基于模糊语义的高分辨率SAR图像汽车检测算法

黄勇; 刘芳

doi:10.11999/JEIT160650

基于模糊语义的高分辨率SAR图像汽车检测算法

doi: 10.11999/JEIT160650

黄勇¹,
刘芳¹

基金项目:

国家973计划项目(2013CB329402)，国家自然科学基金(61573267)，国家自然科学基金重大研究计划(91438201, 91438103)

计量
- 文章访问数: 1403
- HTML全文浏览量: 121
- PDF下载量: 345
- 被引次数: 0
出版历程
- 收稿日期: 2016-06-21
- 修回日期: 2016-11-07
- 刊出日期: 2017-04-19

Detecting Cars in VHR SAR Images with a Fuzzy Semantic Algorithm

HUANG Yong¹,
LIU Fang¹

Funds:

The National 973 Program of China (2013CB329402), The National Natural Science Foundation of China (61573267), The Major Research Plan of the National Natural Science Foundation of China (91438201, 91438103)

摘要

摘要: 针对高分辨率SAR图像难于找到精确的背景杂波分布概率模型的问题，该文提出一种不需要背景杂波分布概率模型的高分辨率SAR图像自动检测汽车的新方法。该算法首先搜索场景中包含的亮区域和暗区域，其次采用模糊隶属度函数提取语义特征，筛选可能是汽车强散射区域的亮区域和可能是汽车遮挡区域的暗区域。再根据空间语义关系，对候选汽车强散射区域与候选汽车遮挡区域进行匹配，若匹配成功则计算它们源于同一辆汽车的隶属度。最后阈值选择高隶属度的目标进行合并输出。通过对MiniSAR图像进行汽车检测实验，表明该方法在不需要背景杂波分布概率模型的条件下仍然具有较高的检测率。
- 高分辨率SAR /
- 图像处理 /
- 目标检测 /
- 图像语义 /
- 模糊隶属度
Abstract: It is hard to select a probability distribution model for very high resolution SAR images. This paper presents a novel method for the automatic detecting of cars from VHR SAR image without the probability distribution model. The proposed method starts with searching bright regions and dark regions by the gray feature. Subsequently, the fuzzy membership is employed to extract the semantic features of car from bright regions and dark regions. The potential scattering surface and shadow are matched and calculated with the spatial semantic relationship. Finally, the cars are selected from the matching. The efficiency of the proposed method is demonstrated by experiment which shows it still has high detection rate without the probability distribution model.
- Very High Resolution SAR (VHR SAR) /
- Image processing /
- Object detection /
- Image semantic /
- Fuzzy membership

HTML全文

参考文献(22)

EL-DARYMLI K, MCGUIRE P, POWER D, et al. Target detection in synthetic aperture radar imagery: A state-of-the- art survey[J]. Journal of Applied Remote Sensing, 2013, 7(1): 1-35. doi: 10.1117/1.JRS.7.071598.

ZHANG Yangrui, GAO Meiguo, and LI Yunjie. Performance analysis of typical mean-level CFAR detectors in the interfering target background[C]. IEEE 9th Conference on (Industrial Electronics and Applications) ICIEA, Hangzhou, 2014: 1045-1048.

YU Wenyi, WANG Yinghua, LIU Hongwei, et al. Superpixel- based CFAR target detection for high-resolution SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(5): 730-734. doi: 10.1109/LGRS.2016.2540809.

HUANG Yong and LIU Fang. Detecting cars in VHR SAR images via semantic CFAR algorithm[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(6): 801-805. doi: 10. 1109/LGRS.2016.2546309.

HOU Biao, CHENG Xingzhong, and JIAO Licheng. Multilayer CFAR detection of ship targets in very high resolution SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(4): 811-815.

宋文青, 王英华, 刘宏伟. 高分辨SAR图像自动区域筛选目标检测算法[J]. 电子与信息学报, 2016, 38(5): 1017-1025. doi: 10.11999/JEIT150808.

SONG Wenqing, WANG Yinghua, and LIU Hongwei. An automatic block-to-block censoring target detector for high resolution SAR image[J]. Journal of Electronics Information Technology, 2016, 38(5): 1017-1025. doi: 10.11999/JEIT150808.

DOERRY A W and DUBBERT D F. Digital signal processing applications in high-performance synthetic aperture radar processing[C]. Signals, Systems and Computers, Monterey, USA, 2004: 947-949.

BRENER A R. Proof of concept for airborne SAR imaging with 5 cm resolution in the X-band[C]. European Conference on Synthetic Aperture Radar, Aachen, Germany, 2010: 615-618.

王岩飞, 刘畅, 李和平, 等. 基于多通道合成的优于0.1 m分辨率的机载SAR系统[J]. 电子与信息学报, 2013, 35(1): 29-35. doi: 10.3724/SP. J.1146.2011.01370.

WANG Yanfei, LIU Chang, and LI Heping, et al. An airborne SAR with 0.1 m resolution using multi-channel synthetic bandwidth[J]. Journal of Electronics Information Technology, 2013, 35(1): 29-35. doi: 10.3724/SP.J.1146.2011. 01370.

CHABBI S, LAROUSSI T, and BARKAT M. Performance analysis of dual automatic censoring and detection in heterogeneous Weibull clutter: A comparison through extensive simulations[J]. Signal Processing, 2013, 99(11): 2879-2893. doi: j.sigpro.2013.03.026.

GAO Gui, LIU Li, and ZHAO Lingjun, et al. An adaptive and fast CFAR algorithm based on automatic censoring for target detection in high-resolution SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(6): 1685-1697. doi: 10.1109/TGRS. 2008.2006504.

ANANTHI V P, BALASUBRAMANIAM P, and LIM C P. Segmentation of gray scale image based on intuitionistic fuzzy sets constructed from several membership functions[J]. Pattern Recognition, 2014, 47(12): 3870-3880.

KRINIDIS S and CHATZIS V. A robust fuzzy local information C-means clustering algorithm[J]. IEEE Transactions on Image Processing, 2010, 19(5): 1328-1336.

WANG Min and SONG Tengyi. Remote sensing image retrieval by scene semantic matching[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(5): 2874-2886.

FERRO A, BRUNNER D, and BRUZZONE L. Automatic detection and reconstruction of building radar footprints from single VHR SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(2): 935-952.

JIAO Licheng, TANG X, HOU B, et al. SAR images retrieval based on semantic classification and region-based similarity measure for earth observation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(8): 3876-3891.

WANG H F and SUN Z X. The methods of semantics processing in content-based image retrieval[J]. Journal of Image Graph, 2001, 6(10): 945-952.

LIU Fang, DUAN Yiping, LI Lingling, et al. SAR image segmenation based on hierarhical visual semantic and adaptive neighborhood multinomial latent model[J]. IEEE Trancactions on Geoscience and Remote Sensing, 2016, 54(7): 4287-4301.

WU N and SONG F M. An image retrieval method based on high-level image semantic information[J]. Journal of Image Graph, 2006, 11(12): 1774-1780.

LIAO Pingsung, CHEN Tsesheng, and CHUNG Pauchoo. A fast algorithm for multilevel thresholding[J]. Journal of Information Science and Engineering, 2001, 17(5): 713-727.

施引文献

资源附件(0)

访问统计