This research introduces a method of predicting tracking failures and applies it to the robust analysis of human gait. The body is represented using a multicomponent structural model. For each component, the proposed approach extracts features from tracked noise covariance matrices and uses them to construct an observation sequence for a hidden Markov model (HMM) trained to detect tracking failures. When transformed with a logarithmic function, the conditional output probability of the HMM is shown to have a causal relationship with imminent tracking failures. This fusion of multiple structural models with a reliable means of failure prediction facilitates the successful tracking and extraction of gait variables. Results are demonstrated on numerous video sequences.

This research presents a new model-based approach toward the three-dimensional (3-D) tracking and extraction of gait and human motion. We suggest the use of a hierarchical, structural model of the human body that introduces the concept of soft kinematic constraints. These constraints take the form of a priori, stochastic distributions learned from previous configurations of the body exhibited during specific activities; they are used to supplement an existing motion model limited by hard kinematic constraints. We use time-varying parameters of the structural model to measure gait velocity, stance width, stride length, stance times, and other gait variables with multiple degrees of accuracy and robustness. To characterize tracking performance, we also introduce a novel geometric model of expected tracking failures. We demonstrate and quantify the performance of the suggested models using multi-view, video sequences of human movement captured in a complex home environment.

We describe a thorough quantitative analysis of a novel, kinematic model of the human body used for the tracking and extraction of gait variables. The model includes multiple levels of structural complexity coupled with absolute and probabilistic kinematic constraints; while the relevant variables include velocity, stride length, stance width, and stance times. The analysis is based on the accuracy of extracted gait variables for various permutations of the proposed kinematic body model. Using patterns of complex human motion collected from a multi-camera video monitoring system, we demonstrate the precise costs and benefits associated with various model components and kinematic constraints.

A semiautomated feature extraction algorithm is presented for the extraction and measurement of the hippocampus from volumetric magnetic resonance imaging (MRI) head scans. This algorithm makes use of elements of both deformable model and region growing techniques and allows incorporation of a priori operator knowledge of hippocampal location and shape. Experimental results indicate that the algorithm is able to estimate hippocampal volume and asymmetry with an accuracy which approaches that of laborious manual outlining techniques.

The in vivo morphological and volumetric analysis of biological structures is a topic which is of increasing interest in the medical community. Such an analysis requires the extraction of the feature of interest from volumetric magnetic resonance (MR), ultrasound (US) or computed tomography (CT) scans. The difficulty of this extraction varies with the modality used and the morphology of the structure of interest, but in many cases current practice requires the manual outlining of the structure on each slice of the scanned volume-a time consuming and tedious task. We seek to provide an automated algorithm which accomplishes this task with minimal a priori knowledge and operator input and with an accuracy which is comparable to that of the current manual and semi-automated techniques.

In order to obtain a 3-D reconstruction of the hippocampus from a volumetric MRI head study, it is necessary to separate it not only from the surrounding white matter, but also from contiguous areas of gray matter. At present it is necessary for a physician to manually segment the hippocampus on each slice of the volume in order to obtain such a reconstruction. The authors propose a novel technique by which a computer may make an unsupervised identification of a given structure through a series of images, even if that structure includes so-called false contours or missing contours. Applications include 3-D reconstruction of difficult-to-segment regions of the brain and abdomen, and volumetric measurements of organs from series of 2-D images.>