A harmonic retrieval framework for discontinuous motion estimation

13 years 8 months ago

Download spincom.umn.edu

Abstract— Motion discontinuities arise when there are occlusions or multiple moving objects in the scene that is imaged. Conventional regularization techniques use smoothness constraints but are not applicable to motion discontinuities. In this paper, we show that discontinuous (or multiple) motion estimation can be viewed as a multicomponent harmonic retrieval problem. From this viewpoint, a number of established techniques for harmonic retrieval can be applied to solve the challenging problem of discontinuous (or multiple) motion. Compared with existing techniques, the resulting algorithm is not iterative, which not only implies computational efﬁciency but also obviates concerns regarding convergence or local minima. It also adds ﬂexibility to spatio-temporal techniques which have suffered from lack of explicit modeling of discontinuous motion. Experimental veriﬁcation of our framework on both synthetic data as well as real image data is provided.

Wei-Ge Chen, Georgios B. Giannakis, N. Nandhakumar

Real-time Traffic