This paper presents a fast, accurate, and novel method for the problem of estimating the number of humans and their positions from background differenced images obtained from a single camera where inter-human occlusion is significant. The problem is challenging firstly because the state space formed by the number, positions, and articulations of people is large. Secondly, in spite of many advances in background maintenance and change detection, background differencing remains a noisy and imprecise process, and its output is far from ideal: holes, fill-ins, irregular boundaries etc. pose additional challenges for our "mid- level" problem of segmenting it to localize humans. We propose a novel example-based algorithm which maps the global shape feature by Fourier descriptors to various configurations of humans directly. We use locally weighted averaging to interpolate for the best possible candidate configuration. The inherent ambiguity resulting from the lack of depth and layer information in the background difference images is mitigated by the use of dynamic programming, which finds the trajectory in state space that best explains the evolution of the projected shapes. The key components of our solution are simple and fast. We demonstrate the accuracy and speed of our approach on real image sequences.

We present a tunable representation for tracking that simultaneously encodes appearance and geometry in a manner that enables the use of mean-shift iterations for tracking. The classic formulation of the tracking problem using mean-shift iterations encodes spatial information very loosely (i.e. using radially symmetric kernels). A problem with such a formulation is that it becomes easy for the tracker to get confused with other objects having the same feature distribution but different spatial configurations of features. Subsequent approaches have addressed this issue but not to the degree of generality required for tracking specific classes of objects and motions (e.g. humans walking). In this paper, we formulate the tracking problem in a manner that encodes the spatial configuration of features along with their density and yet retains robustness to spatial deformations and feature density variations. The encoding of spatial configuration is done using a set of kernels whose parameters can be optimized for a given class of objects and motions, off-line. The formulation enables the use of meanshift iterations and runs in real-time. We demonstrate better tracking results on synthetic and real image sequences as compared to the original mean-shift tracker.

In this paper, a novel robust tracking algorithm in compressed video is proposed. Within the framework of video compression standards, we consider how to accurately estimate motion of an object by utilizing motion vectors available in compressed video together with derived confidence measures. These confidence measures are based on DCT coefficients, spatial continuity of motion and texture measure of the object. We perform tracking directly on the compressed data and also consider tracking of an object with image scale change. In order to achieve robust tracking, we develop a system which enables us to detect object appearance change such as illumination change and occlusion by exploring the confidence measures derived above. Preliminary results indicate that our tracking algorithm works well with a variety of video sequences

The main problem for building a mosaic is the computation of the warping functions (homographies). In fact two cases are to be distinguished. The first is when the homography is mainly a translation (i.e. The rotation around the optical axis and the zooming factor are small). The second is the general case (when the rotation around the optical axis and zooming are arbitrary). Some efficient methods have been developed to solve the first case. But the second case is more difficult, in particular, when the rotation around the optical axis is very large (90 degrees or more). Often in this case human interaction is needed to provide a first approximation of the transformation that will bring one back to the first case. The authors present a method to solve this problem without human interaction for any rotation around the optical axis and fairly large zooming factors.