Title :
Recursive filters for optical flow
Author :
Fleet, David J. ; Langley, Keith
Author_Institution :
Dept. of Comput. & Inf. Sci., Queen´´s Univ., Kingston, Ont., Canada
fDate :
1/1/1995 12:00:00 AM
Abstract :
Working toward efficient (real-time) implementations of optical flow methods, the authors have applied simple recursive filters to achieve temporal smoothing and differentiation of image intensity, and to compute 2d flow from component velocity constraints using spatiotemporal least-squares minimization. Accuracy in simulation is similar to that obtained in the study by Barren et al. (1994), while requiring much less storage, less computation, and shorter delays
Keywords :
image sequences; least squares approximations; minimisation; recursive filters; smoothing methods; 2d flow; component velocity constraints; differentiation; image intensity; optical flow; recursive filters; spatiotemporal least-squares minimization; temporal smoothing; Band pass filters; Delay; Filtering; Image motion analysis; Low pass filters; Navigation; Optical computing; Optical devices; Optical filters; Spatiotemporal phenomena;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
