Novel SAR Target Detection Algorithm Using Free Training
-
摘要: 该文提出了一种基于单样本特征提取的SAR感兴趣目标检测方法,充分利用选取的单个目标样本的有效特征实现SAR图像中同类目标的检测。该方法首先检测SAR图像中的潜在感兴趣目标,然后分别提取目标样本和潜在目标中的面积特征和纹理描述特征,并通过不同的匹配方式逐步剔除潜在兴趣目标中的虚假目标。文中提出的纹理描述通过提取具有一定旋转不变性的区域特征描述的方式来适应目标的不同方位,并对SAR噪声和形变具有一定的抑制作用。与多种特征描述方式的对比测试表明了该文提出方法的可行性和有效性。Abstract: A detection method for Synthetic Aperture Radar (SAR) targets based on single sample feature extraction is proposed. Similar targets in a SAR image are detected according to the effective features of the selected single target sample. First, the potential targets of interest in a SAR image are detected, and the area features and texture features are extracted from the target sample and potential targets, respectively. Then, the false targets are eliminated from the potential targets via different matching methods. The proposed method for texture description in this paper can be adopted for targets with different attitudes by extracting the rotationinvariance features of the local region; these features can deal with speckle noise and deformation. The experimental results show the feasibility and validity of the proposed method.
-
表 1 不同特征提取方法的检测结果
Table 1. The detection results by different feature extraction methods
特征提取 虚警率 检测率 目标与非目标分离度 SURF+upright 0.22 0.54 ■○○○○○○■○○○○○○■■■○■ SURF 0.22 0.54 ■○○○○○○■○○○○○○■■■○■ SIFT 0.22 0.54 ■○○○○○■○○○○○○○■■■○■ DAISY 0.20 0.62 ■○○○○○○■○○○○○○■○■■■ PSURF 0 0.92 ○○○○○○○○○○○○■■■■○■■ 注:○表示目标;■表示非目标 表 2 不同特征提取方法的装甲车检测结果
Table 2. The armored car detection results by different feature extraction methods
特征提取 虚警率 检测率 SURF 0.27 0.76 SIFT 0.26 0.80 DAISY 0.27 0.76 PSURF 0.23 0.88 表 3 不同特征提取方法的飞机检测结果
Table 3. The airplane detection results by different feature extraction methods
特征提取 虚警率 检测率 SURF 0 0.750 SIFT 0 0.875 DAISY 0 0.875 PSURF 0 1.000 -
[1] Liu Shuo and Cao Zong-jie. SAR image target detection in complex environments based on improved visual attention algorithm[J]. EURASIP Journal on Wireless Communications and Networking, 2014, 2014(1): 2–8. doi: 10.1186/1687-1499-2014-2 [2] Cui S, Dumitru C, and Datcu M. Ratio-detector-based feature extraction for very high resolution SAR image patch indexing[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 10(5): 1175–1179. doi: 10.1109/LGRS.2012.2235406 [3] Kreithen D, Halversen S, and Owirka G. Discriminating targets from clutter[J]. The Lincoln Laboratory Journal, 1993, 6(1): 25–52. [4] Kaplan L M. Improved SAR target detection via extended fractal features[J]. IEEE Transactions on Aerospace and Electronic Systems, 2001, 37(2): 436–451. doi: 10.1109/7.937460 [5] Rohling H. Radar CFAR thresholding in clutter and multiple target situations[J]. IEEE Transactions on Aerospace and Electronic Systems, 1983, 19(4): 608–621. [6] Rickard J T and Dillard G M. Adaptive detection algorithms for multiple target Situations[J]. IEEE Transactions on Aerospace and Electronic Systems, 1977, 13(4): 338–343. [7] Smith M E and Varshney P K. Intelligent CFAR processor based on data variability[J]. IEEE Transactions on Aerospace and Electronic Systems, 2000, 36(3): 837–847. doi: 10.1109/7.869503 [8] Farrouki A and Barkat M. Automatic censoring CFAR detector based on ordered data variability for nonhomogeneous environments[J]. IET Proceedings-Radar, Sonar and Navigation, 2005, 152(1): 43–51. doi: 10.1049/ip-rsn:20045006