The OBSERVER: An Intelligent and Automated Video Surveillance System

Duque, Duarte; Santos, Henrique; Cortez, Paulo

doi:10.1007/11867586_81

Cited by 14 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although there are a significant number of approaches to dynamic scene segmentation (Collins et al, 2000;Kim et al, 2005;Gutchess et al, 2001;Li et al, 2003;Paschos and Valavanis, 1999;Haritao˘glu et al, 2000;Bobick and Davis, 2001;Thirde et al, 2006) and abnormal action detection (Duque et al, 2006;Gong, 2006, 2008;Zhong et al, 2004;Hamid et al, 2005;Duong et al, 2005), the offline query-processing capabilities are rather limited in most of the existing video-surveillance systems. Retrieving video sequences related to a previously generated alarm is the basic way of querying the semantic content of surveillance videos (e.g., Lyons et al, 2000;Shet et al, 2005).…”

Section: Related Workmentioning

confidence: 99%

“…Background/foreground subtraction (Collins et al, 2000;Kim et al, 2005;Gutchess et al, 2001;Li et al, 2003;Paschos and Valavanis, 1999;Duque et al, 2006) or temporal template-based methods (Haritao˘glu et al, 2000;Bobick and Davis, 2001) are widely used to detect moving objects. One of the basic aims in understanding the objects' behavior is detecting the anomalies in the objects' actions (Duque et al, 2006;Gong, 2006, 2008;Zhong et al, 2004;Hamid et al, 2005;Duong et al, 2005). Abnormal situations and anomalies are reported to the operator and/or stored in a database for later inspection (Durak et al, 2007;S -aykol et al, 2005a).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Scenario-based query processing for video-surveillance archives

Şaykol

Güdükbay

Ulusoy

2010

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Scenario-based querying and retrieval Visual query specification Event-based querying After-the-fact analysis a b s t r a c t Automated video surveillance has emerged as a trendy application domain in recent years, and accessing the semantic content of surveillance video has become a challenging research area. The results of a considerable amount of research dealing with automated access to video surveillance have appeared in the literature; however, significant semantic gaps in event models and content-based access to surveillance video remain. In this paper, we propose a scenario-based query-processing system for video surveillance archives. In our system, a scenario is specified as a sequence of event predicates that can be enriched with object-based low-level features and directional predicates. We introduce an inverted tracking scheme, which effectively tracks the moving objects and enables view-based addressing of the scene. Our query-processing system also supports inverse querying and view-based querying, for after-the-fact activity analysis. We propose a specific surveillance query language to express the supported query types in a scenario-based manner. We also present a visual queryspecification interface devised to facilitate the query-specification process. We have conducted performance experiments to show that our query-processing technique has a high expressive power and satisfactory retrieval accuracy in video surveillance.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Scenario-based query processing for video-surveillance archives

Şaykol

Güdükbay

Ulusoy

2010

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Another proposal for behavior analysis, rather than fixate in a chain of simple actions, analyzes the entire time sequence in order to learn and cluster different patterns of activities [5,6,10]. This kind of perspective can be more robust, given that the behaviors are explained by a more general perspective rather than a restrictive sequence of actions.…”

Section: Dynamic Oriented Graph Philosophymentioning

confidence: 99%

“…Aspiring the automatic detection and prediction of abnormal events a system, called OBSERVER [4,5,6], has been developed in the University of Minho. The system has endowed with state-of-the-art segmentation and tracking algorithms, and is able to classify tracked objects made of three classes: person, group of people and vehicles.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Abnormal Behaviors for Intelligent Video Surveillance Systems

Duque

Santos

Cortez

2007

2007 IEEE Symposium on Computational Intelligence and Data Mining

Self Cite

View full text Add to dashboard Cite

Abstract-The OBSERVER is a video surveillance system that detects and predicts abnormal behaviors aiming at the intelligent surveillance concept. The system acquires color images from a stationary video camera and applies state of the art algorithms to segment, track and classify moving objects. In this paper we present the behavior analysis module of the system. A novel method, called Dynamic Oriented Graph (DOG) is used to detect and predict abnormal behaviors, using real-time unsupervised learning. The DOG method characterizes observed actions by means of a structure of unidirectional connected nodes, each one defining a region in the hyperspace of attributes measured from the observed moving objects and having assigned a probability to generate an abnormal behavior. An experimental evaluation with synthetic data was held, where the DOG method outperforms the previously used N-ary Trees classifier.

show abstract

“…To date, almost all research in the general area of motion detection has assumed that the video frames contain some form of movement, and the focus has been the classification of that movement into matters of interest, ranging from the identification of moving objects [7], to discriminating between background objects waving versus people walking into a scene [8], to identifying suspicious behavior by individuals within a scene [4,5,11]. Such research fits within the realm of artificial intelligence.…”

Section: Introductionmentioning

confidence: 99%

Video Motion Detection Beyond Reasonable Doubt

Xiao¹,

Poursoltanmohammad²,

Sorell³

2008

Proceedings of the 1st International ICST Conference on Forensic Applications and Techniques in Telecommunications, Information

View full text Add to dashboard Cite

We consider the analysis of surveillance video footage containing occasional activities of potential interest interspersed with long periods of no motion. Such evidence is problematic for three reasons: firstly, it takes up a great deal of storage capacity with little evidential value; secondly, human review of such surveillance is extremely time-consuming and subject to errors due to fatigue; and thirdly, there is often a need to prove to the satisfaction of the Court that excised footage contains no images of evidential value. We are therefore concerned with objective, reliable detection of video motion to automate the extraction of activities of interest and to provide simple but reliable measurements to the court to prove that this is a complete record of all activities in the footage. Early results indicate that average luminance-based detection is particularly reliable, and we provide a comparison with other frame-difference techniques.

show abstract

The OBSERVER: An Intelligent and Automated Video Surveillance System

Cited by 14 publications

References 4 publications

Scenario-based query processing for video-surveillance archives

Scenario-based query processing for video-surveillance archives

Prediction of Abnormal Behaviors for Intelligent Video Surveillance Systems

Video Motion Detection Beyond Reasonable Doubt

Contact Info

Product

Resources

About