Automatic Streaming Segmentation of Stereo Video Using Bilateral Space
This work addresses the problem of automatic video segmentation for practical applications in complex natural scenarios, representing an incremental improvement.
The paper tackles unsupervised segmentation of stereo video by embedding depth information into a bilateral grid within a graph cut model, achieving high precision and time efficiency without user input.
In this paper, we take advantage of binocular camera and propose an unsupervised algorithm based on semi-supervised segmentation algorithm and extracting foreground part efficiently. We creatively embed depth information into bilateral grid in the graph cut model and achieve considerable segmenting accuracy in the case of no user input. The experi- ment approves the high precision, time efficiency of our algorithm and its adaptation to complex natural scenario which is significant for practical application.