Abstract Target detection and tracking is one of the most important and fundamental technologies to develop real world computer vision systems such as security and traffic monitori...
We present a novel variational approach to estimate dense depth maps from multiple images in real-time. By using robust penalizers for both data term and regularizer, our method pr...
A variety of sensors and positioning methods have been developed over the years. Most methods rely on active sensors (such as sonars or lasers) which have range and power restrict...
David P. Miller, Anne Wright, Randy Sargent, Rob C...
Many parameter estimation problems admit divide and conquer or partitioning techniques in order to reduce a highdimensional task into several reduced-dimension problems. These tec...
We derive a probabilistic framework for robust, real-time, visual tracking of previously unseen objects from a moving camera. The tracking problem is handled using a bag-of-pixels ...