CN1766928A - A kind of motion object center of gravity track extraction method based on the dynamic background sport video - Google Patents

A kind of motion object center of gravity track extraction method based on the dynamic background sport video Download PDF

Info

Publication number
CN1766928A
CN1766928A CN 200510055216 CN200510055216A CN1766928A CN 1766928 A CN1766928 A CN 1766928A CN 200510055216 CN200510055216 CN 200510055216 CN 200510055216 A CN200510055216 A CN 200510055216A CN 1766928 A CN1766928 A CN 1766928A
Authority
CN
China
Prior art keywords
motion
motion object
background
center
gravity
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
Application number
CN 200510055216
Other languages
Chinese (zh)
Inventor
邱显杰
夏时洪
王兆其
李***
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Institute of Computing Technology of CAS
Original Assignee
Institute of Computing Technology of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Institute of Computing Technology of CAS filed Critical Institute of Computing Technology of CAS
Priority to CN 200510055216 priority Critical patent/CN1766928A/en
Publication of CN1766928A publication Critical patent/CN1766928A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a kind of motion object center of gravity track extraction method, be used for extracting the barycenter trajectory of motion object at the video of background motion based on the dynamic background sport video; This method may further comprise the steps: the interframe to frame of video is done overall motion estimation, innings kinematic parameter of demanding perfection; According to the global motion parameter, the foreground moving zone of disengaging movement object, the background of reconstitution movement image; The realization background is eliminated, and is partitioned into the motion subject area fast; Record motion history information obtains complete motion subject area; Extract motion object outline; Ask motion object barycenter trajectory.The invention has the advantages that: can be used for various types of motion objects, have good versatility; Just can obtain the two-dimentional center of gravity of motion object by the computing of advantages of simplicity and high efficiency two dimension, can reach real-time effect.

