2014 IEEE Winter Conference on Applications of Computer Vision (WACV) (2014)
Steamboat Springs, CO, USA
March 24, 2014 to March 26, 2014
Radu Dondera , University of Maryland, College Park, USA
Vlad Morariu , University of Maryland, College Park, USA
Yulu Wang , University of Maryland, College Park, USA
Larry Davis , University of Maryland, College Park, USA
We propose an interactive video segmentation system built on the basis of occlusion and long term spatio-temporal structure cues. User supervision is incorporated in a superpixel graph clustering framework that differs crucially from prior art in that it modifies the graph according to the output of an occlusion boundary detector. Working with long temporal intervals (up to 100 frames) enables our system to significantly reduce annotation effort with respect to state of the art systems. Even though the segmentation results are less than perfect, they are obtained efficiently and can be used in weakly supervised learning from video or for video content description. We do not rely on a discriminative object appearance model and allow extracting multiple foreground objects together, saving user time if more than one object is present. Additional experiments with unsupervised clustering based on occlusion boundaries demonstrate the importance of this cue for video segmentation and thus validate our system design.
Image edge detection, Image segmentation, Optical imaging, Image color analysis, Detectors, Motion segmentation, Adaptive optics
R. Dondera, V. Morariu, Yulu Wang and L. Davis, "Interactive video segmentation using occlusion boundaries and temporally coherent superpixels," 2014 IEEE Winter Conference on Applications of Computer Vision (WACV), Steamboat Springs, CO, USA, 2014, pp. 784-791.