A CASCADE STRUCTURE OF AIRCRAFT DETECTION IN HIGH RESOLUTION REMOTE SENSING IMAGES

Aircraft detection is a difficult task in the field of high remote sensing image application. In this paper we present an automatic system for aircraft detection based on locating the candidates of aircrafts and Support Vector Machine (SVM) to detect aircraft from high resolution remote sensing images. The system contains two main modules: in module one, we use segmentation based on statistical region merging and line segment to quickly locate the candidates of aircrafts; in module two, the precise detection process is accomplished by training the SVM classifier with combining the features of segmentation and line segment. Experimental results indicate that the system is effective in handling the remote sensing images. Therefore, it is a good choice for aircraft detection in high remote sensing images.