Research On Video Sensor Networks Coverage Optimization Method For Wildlife Monitoring

The wildlife monitoring method based on video sensor networks can accurately acquire data and automatically collect wildlife images and other information,so it plays a very important role in wildlife monitoring.However,due to the special living environment and climatic conditions of wild animals,it is easy to waste human and material resources by repeatedly adjusting the position and direction of video sensor nodes when directly deploying video sensor network in the wild.In order to save human and material resources during deployment and facilitate deployment,coverage optimization of video sensor networks should be carried out in advance.This section describes how to deploy a video sensor networks.The coverage optimization methods currently studied make overlaps and voids exist in the video sensor networks region,and most of them are studied under ideal conditions,without considering the presence of obstacles.The method of video sensor networks coverage optimization based on particle swarm algorithm is prone to fall into the local optimization problem after many iterations in the optimization process,resulting in overlapping video sensor networks coverage and blind zone,and reducing the coverage of video sensor networks.In order to solve the problem that particle swarm optimization is easy to fall into local optimization and improve the coverage of video sensor networks,this paper proposes a video sensor networks coverage optimization method based on immune cloning particle swarm algorithm.Firstly,the particle swarm algorithm is used to search for the global optimal value and individual optimal value of particles,and the fitness value of each particle is recorded,that is,the coverage of each node of the video sensor.Secondly,the immune cloning optimization algorithm is used to generate the temporary population,and the particles in the temporary population are subjected to immune clonal replication,mutation and selection operations.Finally,update the individual and global optimums of the particle.The results tested on the CEC2017 standard function set show that the proposed algorithm has the ability to jump out of the local optimal solution.The experimental results of the video sensor coverage optimization of the proposed algorithm show that compared with other video sensor network coverage optimization methods,the proposed algorithm effectively improves the video sensor network coverage.The video sensor networks coverage optimization method based on immune cloning particle swarm algorithm can reduce the overlap and void of video sensor networks,and effectively improve the coverage of video sensor networks.However,this optimization method does not consider the existence of obstacles,which will cause overlap between video sensor nodes and obstacles,affecting the coverage of video sensor networks.To solve this problem,this paper proposes a coverage optimization method for video sensor networks based on immune cloning particle swarm algorithm to fuse virtual force in obstacle scenes.Firstly,a directed probabilistic perception model is adopted to adapt to complex obstacle scenarios.Then,by calculating the overlap area between the video sensor node and the obstacle,and between the video sensor node and the neighbor node,the size of the virtual resultant force is determined by the size of the overlapping area.Finally,local adjustments are made using virtual forces,and the immune clonal particle swarm coverage optimization algorithm adjusts the global video sensor nodes.Experimental results show that compared with other video sensor network coverage optimization methods in obstacle scenarios,the proposed algorithm has a better obstacle avoidance effect,which can effectively improve the coverage of video sensor network.