Self-Orienting Wireless Multimedia Sensor Networks for Maximizing Multimedia Coverage

Abstract

Wireless multimedia sensor networks (WMSN) have recently emerged as one of the most important technologies, driven by the powerful multimedia signal acquisition and processing abilities. Target classification is an important research issue addressed in WMSN, which has strict requirement in robustness, quickness and accuracy. This paper proposes a collaborative semi-supervised classifier learning algorithm to achieve durative online learning for support vector machine (SVM) based robust target classification. The proposed algorithm incrementally carries out the semi-supervised classifier learning process in hierarchical WMSN, with the collaboration of multiple sensor nodes in a hybrid computing paradigm. For decreasing the energy consumption and improving the performance, some metrics are introduced to evaluate the effectiveness of the samples in specific sensor nodes, and a sensor node selection strategy is also proposed to reduce the impact of inevitable missing detection and false detection. With the ant optimization routing, the learning process is implemented with the selected sensor nodes, which can decrease the energy consumption. Experimental results demonstrate that the collaborative hybrid semisupervised classifier learning algorithm can effectively implement target classification in hierarchical WMSN. It has outstanding performance in terms of energy efficiency and time cost, which verifies the effectiveness of the sensor nodes selection and ant optimization routing.

Modification of View Field in Wireless Multimedia Sensor Networks

“…However, some simplifications adopted in that work are far from reality since it does not consider the obstacles. Tezcan [2] proposed a distributed algorithm to determine a node's multimedia coverage and to find the sensor orientation, which minimizes the negative effect of occlusions and overlapping regions in the sensing field. This algorithm assumes that each multimedia node knows its location information and the location of all the obstacles around it in advance, which cannot be achieved because WMSNs are usually used in unknown environment.…”

“…The availability of low-cost, small-scale imaging sensors indicate the development of Wireless Multimedia Sensor Networks (WMSNs), which allows retrieving video streams and enhances existing sensor network applications in both civilian and military areas [1]. Demand of these multimedia sensors is driven by the necessity of providing comprehensive information pertaining to a specific region of interest [2]. However, these multimedia sensors produce deluge of data, requiring more extensive processing capacity and higher transmission rates, which puts more challenges on both hardwires and algorithms in WMSNs [3].…”

Multi plane volumetric coverage in wireless visual sensor network

“…In such scenario, visual sensors are placed on a plane (sensor plane) and their coverage at a parallel plane is investigated. This model is used in [2] where it is assumed that sensors have the capability to change orientation after deployment. The goal of [2] is to find the orientation of the cameras which maximizes plane coverage.…”

“…This model is used in [2] where it is assumed that sensors have the capability to change orientation after deployment. The goal of [2] is to find the orientation of the cameras which maximizes plane coverage. In [3] the weighted coverage problem is considered which assign priorities to different regions based on their importance.…”

“…Definition 2: Communication neighbor set is the set of sensors which are in communicational range of the sensor Si' Hence, the communication neighbors of Si are defined as: (2) where N denotes the set of all sensors in the network. Also, de Si' SJ is the Euclidean distance between sensor Si and Sj while R is the communication range of this sensor.…”