CN106803880A - Orbit camera device people's is autonomous with clapping traveling control method - Google Patents
Orbit camera device people's is autonomous with clapping traveling control method Download PDFInfo
- Publication number
- CN106803880A CN106803880A CN201710077249.6A CN201710077249A CN106803880A CN 106803880 A CN106803880 A CN 106803880A CN 201710077249 A CN201710077249 A CN 201710077249A CN 106803880 A CN106803880 A CN 106803880A
- Authority
- CN
- China
- Prior art keywords
- target
- frame
- camera device
- device people
- clapping
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The present invention discloses a kind of the autonomous with clapping traveling control method of orbit camera device people, and photographer is selected with clapping object and determining reference frame by monitor video first;After track cameras people enters with bat pattern, obtained with clapping the relative displacement of the target in target and reference frame in present frame with clapping control module in each speed governing cycle, and the speed governing in this, as traveling motor basis;In shooting task is performed, cameraman can be manipulated and force cameras people to exit with bat pattern cameras people by long-range brake.The present invention can be used for the automatic shooting needs of the fast moving objects of competitive sports and large-scale activity.
Description
Technical field
The invention belongs to radio and television technique for taking field, and in particular to a kind of orbit camera device people's is autonomous with clapping row
Enter control method.
Background technology
TV and film producing process need to carry out substantial amounts of shooting work, and generally same photographed scene needs multiple bat
Take the photograph seat in the plane cooperation.Traditional screening-mode is that have the photographer to carry out shooting operation on each seat in the plane, also some auxiliary
Personnel are using track or hang the forms such as mast and assist the photographer to carry out the change of camera site and angle, and this mode not only works
Efficiency is low, and easily due to multiple seat in the plane matching problems cause camera lens to expose the false wait influence shooting quality situation.Using track
Robot is shot, and photographer carries out remote control on backstage, in sports event live broadcast, perform in a radio or TV programme hall in be to adopt extensively
The orbit camera device people of technology, such as stadium, the underwater robot swum on competition field etc., these robot platforms
Use, improve operating efficiency and shoot effect.However, during reference object is quickly moved, cameraman is often
It is difficult to directly manipulate the human-computer interaction device on operation bench, the accurate tracking to object of matching colors is realized, often largely
Depend on the operation skill and the qualification to equipment of photographer.Simply take the traveling strategy of constant speed, the effect of shooting
Sometimes it is extremely difficult to require again.
It is current to fail to find the inventive technique with clapping control for being directly used in orbit camera device people, related technology master
Have:
(1) video target tracking method, device and automatic video frequency following system (CN 101290681B [P]), invention master
A kind of video target tracking method is disclosed, including gradient vector flow GVF deformations are carried out to each position candidate in present frame, obtained
To each deformation curve;The video features of deformation curve are calculated, determines that a position candidate is made according to the video features being calculated
It is a kind of various methods of target of target location.
(2) a kind of method (CN101860732 B) of control holder camera to automatically track target, the invention is related to one kind
The method for controlling holder camera to automatically track target, comprises the following steps:Automatically select tracing mode:Video processing module root
Automatic tracing mode and global search pattern are automatically selected according to the tracking mode of target;Automatically the processing procedure of tracing mode is:
Video processing module judges monopod video camera state, and after tracking target is matched, position and size according to target send control
System order is adjusted to camera position and focal length;The processing procedure of global search pattern is:Video processing module is to monitoring
Several regions of search in region carry out target detection and matching until searching tracking target according to taking turn mode.
But, the above does not have for orbit camera device people with clapping the control actual solution of proposition, existing method
Though referring to part in video target tracking method, also cannot directly apply.
The content of the invention
Goal of the invention:It is an object of the invention to solve the deficiencies in the prior art, there is provided a kind of orbit camera
Device people's is autonomous with clapping traveling control method, and orbit camera device people is manipulated to shooting right with parallel motion relation for distal end
Elephant it is automatic with clap.
