In biological and medical imaging applications, tracking objects in motion is a critical task. This book describes the state-of-the-art in biomedical tracking techniques. We begin by detailing methods for tracking using active contours, which have been highly successful in biomedical applications. The book next covers the major probabilistic methods for tracking. Starting with the basic Bayesian model, we describe the Kalman filter and conventional tracking methods that use centroid and correlation measurements for target detection. Innovations such as the extended Kalman filter and the interacting multiple model open the door to capturing complex biological objects in motion. A salient highlight of the book is the introduction of the recently emerged particle filter, which promises to solve tracking problems that were previously intractable by conventional means. Another unique feature of Biomedical Image Analysis: Tracking is the explanation of shape-based methods for biomedical image analysis. Methods for both rigid and nonrigid objects are depicted. Each chapter in the book puts forth biomedical case studies that illustrate the methods in action.
Biomedical Image Analysis: Tracking addresses methods for extracting image information from biological/medical images for use in tracking biological targets. Here, and in the forthcoming companion Biomedical Image Analysis: Segmentation (Morgan & Claypool, ISBN: 1598290207), the authors concentrate on aspects of image analysis rather than the modalities or the imaging process itself. This lecture will be a valuable resource for graduate students, faculty, and industrial/governmental researchers interested in applications of imaging, or more specifically, biomedical imaging. It is written from first principles and will be accessible to a broad readership.