Feature selection for residential area recognition in high resolution images based on particle swarm optimization

Automatic recognition of residential areas in high resolution images becomes one of hotspots in the remote sensing field. Feature selection of residential areas is crucial which affects the corresponding recognition results; however, it is very difficult to select optimal residential area features. Particle swarm optimization (PSO) is a new evolutionary computing technique which was developed through the simulation of simplified social models of bird flocks. Because it has some intelligent properties such as adaptation and self-organizing, PSO has the strong ability to search for the optimal solutions for optimization problems. The difficulty mentioned above is a combination optimization problem in essence and therefore discrete binary PSO is applied in solving this combination optimization problem adaptively in this paper. The particles in the swarm are constructed and the swarm search strategy is proposed to meet the needs of feature selection for residential area recognition. The experimental results show that the PSO method is an effective feature selection method which decreases the feature number obviously, and at the same time improves the recognition accuracy of residential areas effectively.