Real-Time Detection, Tracking and Recognition
The key idea of our approach is to formulate the abilities to detect, recognize and to track as classification problems. By doing so we can apply the same techniques for all tasks. The major advantage is that low-level computations can be shared and have to be done only once.
For each frame the integral representation needs to be computed only once which is then used by all three modules for feature computation. Note that each unit selects appropriate features for the specific task however computation time of the features is negligible.
The used hardware setup consists of an ActiveMedia Peoplebot platform including diverse sensors (e.g. sonar, IR). The robot’s head has thirteen degrees of freedom and can move its eyes, mouth, eyebrows, forehead, chin and neck. A Dual Core Centrino with 2 GHz and 1024 MB RAM represents the main processing unit. A stereo camera from Videre Design STH-MDCS2-VAR (max. 1280 × 960 used: 640 × 480) is used for capturing images and about 12 frames per seconds are processed with a non optimized C++ implementation.
