Face images of non-frontal views under poor illumination with low resolution reduce dramatically face recognition accuracy. This is evident most compellingly by the very low recog...
Depth Images are viable representations that can be computed from the real world using cameras and/or other scanning devices. The depth map provides 2-1 2 D structure of the scene...
Pooja Verlani, Aditi Goswami, P. J. Narayanan, She...
Occlusion and lack of visibility in dense crowded scenes make it very difficult to track individual people correctly and consistently. This problem is particularly hard to tackle i...
Recognition of complex activities from surveillance video requires detection and temporal ordering of its constituent "atomic" events. It also requires the capacity to ro...
A major challenge of novel scientific visualization using Augmented Reality is the accuracy of the user/camera position tracking. Many alternative techniques have been proposed, b...