An approach to the segmentation of textured dynamic scenes

Jayaramamurthy, S.N.; Jain, Ramesh

doi:10.1016/0146-664x(82)90050-8

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various approaches have been proposed to deal with different phases of analysis. These include the segmentation of moving human body from the background and extraction of low-level features A hybrid architecture design ( Jayaramamuthy and Jain, 1983;Thompson and Barnard, 1981), body part location which includes moving parts tracking and labeling of the extracted regions (Akita, 1984;Leung and Yang, 1995), and motion pattern analysis (Ferrigno et al, 1990;Rashid, 1980).…”

Section: Introductionmentioning

confidence: 99%

A hybrid architecture design for security monitoring via the Internet

Fong

Hui²

2003

Kybernetes

View full text Add to dashboard Cite

We present the development of a Web-based remote-monitoring system as an attractive alternative to the manual task of security surveillance. The system has built-in human motion analysis that can alert the security personnel when suspicious activities are detected at the monitored sites. In this paper, our focus is on the architectural design of such a system. We discuss the relative strengths and weaknesses of three different architectural approaches: centralized, distributed and hybrid, and conclude that a hybrid approach is most appropriate. Our Web-based system has been implemented for monitoring elevators (lifts) within a university environment. Objective and subjective tests have validated the effectiveness of our system. The Web-based implementation enhances ease of operation and allows users to connect to the system via a Web browser.

show abstract

Section: Introductionmentioning

confidence: 99%

A hybrid architecture design for security monitoring via the Internet

Fong

Hui²

2003

Kybernetes

View full text Add to dashboard Cite

show abstract

“…This strategy is decades old. In the early of the 80s, Jain et al [7,8] used inter-frame differencing to estimate moving objects. More recent works, using background subtraction based segmentation, range from modeling pixels as mixture Gaussian distribution [19,5,3,4] to the more involved Wallflower method [18].…”

Section: Introductionmentioning

confidence: 99%

Challenges in Segmentation of Human Forms in Outdoor Video

Liu

Sarkar

2004 Conference on Computer Vision and Pattern Recognition Workshop

View full text Add to dashboard Cite

Most gait and activity recognition algorithms rely on the use of silhouettes as the low-level representation. However, the detection of good silhouettes is still an open problem, particularly for sequences that are taken outdoors. Illumination conditions, compression artifacts, and low number of pixels on the subject, contribute to the difficulty. Presently, these issues are either ignored by using indoor data or addressed, on a case by case basis, by employing, essentially, a "bag of tricks" based approach. We argue for a more formal approach, based on generic shape and motion models to handle a variety of these problems, under the umbrella of one formalism. We present an HMM-based Eigen Stance model, built based on manually created silhouettes from 71 individuals. The population HMM helps map a frame in any given sequence to a stance and the appearance based Eigen-Stance model is used to reconstruct the computed silhouette in that frame. We quantify the performance in terms of signal based criteria of missed detection and false positive prediction rate. We also show results on three different databases.

show abstract

An approach to the segmentation of textured dynamic scenes

Cited by 2 publications

References 0 publications

A hybrid architecture design for security monitoring via the Internet

A hybrid architecture design for security monitoring via the Internet

Challenges in Segmentation of Human Forms in Outdoor Video

Contact Info

Product

Resources

About