Model-based recognition and motion tracking depends upon the ability to solve for projection and model parameters that will best fit a 3-D model to matching 2-D image features. This paper extends current methods of parameter solving to handle objects with arbitrary curved surfaces and with any number of internal parameters representing articulations, variable dimensions, or surface deformations. Numerical

We present a new technique for tracking 3D objects from 2D image sequences through the integration of qualitative and quantitative techniques. The deformable models are initialized based on a previously developed part-based qualitative shape segmentation system. Using a physics-based quantitative approach, objects are subsequently tracked without feature correspondence based on generalized forces computed from the stereo images. The automatic prediction of possible edge occlusion and disocclusion is performed using an extended Kalman filter. To cope with possible occlusion caused by a previously undetected object, we monitor the magnitude and direction of the computed image forces exerted on the models. Abrupt changes to these forces trigger scene re-segmentation and model re-initialization through the qualitative shape segmentation system. Tracking is subsequently continued using only local image forces. We demonstrate our technique in experiments involving image ...

At the heart of every model-based visual tracker lies a pose estimation routine.

Moving vehicles are detected and tracked automatically in monocular image sequences from road traffic scenes recorded by a stationary camera. In order to exploit the a priori knowledge about shape and motion of vehicles in traffic scenes, a parameterized vehicle model is used for an intraframe matching process and a recursive estimator based on a motion model is used for motion estimation. An interpretation cycle supports the intraframe matching process with a state MAP-update step. Initial model hypotheses are generated using an image segmentation component which clusters coherently moving image features into candidate representations of images of a moving vehicle. The inclusion of an illumination model allows to take shadow edges of the vehicle into account during the matching process. Only such an elaborate combination of various techniques has enabled us to track vehicles under complex illumination conditions and over long (over 400 frames) monocular image sequences. Results on various real world road traffic scenes are presented and open problems as well as future work are outlined. 1