A Grey Wolf Optimization Based Algorithm for Optimum Camera Placement

Camera placement is very important for surveillance applications. Proposed work presents a new method of optimum placement of visual sensors for maximum coverage of the predefined surveillance space. The surveillance space is modeled as priority areas (PAs), obstacles and feasible locations for placement of cameras. We are using PTZ (pan, tilt, zoom) cameras, which not only reduces occlusion due to randomly moving objects in the PA but also increases the covered area compared to pin hole cameras. The proposed approach will be useful for crowd monitoring in a big surveillance space holding multiple events and having multiple entrances. The problem of optimum camera placement for maximum coverage considering both static and randomly moving obstacles is mapped as a Grey Wolf Optimization (GWO) problem. The proposed algorithm is computationally lighter and converges faster as compared to Genetic Algorithm (GA) based camera placement and Particle Swarm Optimization (PSO) based camera placement algorithm. The concept is validated using simulation as well as the experimental results.