An active contour-based video object segmentation scheme for stereoscopic video sequences

A modified snake-based scheme is presented for unsupervised stereoscopic semantic segmentation. The scheme utilizes the provided depth information and the power of active contours to adjust to object edges. Each stereo pair is analyzed and a depth map is constructed. Then a multiresolution implementation of the recursive shortest spanning tree (RSST) segmentation algorithm is applied to the depth field to generate depth segments. Afterwards a novel edge map, free of several non-object edges, is constructed. The next step includes the initialization of the modified snake. The constructed edge map empowers the snake to move towards the object while, at the same time, its new bending energy decreases the computational complexity. Finally the active contour extracts the video object planes (VOP). Experimental results indicate the reliable performance of the proposed scheme on real life stereoscopic video sequences.