Dynamic Scene Analysis
Fundamental concepts of computer vision. Extraction of dynamic information from image sequences. Image differencing. Background subtraction. Optical flow estimation methods. Motion-based image segmentation. Object detection and tracking. Using active contour models (snakes) for object tracking. Model-based object tracking. Probabilistic approaches to object tracking. Differential extraction and tracking of rectangular features (Harris, KLT). Matching invariant features (DOG, SIFT). Geometrical aspects of computer vision: image formation, camera calibration, geometry of one, two and multiple views. Robust parameter estimation. Applications: video surveilance, traffic surveilance, object motion analysis, video compression, navigation, traffic sign detection, recognition and tracking.