High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
In this work a new method is proposed for coding artifact reduction of MPEG compressed video sequences. The method makes use of a simple cost-effective technique that allows the b...
In this paper, we propose a novel technique for modelbased recognition of complex object motion trajectories using Hidden Markov Models (HMM). We build our models on Principal Com...
Faisal I. Bashir, Wei Qu, Ashfaq A. Khokhar, Dan S...
Aerial video provides strong cues for automatic road extraction that are not available in static aerial images. Using stabilized (or geo-referenced) video data, capturing the dist...
The advance of technology makes video acquisition devices better and less costly, thereby increasing the number of applications that can effectively utilize digital video. Compare...