ P
tVariation carry out statistical process, confirm Δ P
tVariances sigma, getting threshold value T is Δ P
t3 times of variance, promptly T=3 σ is used for and Δ P
tValue compares, and judges whether and will demarcate again with this:
As Δ P
tDuring>=T, explain that variation has taken place the calibrating parameters of vision system, send the alerting signal that calibrating parameters changes to system, request is demarcated again;
As Δ P
tDuring<T, explain that the calibrating parameters of vision system does not change, vision system works on, and need not to demarcate.Can realize the real-time monitoring of vision system calibrating parameters like this.
More than show and described ultimate principle of the present invention, principal character and advantage of the present invention.The technician of the industry should understand; The present invention is not restricted to the described embodiments; That describes in the foregoing description and the instructions just explains principle of the present invention; Under the prerequisite that does not break away from spirit and scope of the invention, the present invention also has various changes and modifications, and these variations and improvement all fall in the scope of the invention that requires protection.The present invention requires protection domain to be defined by appending claims and equivalent thereof.
Claims (1)
1. the calibrating parameters method of real-time of a unmanned water surface ship vision system is characterized in that, said monitoring method comprises the steps:
(1) on water surface ship corresponding stationkeeping at least one have the mark of obvious characteristic point; And the image that makes vision system photograph this mark is arranged in a FX of a two field picture; And taking this zone as far as possible, said FX is as the parameter monitoring district;
(2) carrying out the vision system timing signal, utilize uncalibrated image, extract the unique point coordinate of mark image in the said parameter monitoring district, get the demarcation coordinate of the coordinate average of character pair point in whole uncalibrated images as unique point;
(3) under the condition of vision system real work, every collection one two field picture carries out extract real-time to the unique point coordinate of mark image in the parameter monitoring district wherein;
The demarcation coordinate of the unique point that obtains in real-time coordinate of unique point that (4) will from each two field picture, extract and the step (2) compares, and chooses the decision content that the mould sum of the real-time coordinate of all unique points and the difference of demarcating coordinate changes as critical parameter in each two field picture;
(5) decision content and the preset threshold that obtain in the step (4) are compared, when said decision content during more than or equal to said threshold value, send the alerting signal that calibrating parameters changes to system, request is demarcated again; When said decision content less than said threshold value, explain that the calibrating parameters of vision system does not change, vision system works on, and need not to demarcate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210054934.4A CN102629381B (en) | 2012-03-05 | 2012-03-05 | Calibration parameter real-time monitoring method of unmanned surface vessel vision system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210054934.4A CN102629381B (en) | 2012-03-05 | 2012-03-05 | Calibration parameter real-time monitoring method of unmanned surface vessel vision system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102629381A true CN102629381A (en) | 2012-08-08 |
CN102629381B CN102629381B (en) | 2014-12-10 |
Family
ID=46587639
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210054934.4A Expired - Fee Related CN102629381B (en) | 2012-03-05 | 2012-03-05 | Calibration parameter real-time monitoring method of unmanned surface vessel vision system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102629381B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108898637A (en) * | 2018-06-13 | 2018-11-27 | 苏州上善知源汽车电子有限公司 | Front camera scaling method |
CN109960250A (en) * | 2017-12-26 | 2019-07-02 | 浙江大学 | The agricultural unmanned aerodynamic ship and method of self-navigation are carried out based on unmanned plane vision |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1804541A (en) * | 2005-01-10 | 2006-07-19 | 北京航空航天大学 | Spatial three-dimensional position attitude measurement method for video camera |
