A multi-agent framework for visual surveillance

Orwell, James; Massey, Steve; Remagnino, Paolo; Greenhill, D.; Jones, Graeme A.

doi:10.1109/iciap.1999.797748

Cited by 42 publications

(19 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Orwell et al in [34] and Caspi et al in [9] match objects by fusing the estimated trajectories obtained by each camera. However, special care should be applied when using such methods.…”

Section: Previous Workmentioning

confidence: 99%

Sparsity Driven People Localization with a Heterogeneous Network of Cameras

et al. 2011

View full text Add to dashboard Cite

This paper addresses the problem of localizing people in low and high density crowds with a network of heterogeneous cameras. The problem is recast as a linear inverse problem. It relies on deducing the discretized occupancy vector of people on the ground, from the noisy binary silhouettes observed as foreground pixels in each camera. This inverse problem is regularized by imposing a sparse occupancy vector, i.e., made of few non-zero elements, while a particular dictionary of silhouettes linearly maps these nonempty grid locations to the multiple silhouettes viewed by the cameras network. The proposed framework is (i) generic to any scene of people, i.e., people are located in low and high density crowds, (ii) scalable to any number of cameras and already working with a single camera, (iii) unconstrained by the scene surface to be monitored, and (iv) versatile with respect to the camera's geometry, e.g., planar or omnidirectional.Qualitative

show abstract

“…Orwell et al in [34] and Caspi et al in [9] match objects by fusing the estimated trajectories obtained by each camera. However, special care should be applied when using such methods.…”

Section: Previous Workmentioning

confidence: 99%

Sparsity Driven People Localization with a Heterogeneous Network of Cameras

et al. 2011

View full text Add to dashboard Cite

show abstract

“…In this project, the fields of view of the cameras do not overlap. The work of [11], which is very similar to our work, proposes an architecture for implementing algorithms which understand the scene in the visual surveillance domain. The aim of their work is to obtain a high level description of the events observed by multiple cameras.…”

Section: Related Workmentioning

confidence: 99%

A Multi-agent Architecture Based on the BDI Model for Data Fusion in Visual Sensor Networks

Castanedo

García

Patricio

et al. 2010

J Intell Robot Syst

View full text Add to dashboard Cite

The newest surveillance applications attempt more complex tasks such as the analysis of the behavior of individuals and crowds. These complex tasks may use a distributed visual sensor network in order to gain coverage and exploit the inherent redundancy of the overlapped field of views. In this article, a Multi-agent architecture based on the Belief-Desire-Intention (BDI) model for processing the information and fuse data in a distributed visual sensor network is presented.Instead of exchanging raw images between the agents involved in the visual network, local signal processing is performed and only the key observed features are shared. After a registration or calibration phase, the proposed architecture performs tracking, data fusion and coordination. Using the proposed Multi-agent architecture, we focus on the means of fusing the estimated positions on the ground plane from different agents which are applied to the same object. This fusion process is used for two different purposes:(1) to obtain a continuity in the tracking along the field of view of the cameras involved in the distributed network, (2) to improve the quality of the tracking by means of fusion techniques, and by discarding non reliable sensors.Experimental results on two different scenarios show that the designed architecture can successfully track an object even when occlusions or sensor's errors take place. The sensor's errors are reduced by exploiting the inherent redundancy of a visual sensor network with overlapped field of views.

show abstract

“…Many researches has been focused in solve this and similar issues using multiagent systems [11,12], in where each agent is the responsible of control and manage one camera. This distributed solution is a good option for the problem of coordinating multi-camera systems, taking the advantages of scalability and fault-tolerance over centralization.…”

Section: Introductionmentioning

confidence: 99%

Multi-camera Control and Video Transmission Architecture for Distributed Systems

Bustamante

2011

Advances in Intelligent and Soft Computing

View full text Add to dashboard Cite

The increasing number of autonomous systems monitoring and controlling visual sensor networks, make it necessary an homogeneous (device-independent), flexible (accessible from various places), and efficient (real-time) access to all their underlying video devices. This paper describes an architecture for camera control and video transmission in a distributed system like existing in a cooperative multiagent video surveillance scenario. The proposed system enables the access to a limited-access resource (video sensors) in an easy, transparent and efficient way both for local and remote processes. It is particularly suitable for Pan-Tilt-Zoom (PTZ) cameras in which a remote control is essential.

show abstract

A multi-agent framework for visual surveillance

Cited by 42 publications

References 8 publications

Sparsity Driven People Localization with a Heterogeneous Network of Cameras

Sparsity Driven People Localization with a Heterogeneous Network of Cameras

A Multi-agent Architecture Based on the BDI Model for Data Fusion in Visual Sensor Networks

Multi-camera Control and Video Transmission Architecture for Distributed Systems

Contact Info

Product

Resources

About