This paper describes a viewpoint invariant learningbased method for counting people in crowds from a single camera. Our method takes into account feature normalization to deal wit...
We introduce a novel outlook on the self-calibration task, by considering images taken by a camera in motion, allowing for zooming and focusing. Apart from the complex relationshi...
We present a model to estimate motion from monocular visual and inertial measurements. We analyze the model and characterize the conditions under which its state is observable, an...
— This paper proposes a methodology of video–stream output at the receiver for enhancing QoE (Quality of Experience) in audio–video IP transmission. The methodology copes wit...
In this paper, we present a novel method for intra-operative registration directly from monocular endoscopic images. This technique has the potential to provide a more accurate su...
Darius Burschka, Ming Li, Russell H. Taylor, Grego...