Description

A kind of motion object center of gravity track extraction method based on the dynamic background sport video
Technical field
The present invention relates to a kind of motion object center of gravity track extraction method of sport video, particularly a kind of motion object center of gravity track extraction method based on the dynamic background sport video.
Background technology
Utilizing video that the motion motion of objects is analyzed is the hot issue in pattern-recognition, virtual reality, Intelligent Human-Machine Interface field, has great using value.For example, in the sports video athletic motion is analyzed, for instructing trainer and athletic training, improving the level of training and competitiveness has important directive significance.
Wherein, the two-dimentional barycenter trajectory of motion object when carrying out specific action is an extremely important parameter in the motion analysis, if can from video, obtain the two-dimentional barycenter trajectory of motion object in the motion process, just can provide strong foundation for the quality of judging the performed action of motion object.For example,, just can provide effective means,, improve the level of training and competitiveness and have important value improving athletic moving-mass for instructing athletic training if be applied in the sports video.
So-called dynamic background sport video is meant that in sequence of video images comprised the video of the motion of video camera, therefore, the scene background of dynamic background sport video changes.For example, in diving, in the sports videos such as gymnastics, camera position can move along with the motion motion of objects, Here it is so-called dynamic background sport video.
Corresponding with the dynamic background sport video is the static background sport video, and it is meant in sequence of video images, the video that scene background is constant.For example, in the trampolining video, video camera is actionless, and scene background also is static, so the trampolining video just belongs to the static background sport video.
If the barycenter trajectory of motion object in motion process in the video can be extracted, helps the motion motion of objects is analyzed.And compare with the motion object center of gravity track extraction method based on the static background sport video, range of application is wider undoubtedly based on the motion object center of gravity track extraction method of dynamic background video, has more great use value and practical significance.
But, in the existing Video processing software at home and abroad, all do not provide the function of motion object barycenter trajectory in this automatic extraction dynamic background video.When the patent retrieval of being correlated with, do not retrieve the information of any relevant patent yet.
Summary of the invention
The purpose of this invention is to provide a kind of motion object center of gravity track extraction method, be implemented in and extract motion object barycenter trajectory in the video of background motion based on the dynamic background sport video.
To achieve these goals, the invention provides a kind of motion object center of gravity track extraction method based on the dynamic background sport video, the main operational steps of this method is as follows:
1) interframe of frame of video is done overall motion estimation, innings kinematic parameter of demanding perfection;
2) according to the global motion parameter, the foreground moving zone of disengaging movement object, the background of reconstitution movement image;
3) realize the background elimination, be partitioned into the motion subject area fast;
4) record motion history information obtains complete motion subject area;
5) extract motion object outline;
6) ask motion object barycenter trajectory.
In the technique scheme, the record motion history information in step 4) is achieved in that
Calculate the binaryzation template of present frame and previous frame;
Ask the prospect binaryzation template of previous frame;
Ask the common factor of the prospect binaryzation template of the binaryzation template of present frame and previous frame and previous frame, obtain temporary transient static motion subject area;
Temporary transient static motion subject area is eliminated the foreground area merging that obtains with background obtain complete motion subject area.
In the technique scheme, the extraction of motion object outline is to adopt the Snake method to realize in step 5).
In the technique scheme, in step 6), ask the two-dimentional center of gravity that requires the motion object in the single frame before the motion object barycenter trajectory, utilize the global motion parameter that each two-dimentional gravity-center-change is formed barycenter trajectory to designated frame then.
The two-dimentional center of gravity of described motion object is to try to achieve by the geometric center of asking the two dimensional motion object outline.
The invention has the advantages that:
1, the inventive method has realized the extraction to motion object barycenter trajectory in the dynamic background sport video, is with a wide range of applications and great use value.
2, the inventive method can be used for various types of motion objects, has good versatility.
3, the present invention just can obtain the two-dimentional center of gravity of motion object by the computing of advantages of simplicity and high efficiency two dimension, can reach real-time effect.
Description of drawings
Fig. 1 is that the motion object barycenter trajectory of dynamic background video extracts process flow diagram.
Embodiment
Below in conjunction with accompanying drawing, the method for the invention is described further.
As shown in Figure 1, be the process flow diagram of present embodiment method, expression operation in the frame of broken lines in the process flow diagram, the result that the expression associative operation obtains in the solid box.
A kind of motion object center of gravity track extraction method based on the dynamic background sport video of the present invention mainly is divided into following steps:
The video at step 10. pair motion object place extracts sequence of frames of video, and each frame in the video is done the interframe overall motion estimation, obtains the global motion parameter between each frame.Global motion is meant the motion of the pixel that accounts for larger proportion in video sequence frame, how to be caused by camera motion in sport video.Overall motion estimation is meant according to two two field pictures, the rule of global motion between the estimated image, and its rule can be by the global motion parametric representation.In sport video, adopt 6 parameter affined transformation model representations to represent global motion usually, for example: establish p=(x i, y i) be present frame I tCoordinate, p '=(x i', y i') be former frame I T-1On coordinate, correspondence between them relation can be expressed as p=θ T, t-1P ', wherein, θ T, t-1=(a, b, c, d, e, f) be camera motion, it specifically represents the global motion rule between i frame and its former frame i-1 frame, component e wherein, and f is relevant with the translation motion of camera lens, component a, b, c, d then with the convergent-divergent of camera lens, rotatablely move relevant.The acquiring method of global motion parameter has multiple, for example: θ T, t-1Initial solution can be right by between consecutive frame, selecting certain characteristics point, and use Minimum Mean Square Error rule tries to achieve, and progressively improves precision by iteration then.Said method is a prior art, and those skilled in the art should be easy to realize finding the solution the global motion parameter.
