Bøger af Rama Chellappa

This monograph is an outgrowth of the authors' recent research on the de- velopment of algorithms for several low-level vision problems using artificial neural networks. Specific problems considered are static and motion stereo, computation of optical flow, and deblurring an image. From a mathematical point of view, these inverse problems are ill-posed according to Hadamard. Researchers in computer vision have taken the "e;regularization"e; approach to these problems, where one comes up with an appropriate energy or cost function and finds a minimum. Additional constraints such as smoothness, integrability of surfaces, and preservation of discontinuities are added to the cost function explicitly or implicitly. Depending on the nature of the inver- sion to be performed and the constraints, the cost function could exhibit several minima. Optimization of such nonconvex functions can be quite involved. Although progress has been made in making techniques such as simulated annealing computationally more reasonable, it is our view that one can often find satisfactory solutions using deterministic optimization algorithms.

The recognition of humans and their activities from video sequences is currently a very active area of research because of its applications in video surveillance, design of realistic entertainment systems, multimedia communications, and medical diagnosis. In this lecture, we discuss the use of face and gait signatures for human identification and recognition of human activities from video sequences. We survey existing work and describe some of the more well-known methods in these areas. We also describe our own research and outline future possibilities. In the area of face recognition, we start with the traditional methods for image-based analysis and then describe some of the more recent developments related to the use of video sequences, 3D models, and techniques for representing variations of illumination. We note that the main challenge facing researchers in this area is the development of recognition strategies that are robust to changes due to pose, illumination, disguise, and aging. Gait recognition is a more recent area of research in video understanding, although it has been studied for a long time in psychophysics and kinesiology. The goal for video scientists working in this area is to automatically extract the parameters for representation of human gait. We describe some of the techniques that have been developed for this purpose, most of which are appearance based. We also highlight the challenges involved in dealing with changes in viewpoint and propose methods based on image synthesis, visual hull, and 3D models. In the domain of human activity recognition, we present an extensive survey of various methods that have been developed in different disciplines like artificial intelligence, image processing, pattern recognition, and computer vision. We then outline our method for modeling complex activities using 2D and 3D deformable shape theory. The wide application of automatic human identification and activity recognition methods will require the fusion of different modalities like face and gait, dealing with the problems of pose and illumination variations, and accurate computation of 3D models. The last chapter of this lecture deals with these areas of future research.

Provides a comprehensive overview of domain adaptation solutions for visual recognition problems. By starting with the problem description and illustrations, it discusses three adaptation scenarios - unsupervised adaptation, semi-supervised adaptation, and multi-domain heterogeneous adaptation.

Compressed sensing or compressive sensing is a new concept in signal processing where one measures a small number of non-adaptive linear combinations of the signal.

Human Identification Based on Gait is the first book to address gait as a biometric. This book clearly establishes how human gait is biometric. Human Identification Based on Gait is structured to meet the needs of professionals in industry, as well as advanced-level students in computer science.

Face recognition has been actively studied over years. This work provides a comprehensive review of this biometric, especially face recognition from video, assembling a collection of various approaches that are able to recognize human faces under various unconstrained situations. It is useful for researchers and practitioners in the industry.