The computation of optical flow
ACM Computing Surveys (CSUR)
Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Improved Fast Gauss Transform and Efficient Kernel Density Estimation
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
IEEE Transactions on Pattern Analysis and Machine Intelligence
Consistent Segmentation for Optical Flow Estimation
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
CONTROL'05 Proceedings of the 2005 WSEAS international conference on Dynamical systems and control
Video object segmentation using Bayes-based temporal tracking and trajectory-based region merging
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
Unsupervised motion segmentation and tracking in video sequences is a complex task, requiring robust estimation and flexible modeling. The paper presents an unsupervised method of moving object segmentation and tracking in video sequences captured by static cameras. Central to our work is the nonparametric density estimation and the mean shift algorithm for finding local maxima of the probability density. Foreground segmentation obtained from background estimation is combined with simultaneous region tracking and segmentation followed by connectivity-based moving object segmentation, in order to obtain an efficient processing algorithm. Preliminary tests asses the viability of the proposed approach.