A Fusion-Based Framework for Wireless Multimedia Sensor Networks in Surveillance Applications

Abstract

Multimedia sensors enable monitoring applications to obtain more accurate and detailed information. However, the development of efficient and lightweight solutions for managing data traffic over wireless multimedia sensor networks (WMSNs) has become vital because of the excessive volume of data produced by multimedia sensors. As part of this motivation, this paper proposes a fusion-based WMSN framework that reduces the amount of data to be transmitted over the network by intra-node processing. This framework explores three main issues: 1) the design of a wireless multimedia sensor (WMS) node to detect objects using machine learning techniques; 2) a method for increasing the accuracy while reducing the amount of information transmitted by the WMS nodes to the base station, and; 3) a new cluster-based routing algorithm for the WMSNs that consumes less power than the currently used algorithms. In this context, a WMS node is designed and implemented using commercially available components. In order to reduce the amount of information to be transmitted to the base station and thereby extend the lifetime of a WMSN, a method for detecting and classifying objects on three different layers has been developed. A new energy-efficient cluster-based routing algorithm is developed to transfer the collected information/data to the sink. The proposed framework and the cluster-based routing algorithm are applied to our WMS nodes and tested experimentally. The results of the experiments clearly demonstrate the feasibility of the proposed WMSN architecture in the real-world surveillance applications.

Optimization-Based Offloading and Routing Strategies for Sensor-Enabled Video Surveillance Networks

“…This work addresses routing and nodal process problems as well as diverse data aggregation, offloading, and in-network process strategies to reduce the amount of data transmitted along the routing path to the destination. Although the main idea of wireless multimedia sensor networks is to reduce the amount of multimedia data transmitted through the intranode fusion process [35], the specific functions of selecting and routing data to a specific node was not included in their study. From the event-driven routing viewpoint, reducing the transmission and nodal processing time is a major problem [1], [11], [32], [36].…”

“…[1], [35] Offloading Offloading is a type of aggregation of similar data. It requires advanced interactions with other data, such as a facial database.…”

A Clustering Algorithm to Improve the Scan Statistic in Sensor Detection Systems

“…Organizing sensors into a hierarchical topology with clusters has long been suggested for wireless sensor networks to reduce the energy consumption in sensors and the communication burden and latency in the communication network [11], [18], [21]- [30], [33]; and many authors proposed procedures to build clusters [29]- [32]. In fact, many authors proposed procedures in which sensors self-organize into clusters [33], [35]- [39], [54].…”

“…, 6}; i.e., for each point of interest, we include up to 6 clusters into C poi . In all of the results, we considered r min = 0.5 and d min = 0.5 in conditions (20) and (21). For each N inc , we ran Monte Carlo simulations with 10,000 random drops for each of the random shifts and we chose the N inc that produced the C poi with the highest AUC(C poi |l − e ) as the best N inc for the random realization.…”

“…• Proponents of distributed sensor systems often propose that sensors be organized in a hierarchical topology [11], [18], [21]- [33], where sensors are divided into clusters and send their measurements to a clusterhead. Organizing sensors into clusters facilitates the communication between sensors and the fusion center while reducing energy consumption at sensors [27], [34].…”