A harmonic retrieval framework for discontinuous motion estimation

被引:18
作者
Chen, WG [1 ]
Giannakis, GB
Nandhakumar, N
机构
[1] Microsoft Corp, Redmond, WA 98052 USA
[2] Univ Virginia, Dept Elect Engn, Charlottesville, VA 22903 USA
[3] LG Elect Res Ctr Amer Inc, Princeton, NJ 08550 USA
基金
美国国家科学基金会;
关键词
compression; computer vision; discontinuous motion; harmonic retrieval; motion estimation; multimedia; multiple motion; video communication;
D O I
10.1109/83.709656
中图分类号
TP18 [人工智能理论];
学科分类号
081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];
摘要
Motion discontinuities arise when there are occlusions or multiple moving objects in the scene that is imaged, Conventional regularization techniques use smoothness constraints but are not applicable to motion discontinuities. In this paper, we show that discontinuous (or multiple) motion estimation can be viewed as a multicomponent harmonic retrieval problem. From this viewpoint, a number of established techniques for harmonic retrieval can be applied to solve the challenging problem of discontinuous (or multiple) motion, Compared with existing techniques, the resulting algorithm is not iterative, which not only implies computational efficiency but also obviates concerns regarding convergence or local minima. It also adds flexibility to spatio-temporal techniques which have suffered from lack of explicit modeling of discontinuous motion. Experimental verification of our framework on both synthetic data as well as real image data is provided.
引用
收藏
页码:1242 / 1257
页数:16
相关论文
共 32 条
[1]
SPATIOTEMPORAL ENERGY MODELS FOR THE PERCEPTION OF MOTION [J].
ADELSON, EH ;
BERGEN, JR .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1985, 2 (02) :284-299
[2]
ON THE COMPUTATION OF MOTION FROM SEQUENCES OF IMAGES - A REVIEW [J].
AGGARWAL, JK ;
NANDHAKUMAR, N .
PROCEEDINGS OF THE IEEE, 1988, 76 (08) :917-935
[3]
[4]
A COMPUTATIONAL FRAMEWORK AND AN ALGORITHM FOR THE MEASUREMENT OF VISUAL-MOTION [J].
ANANDAN, P .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1989, 2 (03) :283-310
[5]
[Anonymous], 1981, Time series data analysis and theory, DOI 10.1201/b15288-24
[6]
[Anonymous], ADAPTIVE FILTER THEO, DOI DOI 10.1109/ISCAS.2017.8050871
[7]
PERFORMANCE OF OPTICAL-FLOW TECHNIQUES [J].
BARRON, JL ;
FLEET, DJ ;
BEAUCHEMIN, SS .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1994, 12 (01) :43-77
[8]
BLACK MJ, 1994, COMPUT VIS ECCV 94, V1, P138
[9]
Brodatz P, 1966, TEXTURES PHOTOGRAPHI
[10]
Image motion estimation from motion smear - A new computational model [J].
Chen, WG ;
Nandhakumar, N ;
Martin, WN .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1996, 18 (04) :412-425