In this paper we propose a new motion compensated prediction technique that enables successful predictive encoding during fades, blended scenes, temporally decorrelated noise, and...
Markerless tracking of human pose is a hard yet relevant problem. In this paper, we derive an efficient filtering algorithm for tracking human pose at 4-10 frames per second using...
Varun Ganapathi, Christian Plagemann, Sebastian Th...
We present a background model that differentiates between background motion and foreground objects. Unlike most models that represent the variability of pixel intensity at a partic...
Remote sensing of terrain characteristics is an important component for autonomous operation of mobile robots in natural terrain. Often this involves classification of terrain int...
Disability of visual text reading has a huge impact on the quality of life for visually disabled people. One of the most anticipated devices is a wearable camera capable of findi...