Automatic Segmentation of Non-rigid Objects in Image Sequences Using Spatiotemporal Information

Abstract

This paper provides an automatic segmentation method of non-rigid objects in image sequences. The non-rigid objects have fuzzy, blurred, and indefinite boundaries such as smoke and clouds, and are random and unpredictable in spatial and temporal domains. To segment the non-rigid objects, a new segmentation approach considering random and unpredictable characteristics of the non-rigid objects is needed. In this paper, we propose a new segmentation method of the non-rigid objects in image sequences using spatiotemporal information. The procedure toward complete segmentation consists of three steps: spatial segmentation, temporal segmentation, and fusion of the spatial and temporal segmentation results. By means of experiments on various test sequences, we demonstrate that the performance of our method is quite impressive from the viewpoints of the segmentation accuracy.KeywordsSegmentation ResultMarkov Random FieldAutomatic SegmentationTable TennisTemporal SegmentationThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.