Spatial Partitioning in Self-Organizing Smart Camera Systems

Hoffmann, Martin; Wittke, Michael; Hähner, Jörg; Müller-Schloer, Christian

doi:10.1109/jstsp.2008.2001308

Cited by 28 publications

(18 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In multiple iterations they are able to find a satisfactory camera placement with optimal coverage of the defined area. Hoffman et al [10] present a selforganising approach to camera pan-tilt-zoom configurations, however they are concerned with minimising overlap between FOVs, rather than seeing this as an opportunity to make use of redundancy. Further information on camera placement algorithms and coverage optimisation is given in [2], [15], [19].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Self-Organising Zooms for Decentralised Redundancy Management in Visual Sensor Networks

Esterle

Rinner

Lewis

2015

2015 IEEE 9th International Conference on Self-Adaptive and Self-Organizing Systems

View full text Add to dashboard Cite

Abstract-When visual sensor networks are composed of cameras which can adjust the zoom factor of their own lens, one must determine the optimal zoom levels for the cameras, for a given task. This gives rise to an important trade-off between the overlap of the different cameras' fields of view, providing redundancy, and image quality. In an object tracking task, having multiple cameras observe the same area allows for quicker recovery, when a camera fails. In contrast having narrow zooms allow for a higher pixel count on regions of interest, leading to increased tracking confidence. In this paper we propose an approach for the self-organisation of redundancy in a distributed visual sensor network, based on decentralised multi-objective online learning using only local information to approximate the global state. We explore the impact of different zoom levels on these trade-offs, when tasking omnidirectional cameras, having perfect 360-degree view, with keeping track of a varying number of moving objects. We further show how employing decentralised reinforcement learning enables zoom configurations to be achieved dynamically at runtime according to an operator's preference for maximising either the proportion of objects tracked, confidence associated with tracking, or redundancy in expectation of camera failure. We show that explicitly taking account of the level of overlap, even based only on local knowledge, improves resilience when cameras fail. Our results illustrate the trade-off between maintaining high confidence and object coverage, and maintaining redundancy, in anticipation of future failure. Our approach provides a fully tunable decentralised method for the self-organisation of redundancy in a changing environment, according to an operator's preferences.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Therefore, these cameras are typically deployed such that the overlap of their fields of view (FOVs) and hence the redundancy of the observed area is minimised [10]. However, overlapping FOVs can also be useful.…”

Section: Introductionmentioning

confidence: 99%

Self-Organising Zooms for Decentralised Redundancy Management in Visual Sensor Networks

Esterle

Rinner

Lewis

2015

2015 IEEE 9th International Conference on Self-Adaptive and Self-Organizing Systems

View full text Add to dashboard Cite

show abstract

“…In [13], the placement of static cameras is determined according to a floor plan. A camera network deployment approach is developed in [17] to minimize the coverage overlap between neighboring cameras. Different from these approaches that focus on static cameras, we exploit the controllable mobility of robot to increase the likelihood of capturing debris objects.…”

Section: Related Workmentioning

confidence: 99%

Aquatic debris monitoring using smartphone-based robotic sensors

Wang¹,

Tan²,

Xing³

et al. 2014

IPSN-14 Proceedings of the 13th International Symposium on Information Processing in Sensor Networks

View full text Add to dashboard Cite

Abstract-Monitoring aquatic debris is of great interest to the ecosystems, marine life, human health, and water transport. This paper presents the design and implementation of SOAR -a vision-based surveillance robot system that integrates an off-the-shelf Android smartphone and a gliding robotic fish for debris monitoring. SOAR features real-time debris detection and coverage-based rotation scheduling algorithms. The image processing algorithms for debris detection are specifically designed to address the unique challenges in aquatic environments. The rotation scheduling algorithm provides effective coverage of sporadic debris arrivals despite camera's limited angular view. Moreover, SOAR is able to dynamically offload computationintensive processing tasks to the cloud for battery power conservation. We have implemented a SOAR prototype and conducted extensive experimental evaluation. The results show that SOAR can accurately detect debris in the presence of various environment and system dynamics, and the rotation scheduling algorithm enables SOAR to capture debris arrivals with reduced energy consumption.

show abstract

“…In another instance, Erdem et al [Erdem and Sclaroff 2006] consider the problem of determining automatic camera deployment layout to satisfy task-specific and floorplan-specific coverage requirements. Hoffmann et al [Hoffmann et al 2008] propose a distributed algorithm to maximize the total area coverage, where each camera tries to minimize coverage overlaps with its neighboring cameras. Ma et al [Ma et al 2009] propose a 3D model for camera coverage, where cameras can adjust their pan and tilt values.…”

Section: Related Workmentioning

confidence: 99%

Coverage algorithms for visual sensor networks

Munishwar

Abu-Ghazaleh

2013

ACM Trans. Sen. Netw.

View full text Add to dashboard Cite

Visual sensor networks are becoming increasingly popular in a number of application domains. A distinguishing characteristic of VSNs is to self-configure to minimize the need for operator control and improve scalability. One of the areas of self-configuration is camera coverage control: how should cameras adjust their field-of-views to cover maximum targets? This is an NP-hard problem. We show that the existing heuristics have a number of weaknesses that influence both their coverage and their overhead. Therefore, we first propose a computationally efficient centralized heuristic that provides near-optimal coverage for small-scale networks. However, it requires significant communication and computation overhead, making it unsuitable for large scale networks. Thus, we develop a distributed algorithm that outperforms the existing distributed algorithm with lower communication overhead, at the cost of coverage accuracy. We show that the proposed heuristics guarantee to cover at least half of the targets covered by the optimal solution. Finally, to gain benefits of both centralized and distributed algorithms, we propose a hierarchical algorithm where cameras are decomposed into neighborhoods that coordinate their coverage using an elected local coordinator. We observe that the hierarchical algorithm provides scalable near-optimal coverage with networking cost significantly less than that of centralized and distributed solutions.

show abstract

Spatial Partitioning in Self-Organizing Smart Camera Systems

Cited by 28 publications

References 19 publications

Self-Organising Zooms for Decentralised Redundancy Management in Visual Sensor Networks

Self-Organising Zooms for Decentralised Redundancy Management in Visual Sensor Networks

Aquatic debris monitoring using smartphone-based robotic sensors

Coverage algorithms for visual sensor networks

Contact Info

Product

Resources

About