Unsupervised video segmentation and object tracking

In many problems involving advanced computer-aided production, for example, navigation of robots in production and maintenance, automatic inspection and testing of manufactured parts, etc., automatic segmentation of video signals into constituent objects is essential. In the current work, we present a formulation for unsupervised video segmentation and object tracking. This formulation does not require the supervision of a human user. Each frame in the video is partitioned into different segments and the segments are combined to form object traces. We provide an algorithm that simultaneously partitions a video frame and obtains the parameters of the underlying classes. The problem of partitioning each frame is posed as a joint estimation of the partition and class parameter variables. By incorporating the partition information of the previous frame into the segmentation process of the current frame, our method implicitly uses the temporal information. Experimental results show that our method succeeds in capturing the object classes even when the objects undergo translations and rotations not in the plane of the image.