The combination of subtraction stereo with shadow detection we propose improves people tracking in stereoscopic environments. Subtraction stereo is a stereo matching method which is fast and robust for the correspondence problem – one of the most serious issues in computer vision – restricting the search range of matching to foreground regions. Shadow detection gives adequate foreground regions...

Visual processing of people, including detection, tracking, recognition, and behavior interpretation, is a key component of intelligent video surveillance systems. Computer vision algorithms with the capability of “looking at people” at multiple scales can be applied in different surveillance scenarios, such as far-field people detection for wide-area perimeter protection, midfield people detec...

W 4 is a real time visual surveillance system for detecting and tracking people and monitoring their activities in an outdoor environment. It operates on monocular grayscale video imagery, or on video imagery from an infrared camera. Unlike many of systems for tracking people, W 4 makes no use of color cues. Instead, W 4 employs a combination of shape analysis and tracking to locate people and ...

Let M be a simply connected complex submanifold of C . We prove that M is irreducible, up a totally geodesic factor, if and only if the normal holonomy group acts irreducibly. This is an extrinsic analogue of the well-known De Rham decomposition theorem for a complex manifold. Our result is not valid in the real context, as it is shown by many counter-examples.

Since their inception, social networking sites (SNSs) have experienced exponential growth. While substantial research has been dedicated to users’ initial adoption of SNSs, the fall of MySpace reminds us that the long-term success of SNSs depends on users’ post adoption staying power. Inspired by this, this work-in-progress investigates users’ “stickiness” with a specific SNS. Based on Li et al...

This paper reports on an empirical investigation of the relationship between print and hypertext reading skills. Subjects in the study were university students at a public Midwestern university. A repeated-measures, counter-balanced design was employed. Subjects were categorized as highand low-ability readers based on a standardized measure of reading achievement. Experimental tasks required su...

Content contribution from individuals is critical to the viability of online communities. In this study we identify the factors that are associated with the quantity and the quality of content sharing in a photo sharing community, where the act of content creation is decoupled from the act of content sharing. We draw on theories of intrinsic and extrinsic motivation, and find that the prospect ...

W 4 is a real time visual surveillance system for detecting and tracking people and monitoring their activities in an outdoor environment. It operates on monocular grayscale video imagery, or on video imagery from an infrared camera. Unlike many of systems for tracking people, W 4 makes no use of color cues. Instead, W 4 employs a combination of shape analysis and tracking to locate people and ...

We present a novel method for dynamic estimation of pose of multiple people using multiple video cameras. Tracking is performed using a model-based approach and a set of cues which exploit both shape and colour information. For shape we propose a fast line-search method to incorporate multi-view constraints without the computational overhead of a voxel representation. The tracking algorithm is ...

The paper describes a scheme for detecting and tracking people in images. The method effectively combines statistical information about the class of people with motion information for classification and tracking. In this scheme, the u n h o w n distribution of the rmages of people is approximately modeled by learning higher order statistics (HOS) information of the ‘people class’ from sample im...