Rising criminal activities and demand of robust security solutions, detection and tracking of every minute detail of suspicious activity or object has become a topic of interest for researchers all around the world. In this paper, we propose an approach based on Digital Image and Video processing to detect and track the motion of multiple objects during the phenomenon of occlusion and activate an alert if an object is dropped for a long period of time in the region of concentration of camera. The proposed method can be utilized in video surveillance system and the method has been verified through extensive experimentation for multiple video.

Sensing and data aggregation capabilities of wireless sensor networks (WSNs) depends on efficient deployment of sensor nodes (SNs) in an area. In a large surveillance space, there is a need for more SNs to cover important crucial events despite of the optimum coverage. The authors propose an event-based efficient deployment algorithm (EEDA) for relocation of redundant sensors to the event location to achieve full coverage. They divide the deployment region into small square cells that allows individual cells to be efficiently monitored, instead of considering the whole scenario as one unit. EEDA ensures efficient coverage of the entire deployment region and senses the occurrence of any static or dynamic event with an optimum number of sensors. EEDA with square cells performs better than existing hexagon cell algorithm by 39%. EEDA is validated by simulation as well as by experimental results.

Abstract-Information processing using Neural NetworkCounter can result in faster and accurate computation of data due to their parallel processing, learning and adaptability to various environments. In this paper, a novel 4-Bit Negative Edge Triggered Binary Synchronous Up/Down Counter using Artificial Neural Networks trained with hybrid algorithms is proposed. The Counter was built solely using logic gates and flip flops, and then they are trained using different evolutionary algorithms, with a multi objective fitness function using the back propagation learning. Thus, the device is less prone to error with a very fast convergence rate. The simulation results of proposed hybrid algorithms are compared in terms of network weights, bit-value, percentage error and variance with respect to theoretical outputs which show that the proposed counter has values close to the theoretical outputs.