A novel remote sensing image change detection algorithm based on image fusion and wavelet theory

Image change detection is based on the analysis in different time from the same area of two or more images, detect the feature in the region information changes over time. Remote sensing image change detection has been widely used in such as the dynamic monitoring of forest resources monitoring, the change of land cover and use, agricultural resources survey, urban planning layout, environmental monitoring and analysis, assessment of natural disasters, geographic data update and military reconnaissance in the strategic objectives (such as roads, Bridges, airports) of dynamic monitoring and many other fields. Multilayer perceptron learning and classification of certain prior knowledge is known as a condition, namely the network weights adjustment was conducted under the condition of supervision. In practical application, sometimes cannot provide the required prior knowledge, which requires network has the ability to self-learning. Kohonen self-organizing feature map is put forward by the the self-learning function of neural network through the self-organizing feature map neural network model and combining the change detection task to obtain higher detection accuracy and stronger adaptability.