Technical scheme:A kind of orbit camera device people's of the present invention is autonomous with clapping traveling control method, specifically includes successively
Following steps:
Step 1:Implement photographer's manually determined tracking target o of remote control, and determine reference image frame Fr;
Step 2:With time T as controlling cycle, orbit camera device people obtains the frame of video F of current periodt;Wherein, obtain
The frame of video for obtaining current period does not need extras, has vision signal special all the way to make for cameraman in monitor picture
With;
Step 3:Judge FtWhether F is includedrIn with clap target o, if nothing, jump to step 8, otherwise continue;
Step 4:With clapping displacement in frame of video coordinate system of the target relative to reference image frame in calculating present frame
dt;
Step 5:According to displacement dtAnd the displacement d of a upper controlling cyclet-1, calculate orbit camera device people's
Target speed governing increment Delta v=f (dt,dt-1), and platform speed is adjusted to vt+Δv;
Step 6:Detect whether to receive the brake manipulation instruction of console, if nothing, jump to step 2, otherwise continue;
Step 7:Output terminates with bat process, jumps to step 9;
Step 8:Output loses information with clapping target;
Step 9:Exit with bat pattern.
Further, in the step 1, reference image frame FrThe principle of determination is:The important portion of target o at least A%
Position is located in the middle of shooting image in the region Rc of B%.
Further, the detailed process of the step 3 is:
Step 301;Extract reference frame FrThe n key point p that middle target o is included1, p2,…,pn, and its corresponding spy
Levy the sub- fp of description1, fp2,…,fpn;
Step 302;Extract key frame FtIn m key point q1, q2,…,qm, and its corresponding Feature Descriptor
fq1, fq2,…,fqm;
Step 303:Calculate piAnd qjThe distance between son fd (i, j) is described between point, and asks for n dimensions Fdi=minjfd
(i,j);I=1,2 ..., n, j=j, 2 ..., m;
Step 304:If FdiIn less than less than threshold epsilon quantity | { Fdi<ε}|>μn(0<μ<1) in, then judging present frame Ft
Comprising target o, otherwise it is judged as that target is lost.
Further, the specific method of the step 4 is, by the Fd of gained in step 3iSort from small to large, take wherein
Preceding ρ constitute set omega, and 0<ρ<1, then calculate its corresponding key point piAnd qjDisplacement d in frame coordinate systemij
=(xij,yij), ask for dijX durection components average value dx=1/ | Ω | × ΣΩ{xij, as in present frame with clap target
The relative displacement d with reference framet;Xij and yij represent the transverse and longitudinal coordinate value of a vector in frame coordinate system.
Further, in the step 5, the computing formula f (d of speed knots modificationt,dt-1) it is proportional control mode, i.e. f
(dt,dt-1)=k1×dt+k2×dt-1, wherein, parameter k1And k2It is to be obtained by pre-stage test and correct on-the-spot.Wherein, here
K1 and k2 refer to ratio, and acquisition is debugged by specific works scene.Specifically, k1 and k2 here, not only and entirely transports
The kinematic parameter of moving platform is relevant, goes back and the focal length of video camera setting has relation.
Beneficial effect:The present invention manipulates cameras people to the automatic of parallel motion relation reference object for distal end
With clapping, can be used for the automatic shooting needs of the fast moving objects of competitive sports and large-scale activity.
Brief description of the drawings
Fig. 1 is schematic flow sheet of the invention.
Specific embodiment
Technical solution of the present invention is described in detail below, but protection scope of the present invention is not limited to the implementation
Example.
