Visual attention based model for target detection in high resolution remote sensing images

The difficulty and limitation of small target detection methods for high-resolution remote sensing data have been a recent research hot spot. At present, it has much realistic significance to rapidly detect targets in high resolution remote sensing images, especially within limited computation resources. Employing relative achievements of visual attention in perception psychology and neurosciences, this paper endeavors to construct an attention model for target detection and make use of the advantages of fast and accurate small target detection under complex varied nature environment. The proposed model consists of the processing of bottom-up visual information extraction and top-down visual attention guiding. The construction and calculate method is presented in paper. The novel framework breaks down the complex problem of scene analysis and improves the computation efficiency by selective attention. The experimental results over aircraft detection in Quick-bird satellite images show that the proposed model is well-behaved on high resolution remote sensing images.