Human motion analysis is receiving increasing at-tention from computer vision researchers. This inter-est is motivated by a wide spectrum of applications, such as athletic performance analysis, surveillance, man-machine interfaces, content-based image storage and retrieval, and video conferencing. This paper gives an overview of the various tasks involved in motion analysis of the human body. We focus on three major areas related to interpreting human motion: 1) motion analysis involving human body parts, 2) tracking of human motion wing single or multiple cameras, and 8) recognizing human activities from image sequences. Motion analysis of human body parts involves the low-level segmentation of the human body into segments connected by joints, and recovers the 3D structure of the human body using its 20 projections over a se-quence of images. Ilfacking human motion wing a single or multiple cameras focuses on higher-level pro-cessing, in which moving humans are tracked without identifying specific parts of the body structure. After successfully matching the moving human image)?om one frame to another in image sequences, understand-ing the human movements or activities comes natu-rally, which leads to our discussion of recognizing hu-man activities. The review is illustrated by ezamples. 1

In this paper we introduce a template-based method for recognizing human actions called Action MACH. Our approach is based on a Maximum Average Correlation Height (MACH) filter. A common limitation of template-based methods is their inability to generate a single template using a collection of examples. MACH is capable of capturing intra-class variability by synthesizing a single Action MACH filter for a given action class. We generalize the traditional MACH filter to video (3D spatiotemporal volume), and vector valued data. By analyzing the response of the filter in the frequency domain, we avoid the high computational cost commonly incurred in template-based approaches. Vector valued data is analyzed using the Clifford Fourier transform, a generalization of the Fourier transform intended for both scalar and vector-valued data. Finally, we perform an extensive set of experiments and compare our method with some of the most recent approaches in the field by using publicly available datasets, and two new annotated human action datasets which include actions performed in classic feature films and sports broadcast television. 1.

This paper presents a framework for tracking human motion in an indoor environment from sequences of monocular grayscale images obtained from multiple fixed cameras. Multivariate Gaussian models are applied to find the most likely matches of human subjects between consecutive frames taken by cameras mounted in various locations. Experimental results from real data show the robustness of the algorithm and its potential for real time applications. 1. Introduction Tracking human motion in an indoor environment is of interest in applications of surveillance. In particular, we are developing a methodology to track individuals at sites such as corridors, airports, borders, and secured buildings. This requires that the viewing system be able to image the tracked subject in a broad area over a long period of time. In pursuit of this goal, our work has evolved from studying human walking using a fixed camera [1, 2] to tracking non-background objects in a single moving camera [3]. The studies i...

This paper presents an approach to tracking human motion in a sequence of monocular images. The process consists of detecting motion, segmenting moving subjects by recovering the background and, finally, tracking the subject of interest. The usual assumptions of small image motion, a fixed viewing system and constant velocity are systematically relaxed. Two cases are studied: 1) a viewing system with negligible motion, and 2) a viewing system with nonnegligible motion. 1. INTRODUCTION Tracking human motion in a sequence of monocular images is of growing interest in applications such as surveillance, image compression, and content-based multimedia storage and retrieval. In this paper, we describe a framework to detect, segment, and track a sequence of monocular images of humans moving in an indoor environment. The common set of assumptions in tracking human motion includes small image motion[1, 2, 3, 4] , a fixed viewing system [5, 6, 1, 2, 3, 4, 7], constant velocity[7], uniform inte...

This paper describes a self-learning prototype system for the real-time detection of unusual motion patterns. The proposed surveillance system uses a three-step approach consisting of a tracking, a learning and a recognition part. In the rst step, an arbitrary, changing number of objects are tracked with an extension of the Condensation algorithm. From the history of the tracked object states, temporal trajectories are formed which describe the motion paths of these objects. Secondly, characteristic motion patterns are learned by clustering these trajectories into prototype curves. In the nal step, motion recognition is then tackled by tracking the position within these prototype curves based on the same method, the extended Condensation algorithm, used for the object tracking.

We propose a framework for detecting, tracking and analyzing non-rigid motion based on learned motion patterns. The framework features an appearance based approach to represent the spatial information and Hidden Markov Models (HMM) to encode the temporal dynamics of the time varying visual patterns. The low level spatial feature extraction is fused with the temporal analysis, providing a unified spatio-temporal approach to common detection, tracking and classification problems. This is a promising approach for many classes of human motion patterns. Visual tracking is achieved by extracting the most probable sequence of target locations from a video stream using a combination of random sampling and the forward procedure from HMM theory. The method allows us to perform a set of important tasks such as activity recognition, gait-analysis and keyframe extraction. The efficacy of the method is shown on both natural and synthetic test sequences. 1.

Abstract. Human body is an articulated object with high degrees of freedom. Despite the high dimensionality of the configuration space, many human motion activities lie intrinsically on low dimensional manifolds. Although the intrinsic body configuration manifolds might be very low in dimensionality, the resulting appearance manifolds are challenging to model given various aspects that affects the appearance such as the shape and appearance of the person performing the motion, or variation in the view point, or illumination. Our objective is to learn representations for the shape and the appearance of moving (dynamic) objects that support tasks such as synthesis, pose recovery, reconstruction, and tracking. We studied various approaches for representing global deformation manifolds that preserve their geometric structure. Given such representations, we can learn generative models for dynamic shape and appearance. We also address the fundamental question of separating style and content on nonlinear manifolds representing dynamic objects. We learn factorized generative models that explicitly decompose the intrinsic body configuration (content) as a function of time from the appearance/shape (style factors) of the person performing the action as time-invariant parameters. We show results on pose recovery, body tracking, gait recognition, as well as facial expression tracking and recognition. 1

Being able to detect and track human hands is one of the keys to understanding human goals, intentions, and actions. In this paper, we take the first steps towards real-time detection and tracking of human hands in dynamic crowded or cluttered scenes. We have built a prototype hand detection system based on Viola, Jones, and Snow's dynamic detector, which was originally constructed to detect and track pedestrians in outdoor surveillance imagery. The detector combines motion and appearance information to rapidly classify image sub-windows as either containing or not containing a hand. A preliminary evaluation of the system indicates that it has promise.

In this study we are proposing a fuzzy-based rule system for tracking people by using simple tracking algorithms. A simple hue, saturation, and value (HSV) histogram-based color model was used to develop our system. We started by separating the moving object region from the background region by comparing the current frame with the constructed background image. In this paper, as a first step we obtained a motion image through the acquisition and segmentation of video sequences. In this situation where object shadows appear in the background region, a pre-processing median filter is applied to the input image to reduce the shadow effect, before identifying major blobs. The second step includes generating a set of blobs from detected varied regions in each image sequence. When objects are closer the segmented object gets rejected and is thereby detected as a single object. This error can be rectified by using fuzzy logic..

Surveillance video recording is becoming ubiquitous in daily life for public areas such as supermarkets, banks, and airports. The rate at which surveillance video is being generated has accelerated demand for machine understanding to enable better content-based search capabilities. Analyzing human activity is one of the key tasks to understand and search surveillance videos. In this thesis, we perform a comprehensive study on analyzing human activities from short term to long term and from simple to complicated activities in surveillance video achieves. A general, efficient and robust human activity recognition framework is proposed. We extract local descriptors at salient points from videos to represent human activities. The local descriptor is called Motion SIFT (MoSIFT) which explicitly augments appearance features with motion information. A quantization and classification framework then applies the descriptors to recognize activities of interest in surveillance