As shown in figure 1, a kind of orbit camera device people's of the present embodiment is autonomous with clapping traveling control method, specifically successively
Comprise the steps of:
Step 1:Implement photographer's manually determined tracking target o of remote control, and determine reference image frame Fr.It is worth referring to
What is gone out is to determine reference image frame FrThe principle of determination is target o at least 50% significant points in the area of shooting image centre 25%
Domain Rc;
Step 2:With time T=1000ms as controlling cycle, orbit camera device people obtains current frame of video Ft;
Step 3:Judge present frame whether comprising reference frame with clapping target o, if nothing, jump to step 8, otherwise continue;
Specifically judge whether as follows with clapping the deterministic process of target o:
Step 301:Extract key frame FrIn, the n key point p that target o is included1, p2,…,pn, and its Feature Descriptor
fp1, fp2,…,fpn.In the present embodiment, key point we using the SIFT points commonly used in image procossing and the gradients of 128 dimensions
Direction histogram is used as description;
Step 302:Extract key frame FtIn m key point q1, q2,…,qN, and its Feature Descriptor fq1, fq2,…,
fqmIt is the gradient orientation histogram characteristic quantity of 128 dimensions.
Step 303:Calculate piAnd qjThe distance between son fd (i, j) is described, distance calculates to enter using Euclidean distance between point
OK.Specifically, to the sub- fp of description of 128 dimensionsi=[ρ i1,ρi2,...,ρi128] and fqi=[ρ j1,ρj2,...,ρj128] for:
Fd (i, j)=(ΣK=(1,2 ..., 128)(ρik-ρjk)2)1/2
After fd (i, j) is obtained, n dimensions Fd is further asked fori=minjfd(i,j);
Step 304:If FdiIn less than less than threshold epsilon quantity | { Fdi<ε}|>0.6 × n, then judge to be wrapped in present frame Ft
O containing target, is otherwise judged as that target is lost.
Step 4:With clapping the relative displacement d with reference frame of target in calculating present framet;
It is step 401,402,403 identical respectively at step 301,302 and 303;
Step 404:By FdiSort from small to large, take therein preceding 0.4, constitute set omega, calculate its corresponding point piWith
qjDisplacement d in frame of video coordinate systemij=(xij,yij), ask for dijX-component average value dx=1/ | Ω | × ΣΩ
{xij, as the displacement d in present frame with bat target relatively with reference framet;
Step 5:According to displacement dtAnd the displacement d of a upper controlling cyclet-1, calculate orbit camera device people's
Target speed governing increment Delta v=f (dt,dt-1)=f (dt, dt-1)=k1×dt+k2×dt-1, and platform speed is adjusted to vt+Δ
v;Here core control parameter k1And k2Needs obtain empirical value by a large amount of external testings, and after field deployment is completed, lead to
Cross correct on-the-spot selection.Step 6:Detect whether to receive the brake manipulation instruction of console, if nothing, jump to step 2, it is no
Then continue;
Step 7:Output terminates with bat process, jumps to step 9;
Step 8:Output loses information with clapping target;
Step 9:Exit with bat pattern.
Claims (5)
1. a kind of orbit camera device people's is autonomous with clapping traveling control method, it is characterised in that:It is specific to include following step successively
Suddenly:
Step 1:Implement photographer's manually determined tracking target o of remote control, and determine reference image frame Fr;
Step 2:With time T as controlling cycle, orbit camera device people obtains the frame of video F of current periodt;
Step 3:Judge FtWhether F is includedrIn with clap target o, if nothing, jump to step 8, otherwise continue;
Step 4:Calculate current video frame FtIn with clap target relative to reference image frame the displacement in frame of video coordinate system
dt;
Step 5:According to displacement dtAnd the displacement d of a upper controlling cyclet-1, calculate the target tune of orbit camera device people
Fast increment Delta v=f (dt,dt-1), and the platform speed of service is adjusted to vt+ Δ v, vtRefer to the operation speed of whole trolley platform
Degree;
Step 6:Detect whether to receive the brake manipulation instruction of console, if nothing, jump to step 2, otherwise continue;
Step 7:Output terminates with bat process, jumps to step 9;
Step 8:Output loses information with clapping target;
Step 9:Exit with bat pattern.
2. according to claim 1 orbit camera device people it is autonomous with clap traveling control method, it is characterised in that:The step
In rapid 1, reference image frame FrThe principle of determination is:The target o at least significant points of A% are located at B% in the middle of shooting image
In the Rc of region.
