Spatiotemporal energy-based method for velocity estimation

Abstract We present a spatiotemporal energy-based method for the estimation of optical flow for a fixed camera, which exploits the boundary informations between the moving objects and a motionless background. This method, named controlled filtering, is inspired by the architecture of Gabor filters introduced by D. Heeger in 1987. The method consists of motion estimation dependent on boundaries between the moving objects and a motionless background, guided by the result of prior detection of moving objects. The choice of the filter's standard deviations is complex. We propose a new approach based on distance criteria. Though the energy-based methods are reputed to require intensive calculations, we describe an efficient numerical implementation of this method, with recursive Gabor filters.

[1]  Lucas J. van Vliet,et al.  Recursive implementation of the Gaussian filter , 1995, Signal Process..

[2]  D J Heeger,et al.  Model for the extraction of image flow. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[3]  Eric Dubois,et al.  Bayesian Estimation of Motion Vector Fields , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  R. S. Jasinchi.  Intrinsic constraints in space-time filtering: a new approach to representing uncertainty in low-level vision , 1992 .

[5]  David J. Fleet,et al.  Performance of optical flow techniques , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Donald Geman,et al.  Boundary Detection by Constrained Optimization , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Johan Wiklund,et al.  Image Sequence Analysis for Object Tracking. , 1987 .

[8]  Hans-Hellmut Nagel,et al.  Motion Boundary Detection in Image Sequences by Local Stochastic Tests , 1994, ECCV.

[9]  Don R. Hush,et al.  Change detection for target detection and classification in video sequences , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[10]  Patrick Bouthemy,et al.  Multimodal Estimation of Discontinuous Optical Flow using Markov Random Fields , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Siu-Leong Iu.  Robust Estimation of Motion Vector Fields with Discontinuity and Occlusion Using Local Outliers Rejection , 1995, J. Vis. Commun. Image Represent..

[12]  R. Holub,et al.  Response of Visual Cortical Neurons of the cat to moving sinusoidal gratings: response-contrast functions and spatiotemporal interactions. , 1981, Journal of neurophysiology.

[13]  M. Unser.  Fast Gabor-like windowed Fourier and continuous wavelet transforms , 1994, IEEE Signal Processing Letters.

[14]  Patrick Bouthemy,et al.  Motion detection robust to perturbations: A statistical regularization and temporal integration framework , 1993, 1993 (4th) International Conference on Computer Vision.

[15]  Azriel Rosenfeld,et al.  A Pyramid Framework for Early Vision , 1994 .