Energy-efficient visual monitoring based on the sensing relevancies of source nodes for wireless image sensor networks

Image transmissions over wireless sensor networks will typically demand more energy resources than transmission of scalar data, potentially impacting the expected network lifetime. In wireless image sensor networks, some monitoring quality loss may be tolerated since visual information retrieved from source nodes may have different relevance for the application, according to the desired monitoring tasks and the current sensors' poses and fields of view. Based on such sensing relevancies, we propose an energy-efficient visual monitoring mechanism where the frequency of image snapshots transmitted by each source node will be a function of the monitoring relevance of the node for the application. Doing so, we achieve energy saving over the active paths as lower relevant source nodes will transmit fewer images in a period of time, but with low impact to the monitoring functions of the application since sufficient information is still received from the most relevant source nodes. We simulated different communication scenarios to show the expected energy saving when the proposed solution is employed.