3. according to claim 1 orbit camera device people it is autonomous with clap traveling control method, it is characterised in that:The step
Rapid 3 detailed process is:
Step 301;Extract reference frame FrThe n key point p that middle target o is included1, p2,…,pn, and its corresponding feature retouches
State sub- fp1, fp2,…,fpn;
Step 302;Extract present frame FtIn m key point q1, q2,…,qm, and its corresponding Feature Descriptor fq1,
fq2,…,fqm;
Step 303:Calculate piAnd qjThe distance between son fd (i, j) is described between point, and asks for n dimensions Fdi=minjFd (i, j), i
=1,2 ..., n, j=j, 2 ..., m;
Step 304:If FdiIn less than less than threshold epsilon quantity | { Fdi<ε}|>μn(0<μ<1), then judge to be included in present frame Ft
Target o, is otherwise judged as that target is lost.
4. according to claim 1 orbit camera device people it is autonomous with clap traveling control method, it is characterised in that:The step
Rapid 4 specific method is, by the Fd of gained in step 3iSort from small to large, take preceding ρ therein and constitute set omega, and 0<ρ<1,
Then its corresponding key point p is calculatediAnd qjDisplacement d in frame coordinate systemij=(xij,yij), ask for dijX directions
Average value dx=1/ | Ω | × Σ of componentΩ{xij, as the displacement d in present frame with bat target relatively with reference framet;
Xij and yij represent the transverse and longitudinal coordinate value of a vector in frame coordinate system.
5. according to claim 1 orbit camera device people it is autonomous with clap traveling control method, it is characterised in that:The step
In rapid 5, the computing formula f (d of speed knots modification Δ vt,dt-1) it is proportional control mode, i.e. f (dt,dt-1)=k1×dt+k2×
dt-1, wherein, parameter k1And k2It is to be obtained by pre-stage test and scene.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710077249.6A CN106803880A (en) | 2017-02-14 | 2017-02-14 | Orbit camera device people's is autonomous with clapping traveling control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710077249.6A CN106803880A (en) | 2017-02-14 | 2017-02-14 | Orbit camera device people's is autonomous with clapping traveling control method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106803880A true CN106803880A (en) | 2017-06-06 |
Family
ID=58988515
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710077249.6A Pending CN106803880A (en) | 2017-02-14 | 2017-02-14 | Orbit camera device people's is autonomous with clapping traveling control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106803880A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108044596A (en) * | 2017-12-07 | 2018-05-18 | ***创新科技有限公司 | Photography machine people |
CN108044597A (en) * | 2017-12-07 | 2018-05-18 | ***创新科技有限公司 | Machinery performs structure and photography machine people |
CN109143899A (en) * | 2018-07-13 | 2019-01-04 | 南京理工大学 | A kind of implementation method of photography machine people host computer various control |
CN110633612A (en) * | 2019-11-20 | 2019-12-31 | 中通服创立信息科技有限责任公司 | Monitoring method and system for inspection robot |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101540890A (en) * | 2009-04-28 | 2009-09-23 | 南京航空航天大学 | Method for obtaining a clear face image of a moving human body in a monitored video |
CN101770568A (en) * | 2008-12-31 | 2010-07-07 | 南京理工大学 | Target automatically recognizing and tracking method based on affine invariant point and optical flow calculation |
CN102007516A (en) * | 2008-04-14 | 2011-04-06 | 汤姆森特许公司 | Technique for automatically tracking an object |
CN102438122A (en) * | 2010-09-29 | 2012-05-02 | 鸿富锦精密工业(深圳)有限公司 | Camera device and method for dynamically detecting monitoring object by using same |
CN103955950A (en) * | 2014-04-21 | 2014-07-30 | 中国科学院半导体研究所 | Image tracking method utilizing key point feature matching |
CN105574894A (en) * | 2015-12-21 | 2016-05-11 | 零度智控(北京)智能科技有限公司 | Method and system for screening moving object feature point tracking results |
-
2017
