Automatic Streaming Segmentation of Stereo Video Using Bilateral Space

TL;DR

This paper introduces an unsupervised stereo video segmentation method that embeds depth information into bilateral space, achieving high accuracy and efficiency without user input, suitable for complex natural scenes.

Contribution

The novel integration of depth into bilateral grid within a semi-supervised graph cut framework enhances stereo video segmentation accuracy without supervision.

Findings

High segmentation precision demonstrated

Efficient processing suitable for real-time applications

Effective in complex natural environments

Abstract

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.