Single Image Segmentation with Estimated Depth

Abstract

A novel framework for automatic object segmentation is proposed that exploits depth information estimated from a single image as an additional cue. For example, suppose that we have an image containing an object and a background with a similar color or tex- ture to the object. The proposed framework enables us to automatically extract the object from the image while eliminating the misleading background. Although our segmenta- tion framework takes a form of a traditional formulation based on Markov random fields, the proposed method provides a novel scheme to integrate depth and color information, which derives objectness/backgroundness likelihood. We also employ depth estimation via supervised learning so that the proposed method can work even if it has only a single input image with no actual depth information. Experimental results with a dataset origi- nally collected for the evaluation demonstrate the effectiveness of the proposed method against the baseline method and several existing methods for salient region detection.

Publication
British Machine Vision Conference (BMVC)

Related