A motion panorama is an efficient and compact representation of the underlying video. However, the motion panorama construction process is computationally intensive and hence extr...
Yong Wei, Hongyu Wang, Suchendra M. Bhandarkar, Ka...
Abstract. Motion estimation is essential in a variety of image processing and computer vision tasks, like video coding, tracking, directional filtering and denoising, scene analys...
In this paper, we propose an adaptive 3D-DCT compression technique, which dynamically determines an optimal size of the video cube based on the motion analysis. The technique cons...
Borko Furht, Ken Gustafson, Hesong Huang, Oge Marq...
Motion segmentation is an essential process for many computer vision algorithms. During the last decade, a large amount of work has been trying to tackle this challenge, however, p...
Most previous motion deblurring methods restore the degraded image assuming a shift-invariant linear blur filter. These methods are not applicable if the blur is caused by spatial...