Study on Detection Method of Small Object on Sea Based on Kernel-MRF Foreground Segmentation Model

It is very difficult to detect the small target over water in the marine environment because of the complexity of water movement and the complex physical fields produced by the water interact with environment. We mainly study foreground segmentation for small target in visual image based on MRF (Markov Random Fields). A foreground segmentation method is proposed that is based on kernel function and MRF. In this method, the kernel function uses the special and temporal correlation between neighbor pixels. We take the probability distribution of the kernel function method as the observed value of the MRF, and get the energy function of the MRF. Results show our method is applicable to low speed small target segmentation in sea image.