面向船舶目标精细化分析的遥感图像应用研究
1. 宿迁学院, 信息工程学院, 江苏宿迁 223800
2. 哈尔滨工程大学, 信息与通信工程学院, 黑龙江哈尔滨 150001
| 摘 要： | 随着高分辨率图像的出现，海洋监测已不仅仅停留在目标发现阶段。通过对目标主要部件的定性分析，可以实现舰船目标的精细化识别，包括但不限于识别其类型和装备，从而有效应对军区战备水平和区域动态。与单一来源遥感影像相比，融合影像能够提供更全面的目标信息。目前公认的图像融合方法分为像素级、特征级和决策级。如何应用多样性融合方法深入挖掘异源遥感图像的互补信息是本文关注的重点。其中，像素级融合依赖于SAR图像的散射特性能够剔除地物干扰对关键部件检测的影响；特征级融合通过可视化特征集锁定注意力特征，充分挖掘目标多源特性；决策级融合综合专家指导和环境推理，在上述两个级别融合的基础上获得最终识别结果。三层次融合方法层层相扣，充分利用多层次融合结果表明通过目标特征的精细化分析实现了舰船目标型号的识别。 |
| 关 键 词： | 精细化分析; 图像融合; 目标识别; SAR图像 |
| DOI： | 10.57237/j.earth.2023.02.001 |
View:
Downloads:
收稿日期: 2023-11-10
接受日期: 2023-12-15
在线出版日期: 2023-12-27
An Application Study of Remote Sensing Images for Refine Analysis of Vessel Targets
1. College of Information Engineering, Suqian University, Suqian 223800, China
2. College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China
| Abstract: | With the emergence of high-resolution images, ocean monitoring has not only stayed in the stage of the target discovery. Through the qualitative analysis of the main components of the target, the refine identification of the military ship target can be pointed out as well as its type and equipment, which effectively respond to the combat readiness level and regional dynamics of the military area. Compared with the single source remote sensing images, the fusion images can provide more comprehensive information of the objectives. Nowadays, the accepted image fusion method is divided into pixel-level, feature-level and decision-level. How to apply variety fusion methods to deep excavate complementary information is the focus of this paper. Besides, pixel-level fusion relies on the scattering characteristics of SAR images to eliminate the influence of objective interference on the detection of key components. Feature-level fusion locks the attention features through the visual feature set, and fully excavates the multi-source features of the target. In decision-level fusion, expert guidance and environmental reasoning are integrated to realize the final recognition as well as the results obtained on the above two levels of fusion. Multi-level fusion results finally realize the target recognition according to the refine analysis of target characteristics. |
| Keywords: | Refine Analysis; Image Fusion; Target Detection; SAR Image |
参考文献
| [1] | Tupin F, Roux M. Markov random field on region adjacency graph for the fusion of SAR and optical data in radargrammetric applications [J]. IEEE Transactions on Geoscience & Remote Sensing, 2005, 43(8): 1920-1928. |
| [2] | Nie M, Lu L, Xu W. A Novel Fusion and Target Detection Method of Airborne SAR Images and Optical Images [C]. International Conference on Radar. IEEE, 2007: 1-4. |
| [3] | Waske B, Linden S V D. Classifying Multilevel Imagery From SAR and Optical Sensors by Decision Fusion [J]. IEEE Transactions on Geoscience & Remote Sensing, 2008, 46(5): 1457-1466. |
| [4] | Farah I R, Boulila W, Ettabaa K S, et al. Interpretation of Multisensor Remote Sensing Images: Multiapproach Fusion of Uncertain Information [J]. IEEE Transactions on Geoscience & Remote Sensing, 2008, 46(12): 4142-4152. |
| [5] | Amini J, Sumantyo J T S. Employing a Method on SAR and Optical Images for Forest Biomass Estimation [J]. IEEE Transactions on Geoscience & Remote Sensing, 2009, 47(12): 4020-4026. |
