Title :
Multiframe feature-based motion analysis
Author_Institution :
Inst. for Robotics & Intelligent Syst., Univ. of Southern California, Los Angeles, CA, USA
Abstract :
An overview is given of the important aspects of feature-based motion analysis, especially with regard to more than two frames. These topics include some history of feature-based techniques, reasons to use feature-based techniques and longer sequences, applications to real motion sequences, and some directions for this kind of research. It is pointed out that feature-based motion analysis involves work on several subproblems such as feature extraction, feature matching, motion estimation, and the use of the motion estimates. The final use of the motion analysis can be for target tracking 3D reconstruction and improved matching results. Real-world motion analysis programs must assume that the computed feature matches are only good enough for motion estimation, and not perfect. Feature-based systems offer many ways to achieve good performance with real-world data
Keywords :
computerised pattern recognition; computerised picture processing; feature extraction; feature matching; motion estimates; motion estimation; multiframe feature-based motion analysis; target tracking 3D reconstruction; History; Humans; Image motion analysis; Information analysis; Intelligent robots; Layout; Motion analysis; Optical noise; Optical sensors; Target tracking;
Conference_Titel :
Pattern Recognition, 1990. Proceedings., 10th International Conference on
Conference_Location :
Atlantic City, NJ
Print_ISBN :
0-8186-2062-5
DOI :
10.1109/ICPR.1990.118075