Conventional approaches to dynamic scene analysis do not use motion itself explicitly for recognition. The authors propose a different approach for the use of motion in a computer vision system which uses the motion characteristics of moving objects without actually recovering the structure. In this approach, the extended trajectories followed by the objects are considered. It is argued that in many cases, where an object has a fixed and predefined motion, the trajectory of several points may serve to uniquely identify the object. In this approach, the trajectories are analyzed at multiple scales to identify important events corresponding to discontinuities in direction, speed, and acceleration using scale space. These important events are recorded in a presentation called trajectory primal sketch. Experimental results are presented graphically, demonstrating the potential value of this approach.<<ETX>>
[1]
Ishwar K. Sethi,et al.
Finding trajectories of points in a monocular image sequence
,
1985
.
[2]
Ramesh C. Jain,et al.
Pulse and staircase edge models
,
1986,
Comput. Vis. Graph. Image Process..
[3]
Michael Brady,et al.
The Curvature Primal Sketch
,
1986,
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[4]
Andrew P. Witkin,et al.
Scale-Space Filtering
,
1983,
IJCAI.
[5]
Kiyotaka Asada.
異好抗体に関する研究 第1編 流行性肝炎の流行と異好抗体について
,
1959
.
[6]
Andrew P. Witkin,et al.
Scale-space filtering: A new approach to multi-scale description
,
1984,
ICASSP.
[7]
R. Haralick,et al.
The Topographic Primal Sketch
,
1983
.