- 2017-02-14 CN CN201710077249.6A patent/CN106803880A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102007516A (en) * | 2008-04-14 | 2011-04-06 | 汤姆森特许公司 | Technique for automatically tracking an object |
CN101770568A (en) * | 2008-12-31 | 2010-07-07 | 南京理工大学 | Target automatically recognizing and tracking method based on affine invariant point and optical flow calculation |
CN101540890A (en) * | 2009-04-28 | 2009-09-23 | 南京航空航天大学 | Method for obtaining a clear face image of a moving human body in a monitored video |
CN102438122A (en) * | 2010-09-29 | 2012-05-02 | 鸿富锦精密工业(深圳)有限公司 | Camera device and method for dynamically detecting monitoring object by using same |
CN103955950A (en) * | 2014-04-21 | 2014-07-30 | 中国科学院半导体研究所 | Image tracking method utilizing key point feature matching |
CN105574894A (en) * | 2015-12-21 | 2016-05-11 | 零度智控(北京)智能科技有限公司 | Method and system for screening moving object feature point tracking results |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108044596A (en) * | 2017-12-07 | 2018-05-18 | ***创新科技有限公司 | Photography machine people |
CN108044597A (en) * | 2017-12-07 | 2018-05-18 | ***创新科技有限公司 | Machinery performs structure and photography machine people |
CN109143899A (en) * | 2018-07-13 | 2019-01-04 | 南京理工大学 | A kind of implementation method of photography machine people host computer various control |
CN110633612A (en) * | 2019-11-20 | 2019-12-31 | 中通服创立信息科技有限责任公司 | Monitoring method and system for inspection robot |
CN110633612B (en) * | 2019-11-20 | 2020-09-11 | 中通服创立信息科技有限责任公司 | Monitoring method and system for inspection robot |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109887040B (en) | Moving target active sensing method and system for video monitoring | |
CN109151439B (en) | Automatic tracking shooting system and method based on vision | |
CN110142785A (en) | A kind of crusing robot visual servo method based on target detection | |
Iwase et al. | Parallel tracking of all soccer players by integrating detected positions in multiple view images | |
CN106803880A (en) | Orbit camera device people's is autonomous with clapping traveling control method | |
CN105898107B (en) | A kind of target object grasp shoot method and system | |
CN107357286A (en) | Vision positioning guider and its method | |
CN105654512A (en) | Target tracking method and device | |
CN103424959B (en) | Image picking system and lens devices | |
CN110910459B (en) | Camera device calibration method and device and calibration equipment | |
CN106910206B (en) | Target tracking method and device | |
CN106054627B (en) | Control method and device based on gesture recognition and air conditioner | |
CN108020158A (en) | A kind of three-dimensional position measuring method and device based on ball machine | |
CN116309685A (en) | Multi-camera collaborative swimming movement speed measurement method and system based on video stitching | |
CN106447735A (en) | Panoramic camera geometric calibration processing method | |
KR101469099B1 (en) | Auto-Camera Calibration Method Based on Human Object Tracking | |
CN113506340A (en) | Method and equipment for predicting cloud deck pose and computer readable storage medium | |
Fahn et al. | A high-definition human face tracking system using the fusion of omni-directional and PTZ cameras mounted on a mobile robot | |
CN106067943A (en) | Control device, optical device, picture pick-up device and control method | |
Karungaru et al. | Ground sports strategy formulation and assistance technology develpoment: player data acquisition from drone videos | |
Perš et al. | Tracking people in sport: Making use of partially controlled environment | |
CN106846284A (en) | Active-mode intelligent sensing device and method based on cell | |
CN114594770A (en) | Inspection method for inspection robot without stopping | |
Matsumoto et al. | 3—22 Optimized Camera Viewpoint Determination System for Soccer Game Broadcasting | |
KR101649181B1 (en) | Flight information estimator and estimation method of the flying objects |
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: 20170606 |
|
RJ01 | Rejection of invention patent application after publication |