Video sequence interpretation for visual surveillance

Rota, Nathanaël; Thonnat, Monique

doi:10.1109/vs.2000.856858

Cited by 52 publications

(40 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A detector is an independent evidence collector that targets a given type of entity. Such detectors have been widely used for event recognition, for example in detecting motion [9,26,34,39], cars [23] and pedestrians [35]. Some detectors are widely applicable and others are specific to a narrow domain.…”

Section: Definitionsmentioning

confidence: 99%

See 1 more Smart Citation

Explaining Activities as Consistent Groups of Events

Damen

Hogg

2011

Int J Comput Vis

View full text Add to dashboard Cite

We propose a method for disambiguating uncertain detections of events by seeking global explanations for activities. Given a noisy visual input, and exploiting our knowledge of the activity and its constraints, one can provide a consistent set of events explaining all the detections. The paper presents a complete framework that starts with a general way to formalise the set of global explanations for a given activity using attribute multiset grammars (AMG). AMG combines the event hierarchy with the necessary features for recognition and all natural constraints. Parsing a set of detections by such a grammar finds a consistent set of events that satisfies the activity's natural constraints. Each parse tree has a posterior probability in a Bayesian sense. To find the best parse tree, the grammar and a finite set of detections are mapped into a Bayesian Network (BN). The set of possible labellings of the Bayesian network corresponds to the set of all parse trees for a given set of detections. We compare greedy, multiplehypotheses trees, reversible jump MCMC, and integer programming for finding the Maximum a Posteriori (MAP) solution over the space of explanations. The framework is tested for two applications; the activity in a bicycle rack and around a building entrance.

show abstract

Section: Definitionsmentioning

confidence: 99%

“…Although not part of the SCFG formalism, they also added a consistency check within the recognition process to enforce temporal constraints necessary for an explanation to be valid. Several non-grammatical linguistic methods have been proposed to incorporate such constraints directly into the formalism [22,24,34,39,41,42].…”

Section: Representing Activitiesmentioning

confidence: 99%

Explaining Activities as Consistent Groups of Events

Damen

Hogg

2011

Int J Comput Vis

View full text Add to dashboard Cite

show abstract

“…These systems obviously differ in the approach proposed, but also in various assumptions about the operational environment. One first main distinction is between systems adopting a single, fixed camera [1][2][3][4][5][6] with respect to systems adopting either multiple cameras [7] or an airborne camera [8]. In this work, we focus on a single fixed camera scenario, since it still captures a wide spread of applications.…”

Section: Related Workmentioning

confidence: 99%

“…In this work, we focus on a single fixed camera scenario, since it still captures a wide spread of applications. Another relevant distinction is made between systems oriented to monitoring of traffic scenes, where the main targets are vehicles and pedestrians (see for instance [1,5,6,9]), and systems for video surveillance of unattended areas such as metro platforms,parking areas (see [3,4]) and unmanned railways environments [10]. In the two cases, different a-priori knowledge about objects in the scene can be exploited in order to improve detection and/or tracking.…”

Section: Related Workmentioning

confidence: 99%

The Sakbot System for Moving Object Detection and Tracking

Cucchiara

Grana

Neri

et al. 2002

Video-Based Surveillance Systems

View full text Add to dashboard Cite

Abstract:This paper presents Sakbot, a system for moving object detection in traffic monitoring and video surveillance applications. The system is endowed with robust and efficient detection techniques, which main features are the statistical and knowledge-based background update and the use of HSV color information for shadow suppression. Tracking is provided by a symbolic reasoning module allowing flexible object tracking over a variety of different applications. This system proves effective on many different situations, both from the point of view of the scene appearance and the purpose of the application.

show abstract

“…( [10] uses a Variable Length HMM to deal with varying lengths of dependency on the past, retaining the efficiency of the HMM for short-term dependencies.) Secondly, there are purely logic-based systems for behaviour understanding, eg, [3,6,21]. Logical reasoning is used extensively in other areas of AI, but it is open whether it is sufficiently robust for video sequence analysis given the ambiguity in features extracted from images.…”

Section: Introductionmentioning

confidence: 99%

Efficient Hidden Semi-Markov Model Inference for Structured Video Sequences

Tweed

Fisher

Bins

et al.

2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance

View full text Add to dashboard Cite

The semantic interpretation of video sequences by computer is often formulated as probabilistically relating lowerlevel features to higher-level states, constrained by a transition graph. Using Hidden Markov Models inference is efficient but time-in-state data cannot be included, whereas using Hidden Semi-Markov Models we can model duration but have inefficient inference. We present a new efficient O(T ) algorithm for inference in certain HSMMs and show experimental results on video sequence interpretation in television footage to demonstrate that explicitly modelling timein-state improves interpretation performance.

show abstract

Video sequence interpretation for visual surveillance

Abstract: This paper presents recent work done on video sequence interpretation. We propose a framework based on two kinds of a priori knowledge : predefined scenarios and contextual information. This approach has been applied on video sequences of the AVS-PV visual surveillance european project.

Cited by 52 publications

References 9 publications

Explaining Activities as Consistent Groups of Events

Explaining Activities as Consistent Groups of Events

The Sakbot System for Moving Object Detection and Tracking

Efficient Hidden Semi-Markov Model Inference for Structured Video Sequences

Contact Info

Product

Resources

About