The global motion parameter that step 20. utilizes step 10 to obtain, the foreground moving zone of disengaging movement object, the background of tectonic movement image.
A1, the global motion parameter of asking for by previous step are carried out the pointwise conversion to the pixel of present frame former frame image.For example, the pixel of former frame (x, y) through after the global motion parameter transformation in present frame just corresponding to (pixel intensity of these two points is identical for X, Y) position.
After b1, the process conversion, just can compare the difference between these adjacent two frames, note discrepant zone between two frames, this zone has comprised the foreground moving zone of motion object in two frames.Obtained the foreground moving zone of motion object in two frames, just the foreground area of motion object can have been separated, to eliminate the foreground area influence synthetic background.In fact the process of above-mentioned comparison two frame differences is similar to XOR notion in logic, is 0 when promptly both are identical, and both are not 1 simultaneously.
C1, owing to there is a global motion, the background area of the consecutive frame of present frame is not exclusively the same with the background area of present frame, so to carrying out whole background area that xor operation can not get present frame through the pixel of later two frames of global change.Because the background of present frame has disappearance, its part background must be obtained from consecutive frame.Through the inverse transformation of global motion conversion, just can know present frame disappearance background pixel correspondence be which partial pixel of its consecutive frame.The missing pixel of filling up corresponding present frame with those pixels of consecutive frame just can realize the polishing of present frame background.
Step 30. realizes the elimination of background, is partitioned into the motion subject area fast.After the background of present frame is able to reconstruct, can be partitioned into the motion subject area apace by the background elimination.The concrete grammar that background is eliminated, present embodiment can be represented with following formula: make D kFor the frame of background after eliminating poor, D then k(p)=| W * I k(p)-B k(p) |, wherein, W is a smoothing operator, is a known factor, I k(p) expression present frame, B k(p) background of expression present frame.Then to D kCarry out the black and white binaryzation, just can obtain prospect template M k BBecause the accumulated error during background is aimed at, the The noise such as error of interpolation calculation are at prospect template M k BThere is the small size noise region that causes because of these factors in middle meeting, therefore also needs to use connection constituent analysis and morphology opening operation elimination M k BIn the small size noise region and keep and to have larger area motion subject area.
Step 40. record motion history information, the motion object cuts apart in the realization frame of video.If certain a part of health transfixion in a period of time of motion object, then this a part of health might be retained in the background of being constructed, background is eliminated in the resulting motion subject area in back just this a part of body region can not occur, and this a part of body region can be referred to as static foreground area.In order to address the above problem, to the binaryzation template D of present frame and previous frame K, k-1With previous frame motion subject area template M K-1Carry out logical operation, detect static foreground area M k HD K, k-1Be meant the frame difference of present frame and previous frame image is carried out resulting image template after the binary conversion treatment, M K-1Find the solution and following M kMethod for solving similar, both are relations of iteration.Obtain static foreground area M k HAfter, itself and background are eliminated the motion subject area M that obtains k BMerge and obtain complete motion subject area M k, that is:
M k H ( p ) = 1 M k - 1 comp ( p ) = land D k , k - 1 ( p ) = 0 0 else
M k = M k B ∪ M k H
M wherein K-1 CompBe previous frame motion subject area template through spatially aliging with present frame behind the global motion compensation.
Obtain complete motion subject area M kAlso just mean finishing of motion Object Segmentation in the frame of video.
Step 50. is extracted motion object outline after obtaining the motion subject area.In the present embodiment, the extracting method of motion object outline adopts movable contour model Snake.Movable contour model Snake is used to realize the rim detection of object or the effective tool that profile extracts in current Flame Image Process and computer vision.Specifically, snake is a defined deformable curve in image area, by to the minimizing and be out of shape and the natural shape of adjusting snake is mated specific object of its energy function, thereby produces the profile of continuously smooth.That is to say, when the energy of snake for hour, snake and object match..The shape of movable contour model (snake) is controlled by the internal force of curve itself and the external force of view data, and the power on the snake of acting on is dependent on the residing position of profile and its shape will change partly in the space.Effect is different to internal force with external force: internal force plays the smoothness constraint effect, and external force then guides snake to move to characteristics of image.The details of Snake method can be referring to list of references 1 " based on the DP correction algorithm of movable contour model ", Shanghai University's journal, 1999 the 5th the 5th phases of volume.The advantage of utilization Snake method is accurately to extract the motion contours of objects.
Utilize the concrete steps of Snake method to be:
A2, with the initial position setting of Snake on the edge of motion subject area, the external energy of Snake can be given by the space-time gradient;
Minimizing of the gross energy of b2, Snake can obtain by the rapid solving based on greedy algorithm;
C2, when the gross energy of Snake reaches hour, just can extract the motion contours of objects.
Motion object outline in the video is two-dimentional, has therefore also just obtained the two-dimensional silhouette information in the video when obtaining motion object outline.
Step 60, by motion object outline, ask the two-dimentional center of gravity of motion object.The two-dimentional center of gravity of motion object can obtain by the simple two-dimensional computing.The simple two-dimensional computing just is meant the geometric center of calculating the two dimensional motion object outline, for example:
If G LMotion object outline zone for L two field picture in the video sequence; And (X 1, Y 1), (X 2, Y 2) ..., (X n, Y n) be component movement object outline zone G LAll pixels, then (X is the two-dimentional barycenter trajectory point coordinate of this two field picture just Y), wherein:
X = ( X 1 + X 2 + · · · + X n n ) , Y = ( Y 1 + Y 2 + · · · + Y n n ) .
The center of gravity of motion object is through after the global motion compensation in step 70, the single frame that will try to achieve, barycentric coordinates are transformed into the frame of an appointment, as initial frame, then the center of gravity of the motion object in each frame is done same operation, in designated frame, obtain the track of continuous motion object center of gravity at last.

