Design of multimedia surveillance systems

Sivaram, G.S.V.S.; Kankanhalli, Mohan; Ramakrishnan, K. R.

doi:10.1145/1556134.1556140

Cited by 16 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Linear programming, coverage (Sivaram et al 2009;Bottino et al 2009 Marchand and Chaumette 1999b) Object modeling Next best view (Banta et al 2000;Chen and Li 2005;Pito 1999) Object modeling Information entropy,rule based (Li and Liu 2005;Kutulakos and Dyer 1995) Recognition Optimal visibility (de Ruiter et al 2010) Recognition Probabilistic (Farshidi et al 2009;Roy et al 2005) Path planning Roadmap (Baumann et al 2008;Zhang et al 2009) General Random occlusion (Mittal and Davis 2008) Camera-lighting Geometrical (Marchand 2007) Multirobot formation Graph theory (Kaminka et al 2008)…”

Section: Representative Workmentioning

confidence: 99%

Active vision in robotic systems: A survey of recent developments

Chen

Kwok

2011

The International Journal of Robotics Research

366

204

View full text Add to dashboard Cite

In this paper we provide a broad survey of developments in active vision in robotic applications over the last 15 years. With increasing demand for robotic automation, research in this area has received much attention. Among the many factors that can be attributed to a high-performance robotic system, the planned sensing or acquisition of perceptions on the operating environment is a crucial component. The aim of sensor planning is to determine the pose and settings of vision sensors for undertaking a vision-based task that usually requires obtaining multiple views of the object to be manipulated. Planning for robot vision is a complex problem for an active system due to its sensing uncertainty and environmental uncertainty. This paper describes such problems arising from many applications, e.g. object recognition and modeling, site reconstruction and inspection, surveillance, tracking and search, as well as robotic manipulation and assembly, localization and mapping, navigation and exploration. A bundle of solutions and methods have been proposed to solve these problems in the past. They are summarized in this review while enabling readers to easily refer solution methods for practical applications. Representative contributions, their evaluations, analyses, and future research trends are also addressed in an abstract level.

show abstract

Section: Representative Workmentioning

confidence: 99%

Active vision in robotic systems: A survey of recent developments

Chen

Kwok

2011

The International Journal of Robotics Research

366

204

View full text Add to dashboard Cite

show abstract

“…(Hörster and Lienhart, 2006a;Hörster and Lienhart, 2006b;Hörster and Lienhart, 2006c) proposed a linear programming approach that determines the calibration for each camera in the network that maximizes the coverage of the observable space with a certain resolution. (Ram et al, 2006;Sivaram et al, 2009) proposed a performance metric that evaluates the probability of accomplishing a task as a function of set of camera configurations. This metric took into consideration the objects of interest in the scenario and was defined to realize only images obtained in a certain direction (frontal image of the person).…”

Section: Previous Workmentioning

confidence: 99%

“…Although (Bodor et al, 2007;Janoos et al, 2007) proposed the use of observed human activity for optimizing the camera placement, in the proposed work the human trajectories are simulated and not observed in order to identify regions with dominant human activity. Furthermore, (Ram et al, 2006;Sivaram et al, 2009) proposed the use of frontal view from observations as a task for optimizing the camera position unlike the proposed method that predicts frontal view based on human behavior. Finally, the human behavior in a given scenario is influenced by the 3D geometry of that environment (Mantini and Shah, 2014;Kitani et al, 2012).…”

Section: Previous Workmentioning

confidence: 99%

Camera Placement Optimization Conditioned on Human Behavior and 3D Geometry

Mantini

Shah

2016

Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

View full text Add to dashboard Cite

This paper proposes an algorithm to optimize the placement of surveillance cameras in a 3D infrastructure. The key differentiating feature in the algorithm design is the incorporation of human behavior within the infrastructure for optimization. Infrastructures depending on their geometries may exhibit regions with dominant human activity. In the absence of observations, this paper presents a method to predict this human behavior and identify such regions to deploy an effective surveillance scenario. Domain knowledge regarding the infrastructure was used to predict the possible human motion trajectories in the infrastructure. These trajectories were used to identify areas with dominant human activity. Furthermore, a metric that quantifies the position and orientation of a camera based on the observable space, activity in the space, pose of objects of interest within the activity, and their image resolution in camera view was defined for optimization. This method was compared with the state-of-the-art algorithms and the results are shown with respect to amount of observable space, human activity, and face detection rate per camera in a configuration of cameras.

show abstract

“…Many recent works have been proposed for enhancing event monitoring performance, including multimedia coding [2][3][4], event coverage [5][6][7], and event detection [8][9][10]. For multimedia coding-related works, as it relates to the transmission and exchange of large amounts of data, in addition to computation-intensive features, it also has resource-demanding features.…”

Section: Introductionmentioning

confidence: 99%

C2EM: cloud-assisted complex event monitoring in wireless multimedia sensor networks

Shen

Bai

et al. 2015

J Wireless Com Network

View full text Add to dashboard Cite

This paper addresses the problem of how to provide a more flexible service for complex event monitoring in wireless multimedia sensor networks (WMSNs). In particular, we propose C2EM, a cloud-assisted complex event monitoring architecture that involves scalar sensors, camera sensors, cloudlets, and clouds to leverage computation offloading reliability, service response time, coverage efficiency, and energy efficiency. On clouds, we design an opportunistic service access point selection scheme that provides quality of service (QoS) supports for scalar sensor computation offloading. Meanwhile, clouds are responsible for optimizing camera sensor utilization of the whole network. On cloudlets, we design a real-time camera actuation scheme with the objective of minimizing the possible coverage overlaps while providing probabilistic guarantee in residual energy. Through computation division, most complex computations and network environment profilers are executed on cloudlets or clouds. Sensors only need to carry out very simple operations. We evaluate the performance of C2EM through simulations under a complex event scenario. The results demonstrate that C2EM can enhance complex event monitoring performance with optimized energy efficiency, desirable event coverage quality, and potential adaptability to the dynamics of complex events.

show abstract

Design of multimedia surveillance systems

Cited by 16 publications

References 14 publications

Active vision in robotic systems: A survey of recent developments

Active vision in robotic systems: A survey of recent developments

Camera Placement Optimization Conditioned on Human Behavior and 3D Geometry

C2EM: cloud-assisted complex event monitoring in wireless multimedia sensor networks

Contact Info

Product

Resources

About