CFAR detection algorithm for ground target in heterogeneous clutter using high resolution SAR image
暂无分享,去创建一个
Because of increasing SAR image resolution, the well-known classical statistical SAR image models sometimes do not fit to heterogeneous environment. In this paper, G0 model based CFAR detector is proposed to detect the vehicle targets in the heterogeneous ground environment. The G0 distribution model is known as suitable for various degree of homogeneity and is adopted as the statistical model in this paper. Although G0 model well fits to heterogeneous SAR image, G0 based CFAR detector still has many false alarms arising from impulsive strong echoes. In order to reduce false alarms, which is occupied in a few pixels compared to actual target size, extended target window scheme is applied in this paper. Detection results are presented using high resolution real SAR image with the intended vehicle targets in the heterogeneous background environment.
[1] Gangyao Kuang,et al. An Adaptive and Fast CFAR Algorithm Based on Automatic Censoring for Target Detection in High-Resolution SAR Images , 2009, IEEE Transactions on Geoscience and Remote Sensing.
[2] Lars M. H. Ulander,et al. A challenge problem for detection of targets in foliage , 2006, SPIE Defense + Commercial Sensing.
[3] L. Novak,et al. The Automatic Target- Recognition System in SAIP , 1997 .
[4] Corina da Costa Freitas,et al. A model for extremely heterogeneous clutter , 1997, IEEE Trans. Geosci. Remote. Sens..