CN101441769A (en) * | 2008-12-11 | 2009-05-27 | 上海交通大学 | Real time vision positioning method of monocular camera |
CN101598556A (en) * | 2009-07-15 | 2009-12-09 | 北京航空航天大学 | Unmanned plane vision/inertia integrated navigation method under a kind of circumstances not known |
CN101661617A (en) * | 2008-08-30 | 2010-03-03 | 深圳华为通信技术有限公司 | Method and device for camera calibration |
CN101788660A (en) * | 2009-01-23 | 2010-07-28 | 日电(中国)有限公司 | System, method and equipment for determining whether positioning equipment in space is moved or not |
US20100245576A1 (en) * | 2009-03-31 | 2010-09-30 | Aisin Seiki Kabushiki Kaisha | Calibrating apparatus for on-board camera of vehicle |
-
2012
- 2012-03-05 CN CN201210054934.4A patent/CN102629381B/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1804541A (en) * | 2005-01-10 | 2006-07-19 | 北京航空航天大学 | Spatial three-dimensional position attitude measurement method for video camera |
CN101661617A (en) * | 2008-08-30 | 2010-03-03 | 深圳华为通信技术有限公司 | Method and device for camera calibration |
CN101441769A (en) * | 2008-12-11 | 2009-05-27 | 上海交通大学 | Real time vision positioning method of monocular camera |
CN101788660A (en) * | 2009-01-23 | 2010-07-28 | 日电(中国)有限公司 | System, method and equipment for determining whether positioning equipment in space is moved or not |
US20100245576A1 (en) * | 2009-03-31 | 2010-09-30 | Aisin Seiki Kabushiki Kaisha | Calibrating apparatus for on-board camera of vehicle |
CN101598556A (en) * | 2009-07-15 | 2009-12-09 | 北京航空航天大学 | Unmanned plane vision/inertia integrated navigation method under a kind of circumstances not known |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109960250A (en) * | 2017-12-26 | 2019-07-02 | 浙江大学 | The agricultural unmanned aerodynamic ship and method of self-navigation are carried out based on unmanned plane vision |
CN108898637A (en) * | 2018-06-13 | 2018-11-27 | 苏州上善知源汽车电子有限公司 | Front camera scaling method |
Also Published As
Publication number | Publication date |
---|---|
CN102629381B (en) | 2014-12-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7124816B2 (en) | Modification of vehicle components based on vehicle accident reconstruction data | |
KR101866239B1 (en) | Method for Monitoring Water Quality Environment Using Drone | |
FR2913800A1 (en) | Anti-collision alert filtering device for e.g. helicopter, has alarm manger centralizing alerts transmitted by anti-collision equipments to crew, where each alert comprises danger level code, and alert filter filtering alerts based on code | |
KR101687073B1 (en) | Apparatus for esimating tunnel height and method thereof | |
US9382016B2 (en) | Aircraft landing monitor | |
US9892646B2 (en) | Context-aware landing zone classification | |
US9533769B1 (en) | Terrain warning systems and methods | |
US20220373353A1 (en) | Map Updating Method and Apparatus, and Device | |
EP3657464A1 (en) | Control device, control method, and program | |
US10565887B2 (en) | Flight initiation proximity warning system | |
KR20170101519A (en) | Apparatus and method for disaster monitoring using unmanned aerial vehicle | |
KR20170101516A (en) | Apparatus and method for fire monitoring using unmanned aerial vehicle | |
JP6652979B2 (en) | Image processing device, flying object and program | |
US11440657B2 (en) | Aerial vehicles with machine vision | |
CN104240239A (en) | Method for detecting local road segment hazy weather based on road image | |
CN107784844B (en) | Intelligent traffic signal lamp system and road environment detection method thereof | |
CN112330915B (en) | Unmanned aerial vehicle forest fire prevention early warning method and system, electronic equipment and storage medium | |
JP7159338B2 (en) | AIS information processing device | |
CN112930290A (en) | Method for formulating control instructions for a motor vehicle | |
CN105610087A (en) | Power transmission line inspection system of power grid | |
EP3438703A1 (en) | Method and device for monitoring the position of a following aircraft relative to a leading aircraft during a formation flight | |
CN102629381B (en) | Calibration parameter real-time monitoring method of unmanned surface vessel vision system | |
US20200312050A1 (en) | Control device, server, safety system, and control method of control device | |
EP3438949A1 (en) | Method and device for controlling the trajectory of a following aircraft relative to a leading aircraft during a risk of collision | |
US11209830B2 (en) | Safety aware automated governance of vehicles |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20141210 Termination date: 20180305 |