We consider di usion processes on a class of R trees. The processes are de ned in a manner similar to that of Le Gall's Brownian snake. Each point in the tree has a real value...
We present an image-based Simultaneous Localization and Mapping (SLAM) framework with online, appearanceonly loop closing. We adopt a layered approach with metric maps over small ...
Interactive segmentation is useful for selecting objects of interest in images and continues to be a topic of much study. Methods that grow regions from foreground/background seed...
The classical optical flow assumes that a feature point maintains constant brightness across the frames. For fluidtype motions such as smoke or clouds, the constant brightness ass...
We present an active learning framework to simultaneously learn appearance and contextual models for scene understanding tasks (multi-class classification). Existing multi-class a...