| [6] | Tian W, Zhu W, Li J. Target fusion detection of remote sensing image based on the multifractal analysis [C]. IEEE, International Conference on Signal Processing. IEEE, 2013: 838-841. |
| [7] | Corbane C, Najman L, Pecoul E, et al. A complete processing chain for ship detection using optical satellite imagery [J]. International Journal of Remote Sensing, 2010, 31(22): 5837-5854. |
| [8] | Yang F, Xu Q, Li B. Ship Detection From Optical Satellite Images Based on Saliency Segmentation and Structure-LBP Feature [J]. IEEE Geoscience & Remote Sensing Letters, PP(99): 1-5. |
| [9] | Xie X, Xu Q, Hu L. Fast ship detection from optical satellite images based on ship distribution probability analysis [C]. International Workshop on Earth Observation and Remote Sensing Applications. IEEE, 2016. |
| [10] | Touzi R, Raney R K, Charbonneau F. On the use of permanent symmetric scatterers for ship characterization [J]. Geoscience & Remote Sensing IEEE Transactions on, 2004, 42(10): 2039-2045. |
| [11] | Hu C, Ferrofamil L, Kuang G. Ship Discrimination Using Polarimetric SAR Data and Coherent Time-Frequency Analysis [J]. Remote Sensing, 2013, 5(12): 6899-6920. |
| [12] | Yin X, Wang C, Zhang H. Vessel recognition with high resolution TerraSAR-X image based on structure feature [J]. Journal of Image & Graphics, 2012. |
| [13] | Zhu J, Qiu X, Pan Z, et al. Projection Shape Template-Based Ship Target Recognition in TerraSAR-X Images [J]. IEEE Geoscience & Remote Sensing Letters, 2017, 14(2): 222-226. |
| [14] | A. O. Knapskog, Classification of ships in TerraSAR-X images based on 3D models and silhouette matching. Proc. IEEE 8th EUSAR, Jun. 2010, pp. 1–4. |
| [15] | J. Park, S. Park, and K. Kim, “New discrimination features for SAR automatic target recognition,” IEEE Geosci. Remote Sens. Lett., vol. 10, no. 3, pp. 476–480, May 2013. |
| [16] | J. Park and K. Kim, “Modified polar mapping classifier for SAR automatic target recognition,” IEEE Trans. Aerosp. Electron. Syst., vol. 36, no. 4, pp. 1092–1106, Apr. 2014. |
| [17] | M. Amoon and G. Rezai-Rad, “Automatic target recognition of synthetic aperture radar (SAR) images based on optimal selection of Zernike moments features,” IET Comput. Vis., vol. 8, no. 2, pp. 77–85, 2014. |
| [18] | S. Papson and R. Narayanan. Classification via the shadow region in SAR imagery. IEEE Trans. Aerosp. Electron. Syst., vol. 48, no. 2, pp. 969–980, Apr. 2012. |
| [19] | Chen S, Wang H, Xu F, et al. Target Classification Using the Deep Convolutional Networks for SAR Images [J]. IEEE Transactions on Geoscience & Remote Sensing, 2016, 54(8): 4806-4817. |
| [20] | Song Tu 1, Junbo Liao 2, and Yi Su. Target Retrieval in Large-Scale and High-Resolution Synthetic Aperture Radar Imagery based on Deep Learning and Multi-Scale Saliency. 2016 IEEE International Conferernce on Image Processong (ICIP). 2016. pp: 1948-1952. |
| [21] | Schwegmann C P, Kleynhans W, Salmon B P, et al. Very deep learning for ship discrimination in Synthetic Aperture Radar imagery [C]. Geoscience and Remote Sensing Symposium. IEEE, 2016: 104-107. |
| [22] | Wang L, Yazıcı B. Height reconstruction using differential layover for SAR imagery [C]. Radar Conference. IEEE, 2017: 0163-0168. |
| [23] | Fornaro G, Serafino F, Soldovieri F. Three-dimensional focusing with multipass SAR data [J]. IEEE Transactions on Geoscience & Remote Sensing, 2003, 41(3): 507-517. |
