A Framework for Evaluating Video Object Segmentation Algorithms

Segmentation of moving objects in image sequences plays an important role in video processing and analy-sis. Evaluating the quality of segmentation results is nec-essary to allow the appropriate selection of segmentation algorithms and to tune their parameters for optimal per-formance. Many segmentation algorithms have been pro-posed along with a number of evaluation criteria. Never-theless, no psychophysical experiments evaluating the qual-ity of different video object segmentation results have been conducted. In this paper, a generic framework for segmen-tation quality evaluation is presented. A perceptually driven automatic method for segmentation evaluation is proposed and compared against an existing approach. Moreover, on the basis of subjective results, perceptual factors are intro-duced into the novel objective metric to meet the specificity of different segmentation applications such as video com-pression. Experimental results confirm the efficiency of the proposed evaluation criteria. 1