Video background modeling is an important preprocessing stage for various applications, and principal component pursuit (PCP) is\namong the state-of-the-art algorithms for this task. One of the main drawbacks of PCP is its sensitivity to jitter and camera\nmovement. This problem has only been partially solved by a few methods devised for jitter or small transformations. However, such\nmethods cannot handle the case of moving or panning cameras in an incremental fashion. In this paper, we greatly expand the results\nof our earlier work, in which we presented a novel, fully incremental PCP algorithm, named incPCP-PTI, which was able to cope with\npanning scenarios and jitter by continuously aligning the low-rank component to the current reference frame of the camera. To the\nbest of our knowledge, incPCP-PTI is the first low-rank plus additive incremental matrix method capable of handling these scenarios\nin an incremental way. The results on synthetic videos and Moseg, DAVIS, and CDnet2014 datasets show that incPCP-PTI is able to\nmaintain a good performance in the detection of moving objects even when panning and jitter are present in a video. Additionally, in\nmost videos, incPCP-PTI obtains competitive or superior results compared to state-of-the-art batch methods.
Loading....