Claims (5)

1, a kind of motion object center of gravity track extraction method based on the dynamic background sport video is used for the barycenter trajectory at the video extraction motion object of background motion; This method may further comprise the steps:
1) interframe of frame of video is done overall motion estimation, innings kinematic parameter of demanding perfection;
2) according to the global motion parameter, the foreground moving zone of disengaging movement object, the background of reconstitution movement image;
3) realize the background elimination, be partitioned into the motion subject area fast;
4) record motion history information obtains complete motion subject area;
5) extract motion object outline;
6) ask motion object barycenter trajectory.
2, the motion object center of gravity track extraction method based on the dynamic background sport video according to claim 1 is characterized in that, the record motion history information in the step 4) is achieved in that
Calculate the binaryzation template of present frame and previous frame;
Ask the prospect binaryzation template of previous frame;
Ask the common factor of the prospect binaryzation template of the binaryzation template of present frame and previous frame and previous frame, obtain temporary transient static motion subject area;
Temporary transient static motion subject area is eliminated the foreground area merging that obtains with background obtain complete motion subject area.
3, the motion object center of gravity track extraction method based on the dynamic background sport video according to claim 1 is characterized in that, the extraction of motion object outline is to adopt the Snake method to realize in the step 5).
4, the motion object center of gravity track extraction method based on the dynamic background sport video according to claim 1, it is characterized in that, ask motion object barycenter trajectory to require the two-dimentional center of gravity of the motion object in the single frame before in the step 6), utilize the global motion parameter that each two-dimentional gravity-center-change is formed barycenter trajectory to designated frame then.
5, the motion object center of gravity track extraction method based on the dynamic background sport video according to claim 4 is characterized in that the two-dimentional center of gravity of described motion object is to try to achieve by the geometric center of asking the two dimensional motion object outline.
CN 200510055216 2004-10-29 2005-03-16 A kind of motion object center of gravity track extraction method based on the dynamic background sport video Pending CN1766928A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 200510055216 CN1766928A (en) 2004-10-29 2005-03-16 A kind of motion object center of gravity track extraction method based on the dynamic background sport video

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN200410086743.1 2004-10-29
CN200410086743 2004-10-29
CN 200510055216 CN1766928A (en) 2004-10-29 2005-03-16 A kind of motion object center of gravity track extraction method based on the dynamic background sport video

Publications (1)

Publication Number Publication Date
CN1766928A true CN1766928A (en) 2006-05-03

Family

ID=36742795

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 200510055216 Pending CN1766928A (en) 2004-10-29 2005-03-16 A kind of motion object center of gravity track extraction method based on the dynamic background sport video

Country Status (1)

