Low-level image analysis systems typically detect "points of interest", i.e., areas of natural images that contain corners or edges. Most of the robust and computationall...
This paper reports on the implementation of a GPUbased, real-time eye blink detector on very low contrast images acquired under near-infrared illumination. This detector is part o...
Marc Lalonde, David Byrns, Langis Gagnon, Normand ...
Abstract. Computation time is an important performance characteristic of computer vision algorithms. This paper shows how existing (slow) binary-valued decision algorithms can be a...
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...
Consider the task of a mobile robot autonomously navigating through an environment while detecting and mapping objects of interest using a noisy object detector. The robot must re...