We extend the work of Black and Yacoob on the tracking and recognition of human facial expressions using parameterized models of optical flow to deal with the articulatedmotion of...
- This paper presents a global method to process monocular image sequences for mobile robot obstacle detection. We do not aim to achieve a complete scene reconstruction, but only t...
This paper proposes a two-step methodology for improving the discriminatory power of Linear Discriminant Analysis (LDA) for video-based human face recognition. Results indicate th...
We presen t a multiview method for the computation of object shape and re ectance characteristics based on the integration of shape from shading (SFS) and stereo, for nonconstan t...
Dimitris Samaras, Dimitris N. Metaxas, Pascal Fua,...
Abstract. Brightness values of pixels in an image are related to image irradiance by a non-linear function, called the radiometric response function. Recovery of this function is i...