Detection of group of stationary targets using high-resolution SAR and EO images

In this study, the target detection is performed using TerraSAR-X and WorldView-2 high-resolution satellite images, considering the characteristics of targets. The target of our interest is characterized by being stationary and appearing as cluster targets. After the target detection of SAR image based on CFAR (Constant False Alarm Rate) algorithm, a series of processing (target pixel clustering, network clustering and coherence analysis) is performed in order to reduce false alarms. However, the false alarm is still too quite large to narrow down the candidate areas. The fast and effective ellipse detection using hough transform is developed and applied to an EO (Electro Optical) image. The result helps us to lower significantly the false alarm. Based on the detected ellipse and network analysis the candidates of cluster targets are successfully identified with very low false alarm.