作者: Baiyuan Ding , Gongjian Wen
DOI: 10.1080/2150704X.2017.1346397
关键词: Multi resolution 、 Computer vision 、 Artificial intelligence 、 Test sample 、 Target acquisition 、 Robustness (computer science) 、 Computer science 、 Sparse approximation 、 Pattern recognition 、 Synthetic aperture radar
摘要: ABSTRACTThis letter presents a target recognition method for synthetic aperture radar (SAR) images by exploiting the multi-resolution information. For training samples, with lower resolutions are generated to construct dictionary sparse representation-based classification (SRC). Then test sample will be classified based on augmented dictionary. The representation of samples can not only promote capability but also enhance robustness resolution variance due sensor variation. Experiments conducted moving and stationary acquisition (MSTAR) dataset demonstrate validity proposed method.