Country Link
CN (1) CN1766928A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101819164A (en) * 2010-05-14 2010-09-01 山东大学 Device and method for detecting impurities after filling of beverage
CN101588501B (en) * 2008-05-19 2012-06-20 索尼株式会社 Image processing apparatus and image processing method
CN101751549B (en) * 2008-12-03 2014-03-26 财团法人工业技术研究院 Method for tracking moving object
CN103776604A (en) * 2014-02-13 2014-05-07 山东理工大学 Trampoline impacting ball detecting method
CN104240291A (en) * 2014-09-03 2014-12-24 中国科学院计算技术研究所 Image segmentation and reconstruction method and system based on nuclear magnetic resonance image sequences
WO2018028363A1 (en) * 2016-08-09 2018-02-15 深圳光启合众科技有限公司 Target object tracking method and device
CN115999135A (en) * 2022-12-15 2023-04-25 华中科技大学 Snowmobile sled simulator control method and system based on somatosensory control

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101588501B (en) * 2008-05-19 2012-06-20 索尼株式会社 Image processing apparatus and image processing method
CN101751549B (en) * 2008-12-03 2014-03-26 财团法人工业技术研究院 Method for tracking moving object
CN101819164A (en) * 2010-05-14 2010-09-01 山东大学 Device and method for detecting impurities after filling of beverage
CN103776604A (en) * 2014-02-13 2014-05-07 山东理工大学 Trampoline impacting ball detecting method
CN103776604B (en) * 2014-02-13 2016-02-10 山东理工大学 Trampoline impacts ball detection method
CN104240291A (en) * 2014-09-03 2014-12-24 中国科学院计算技术研究所 Image segmentation and reconstruction method and system based on nuclear magnetic resonance image sequences
CN104240291B (en) * 2014-09-03 2017-10-27 中国科学院计算技术研究所 A kind of image segmentation method for reconstructing and system based on nuclear magnetic resonance image sequence
WO2018028363A1 (en) * 2016-08-09 2018-02-15 深圳光启合众科技有限公司 Target object tracking method and device
CN107730534A (en) * 2016-08-09 2018-02-23 深圳光启合众科技有限公司 The tracking and device of destination object
CN107730534B (en) * 2016-08-09 2020-10-23 深圳光启合众科技有限公司 Target object tracking method and device
CN115999135A (en) * 2022-12-15 2023-04-25 华中科技大学 Snowmobile sled simulator control method and system based on somatosensory control
CN115999135B (en) * 2022-12-15 2024-05-14 华中科技大学 Snowmobile sled simulator control method and system based on somatosensory control

Similar Documents

Publication Publication Date Title
US11210803B2 (en) Method for 3D scene dense reconstruction based on monocular visual slam
CN103268480B (en) A kind of Visual Tracking System and method
CN106780576B (en) RGBD data stream-oriented camera pose estimation method
CN1131439C (en) Target tracking method and device therefor
CN1270542C (en) Method for compressing video image
CN109903328B (en) Object volume measuring device and method applied to smart phone
CN1766928A (en) A kind of motion object center of gravity track extraction method based on the dynamic background sport video
CN108597009B (en) Method for detecting three-dimensional target based on direction angle information
TW202004679A (en) Image feature extraction method and saliency prediction method including the same
CN101640809A (en) Depth extraction method of merging motion information and geometric information
CN105046649A (en) Panorama stitching method for removing moving object in moving video
CN112837344A (en) Target tracking method for generating twin network based on conditional confrontation
CN100337473C (en) Panorama composing method for motion video
CN108200432A (en) A kind of target following technology based on video compress domain
CN115619826A (en) Dynamic SLAM method based on reprojection error and depth estimation
CN115375733A (en) Snow vehicle sled three-dimensional sliding track extraction method based on videos and point cloud data
CN102917220A (en) Dynamic background video object extraction based on hexagon search and three-frame background alignment
CN111161219B (en) Robust monocular vision SLAM method suitable for shadow environment
CN1766929A (en) A kind of motion object motion reconstructing method based on three-dimensional data base
CN105243673B (en) A kind of method for estimating, movement estimation system and its application based on Block- matching
CN105913084A (en) Intensive track and DHOG-based ultrasonic heartbeat video image classifying method
CN116524026B (en) Dynamic vision SLAM method based on frequency domain and semantics
CN100337472C (en) Video composing method with motion prospect
CN1770204A (en) Method for extracting barycenter trajectory of motive object from motive video with static background
CN102917222B (en) Mobile background video object extraction method based on self-adaptive hexagonal search and five-frame background alignment

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication