We describe some techniques that can be used to represent and detect deformable shapes in images. The main difficulty with deformable template models is the very large or infinite...
We present a two-layer hierarchical formulation to exploit different levels of contextual information in images for robust classification. Each layer is modeled as a conditional f...
In this paper, detection of pedestrian groups and counting of the number of pedestrians in each group using “subtraction stereo” are discussed. Subtraction stereo is a stereo v...
We propose a novel learning algorithm to detect moving pedestrians from a stationary camera in real-time. The algorithm learns a discriminative model based on eigenflow, i.e. the ...
Kernel-based objective functions optimized using the mean shift algorithm have been demonstrated as an effective means of tracking in video sequences. The resulting algorithms com...
Gregory D. Hager, Maneesh Dewan, Charles V. Stewar...