A robust optical flow computation algorithm utilizing the trajectories of feature points has been developed. For some applications of optical flows, correct optical flows though they are not so many are more useful than unreliable ones at every pixel point. The proposed algorithm is for detecting the optical flows only at the feature points. The optical flow vectors are extracted from the trajectory segments of feature points on which distance information is developed through the Distance Transform. A multi-layer CNN structure and nonlinear templates for the proposed algorithm are suggested and examined. The simulation result shows that the proposed algorithm is robust against noise even without any preprocessing.
|Number of pages||10|
|Journal||IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation|
|Publication status||Published - Dec 1 2000|
|Event||2000 IEEE Workshop on Signal Processing Systems (SIPS 2000) - Lafayette, LA, USA|
Duration: Oct 11 2000 → Oct 13 2000
ASJC Scopus subject areas