Managing the information flow in visual sensor networks

Abstract

Sensor networks, or sensor webs, which consist of a large number of interconnected sensing devices, have been the subject of extensive research in the past couple of years. Typical applications of sensor networks include monitoring of possibly very large, remote and/or inaccessible areas, surveillance, smart environments like meeting rooms, buildings, homes, and highways. Our focus is on visual sensor networks, which are networks of cameras equipped with enough processing power to support local image analysis. This paper describes ongoing research at UCSC in visual sensor networks and highlights the research challenges to be addressed. It motivates the need for the tight coupling between vision techniques and communication protocols for more effective monitoring/tracking capabilities (by having sensors operate in a coordinated manner), as well as energy-and bandwidth-efficient protocols which will prolong the operational life of the sensor network.

Node Clustering Based on Overlapping FoVs for Wireless Multimedia Sensor Networks

“…The number of clusters and cluster-size are parameters that usually impact cluster formation procedures. K. Obrackza et al [9] state the fact that directional FoV should be the key parameter to form clusters in WMSN and also highlight examples in which video sensor spatial-based collaboration provides robust object detection by cross-validating information.…”

Distributed volumetric scene geometry reconstruction with a network of distributed smart cameras

“…These "smart cameras" can form a network to collaboratively monitor, track and analyze the scenes of interest. This area have drawn a lot of attention in both academia and industry over the past years (see [1] [11] and [13] for an overview). However compared with the maturity and availability of the camera network hardware, the software capable of fully utilizing the huge amount of visual information is greatly under-developed.…”

“…Algorithm 1 Camera-centric distributed algorithm for scene geometry reconstruction 1: for each smart camera c, do 2: Compute the incremental updates F c v , ∀v ∈ V c , according to formula (11). If max v∈Vc |F c v | < ε (where ε is a stop criterion threshold), then terminate.…”

On the coverage problem in video-based wireless sensor networks

“…We assume that in the first phase of system operations, all cameras with overlapped FoVs are jointly calibrated [4], [9]. Because cameras monitor the scene, which is in one plane, we simplify the problem of volumetric coverage, and consider the coverage of the scene that lays on the parallel plane π 1 .…”

“…The authors in [4] address the research challenges in video-based sensor networks. In particular, they highlight the importance of sensor collaboration and the development of video-sensor specific network-layer and MAC-layer protocols.…”