A belief theory-based static posture recognition system for real-time video surveillance applications

Girondel, Vincent; Caplier, Alice; Bonnaud, Laurent

doi:10.1109/avss.2005.1577235

Cited by 5 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We present the classification results obtained when using the maximum belief mass as criterion. Comparison between criteria and subsequent classifiers is available in [51]. Training step and test step recognition rates are available in Tables 2 and 3.…”

Section: Posture Recognition Resultsmentioning

confidence: 99%

“…Most of the research work done on the human body as a whole is mainly gait analysis and recognition, or recognition of simple interactions between people, or between people and objects. In this section, we present a method to recognise a set of four static human body postures (standing, sitting, squatting, and lying) thanks to data fusion using the belief theory [50,51].…”

Section: High-level Human Behaviour Interpretation: Static Posture Rementioning

confidence: 99%

See 1 more Smart Citation

A Human Body Analysis System

Girondel

Bonnaud

Caplier

2006

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

This paper describes a system for human body analysis (segmentation, tracking, face/hands localisation, posture recognition) from a single view that is fast and completely automatic. The system first extracts low-level data and uses part of the data for high-level interpretation. It can detect and track several persons even if they merge or are completely occluded by another person from the camera's point of view. For the high-level interpretation step, static posture recognition is performed using a belief theorybased classifier. The belief theory is considered here as a new approach for performing posture recognition and classification using imprecise and/or conflicting data. Four different static postures are considered: standing, sitting, squatting, and lying. The aim of this paper is to give a global view and an evaluation of the performances of the entire system and to describe in detail each of its processing steps, whereas our previous publications focused on a single part of the system. The efficiency and the limits of the system have been highlighted on a database of more than fifty video sequences where a dozen different individuals appear. This system allows real-time processing and aims at monitoring elderly people in video surveillance applications or at the mixing of real and virtual worlds in ambient intelligence systems.

show abstract

Section: Posture Recognition Resultsmentioning

confidence: 99%

Section: High-level Human Behaviour Interpretation: Static Posture Rementioning

confidence: 99%

A Human Body Analysis System

Girondel

Bonnaud

Caplier

2006

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Uncertainty handling can improve visual attention schemes[98]. Various other models have been used in surveillance-related applications, including classifying human motion and simple human interactions using a small belief network[99], human postures using belief networks[100], description of traffic scenes using a dynamic Bayes network[101], human activity recognition using a hierarchal Bayes network[102], and anomalous behavior detection using trajectory learning with Hidden Markov Models[103,104 ]. is defined as the presence of an individual in an area for a period of time longer than a given time threshold.…”

mentioning

confidence: 99%

Evaluation of Smart Video for Transit Event Detection

Goldgof¹

2009

View full text Add to dashboard Cite

Transit agencies are increasingly using video cameras to fight crime and terrorism. As the volume of video data increases, the existing digital video surveillance systems provide the infrastructure only to capture, store and distribute video, while leaving the task of threat detection exclusively to human operators. The objective of this research project was to study and develop an evaluation framework for commercial video analytics systems. A state-of-the-art research literature survey was conducted. Identified strengths, weaknesses, future directions of research and state-of-the-art commercial video analytics products were surveyed. Product capabilities were identified by working together with vendors and analyzing the available literature offered by the providers. Use of analytic technology in transit agencies in Florida was analyzed. A technology survey among the largest agencies in the state indicates very low use of video analytics, significant skepticism, and poor general knowledge of the technology and its capabilities. Based on existing general evaluation frameworks, an evaluation framework for video analytics technology was developed, including annotation guidelines, scoring metrics, and implementation of the scoring metrics in the scoring software.

show abstract

Multi-sensors data fusion system for fall detection

Brulin

Courtial

2010

Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine

View full text Add to dashboard Cite

A belief theory-based static posture recognition system for real-time video surveillance applications

Cited by 5 publications

References 14 publications

A Human Body Analysis System

A Human Body Analysis System

Evaluation of Smart Video for Transit Event Detection

Multi-sensors data fusion system for fall detection

Contact Info

Product

Resources

About