透過您的圖書館登入
IP:3.140.186.201
  • 期刊
  • OpenAccess

Unsupervised Satellite Change Detection Using Particle Swarm Optimisation in Spherical Coordinates

並列摘要


This paper proposes a new unsupervised satellite change detection method, which is invariant to shadow and shading effects. To achieve this, firstly, the RGB satellite images are transformed into spherical colour space to remove illumination artifacts. Then, a new unsupervised change detection is used. The resultant optimal binary change mask is obtained by minimizing thea mean square error based cost function using Binary Particle Swarm Optimisation (BPSO). The proposed method is compared with three other satellite change detection methods and the results demonstrate that our method provides a significant improvement of obtaining the changed and unchanged regions on different image. The total errors show that our method is at least 39.62% better than the best compared method and are utmost 176.18% better than the worst one.

延伸閱讀