Vehicle Detection in Multi-aspect SAR Images Based on Improved GOFRO

LIU Qi; YU Weidong; HONG Wen

doi:10.12000/JR23042

Volume 12 Issue 5

Oct. 2023

Turn off MathJax

Article Contents

Abstract

References

Article Navigation > Journal of Radars > 2023 > 12(5): 1081-1096

Wu Sunyong, Xue Qiutiao, Zhu Shengqi, Yan Qingzhu, Sun Xiyan. Track-Before-Detect Algorithm for Weak Extended Target Based on Particle Filter under Clutter Environment[J]. Journal of Radars, 2017, 6(3): 252-258. doi: 10.12000/JR16128

Citation:

LIU Qi, YU Weidong, and HONG Wen. Vehicle detection in multi-aspect SAR images based on improved GOFRO[J]. Journal of Radars, 2023, 12(5): 1081–1096. doi: 10.12000/JR23042

Citation:

LIU Qi, YU Weidong, and HONG Wen. Vehicle detection in multi-aspect SAR images based on improved GOFRO[J]. Journal of Radars, 2023, 12(5): 1081–1096. doi: 10.12000/JR23042

PDF( 3593 KB)

Vehicle Detection in Multi-aspect SAR Images Based on Improved GOFRO

DOI: 10.12000/JR23042

LIU Qi^{1, 2},
YU Weidong^{1, 2
,
,},
HONG Wen^{1, 2}

1.
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
2.
University of Chinese Academy of Sciences, School of Electronic, Electrical and Communication Engineering, Beijing 101408, China

Funds: The National Natural Science Foundation of China (61860206013)

More Information

Corresponding author: YU Weidong, yuwd@aircas.ac.cn
Received Date: 2023-04-10
Rev Recd Date: 2023-05-14

Available Online: 2023-05-20

Publish Date: 2023-06-20

Abstract

Abstract

Vehicle targets in urban scenes have the characteristics of random distribution and can be easily disturbed by environmental factors during the detection process. Given the above issues, this paper proposes a detection method that utilizes multi-aspect Synthetic Aperture Radar (SAR) images for stationary vehicle target extraction. In the feature extraction stage, a novel feature extraction method called Multiscale Rotational Gabor Odd Filter-based Ratio Operator (MR-GOFRO) is designed for vehicle targets in multi-aspect SAR images, where the original GOFRO features are improved from four aspects—filter form, feature scale, feature direction and feature level. The improvement allows MR-GOFRO to adapt to possible variations in the target direction, scale, morphology, etc. In the image fusion stage, a Weighted-Non-negative Matrix Factorization (W-NMF) method is developed to adjust the feature weights from various images according to the feature quality. This method can reduce the quality degradation of the fusion features due to mutual interference between different aspects. The proposed method is verified on various airborne multi-aspect image datasets. The experimental results revealed that the feature extraction and feature fusion methods proposed in this paper enhance the detection accuracy by an average of 3.69% and 4.67%, respectively, compared with similar methods.
- Multi-aspect SAR,
- Vehicle target detection,
- Feature extraction,
- Feature selection,
- Image fusion

FullText(HTML)

References(24)

References

[1]	LEITLOFF J, HINZ S, and STILLA U. Vehicle detection in very high resolution satellite images of city areas[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(7): 2795–2806. doi: 10.1109/TGRS.2010.2043109
[2]	PALUBINSKAS G and RUNGE H. Change detection for traffic monitoring in TerraSAR-X imagery[C]. 2008 IEEE International Geoscience and Remote Sensing Symposium, Boston, USA, 2008: I-169–I-172,
[3]	MITTERMAYER J, WOLLSTADT S, PRATS-IRAOLA P, et al. The TerraSAR-X staring spotlight mode concept[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(6): 3695–3706. doi: 10.1109/TGRS.2013.2274821
[4]	ZOU Bin, QIN Jiang, and ZHANG Lamei. Vehicle detection based on semantic-context enhancement for high-resolution SAR images in complex background[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 4503905. doi: 10.1109/LGRS.2021.3139605
[5]	MAKSYMIUK O, SCHMITT M, BRENNER A R, et al. First investigations on detection of stationary vehicles in airborne decimeter resolution SAR data by supervised learning[C]. 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, Germany, 2012: 3584–3587.
[6]	BAUMGARTNER S V and KRIEGER G. Real-time road traffic monitoring using a fast a priori knowledge based SAR-GMTI algorithm[C]. 2010 IEEE International Geoscience and Remote Sensing Symposium, Honolulu, USA, 2010: 1843–1846.
[7]	NOVAK L M, OWIRKA G J, and BROWER W S. Performance of 10- and 20-target MSE classifiers[J]. IEEE Transactions on Aerospace and Electronic Systems, 2000, 36(4): 1279–1289. doi: 10.1109/7.892675
[8]	EL-DARYMLI K, GILL E W, MCGUIRE P, et al. Automatic target recognition in synthetic aperture radar imagery: A state-of-the-art review[J]. IEEE Access, 2016, 4: 6014–6058. doi: 10.1109/ACCESS.2016.2611492
[9]	CHENG Gong and HAN Junwei. A survey on object detection in optical remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 117: 11–28. doi: 10.1016/j.isprsjprs.2016.03.014
[10]	WANG Zhixu, XIN Zhihui, HUANG Xiaoqiao, et al. Overview of SAR Image Feature Extraction and Target Recognition[M]. JAIN L C, KOUNTCHEV R, and SHI Junsheng. 3D Imaging Technologies—Multi-dimensional Signal Processing and Deep Learning. Singapore: Springer, 2021: 69–75.
[11]	LI Lu, DU Yuang, and DU Lan. Vehicle target detection network in SAR images based on rectangle-invariant rotatable convolution[J]. Remote Sensing, 2022, 14(13): 3086. doi: 10.3390/rs14133086
[12]	YANG Xinpeng, ZHANG Qiang, ZHAO Shixiang, et al. Focal-pyramid-based vehicle segmentation in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 4028705. doi: 10.1109/LGRS.2022.3224904
[13]	BRENNER A R, ESSEN H, and STILLA U. Representation of stationary vehicles in ultra-high resolution SAR and turntable ISAR images[C]. The 9th European Conference on Synthetic Aperture Radar, Nuremberg, Germany, 2012: 147–150.
[14]	WANG Guoli, WANG Xinchao, FAN Bin, et al. Feature extraction by rotation-invariant matrix representation for object detection in aerial image[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(6): 851–855. doi: 10.1109/LGRS.2017.2683495
[15]	SUN Yi, WANG Wenna, ZHANG Qianyu, et al. Improved YOLOv5 with transformer for large scene military vehicle detection on SAR image[C]. The 2022 7th International Conference on Image, Vision and Computing, Xi’an, China, 2022: 87–93.
[16]	龙泓琳, 皮亦鸣, 曹宗杰. 基于非负矩阵分解的SAR图像目标识别[J]. 电子学报, 2010, 38(6): 1425–1429. LONG Honglin, PI Yiming, and CAO Zongjie. Non-negative matrix factorization for target recognition[J]. Acta Electronica Sinica, 2010, 38(6): 1425–1429.
[17]	ZHANG Haichao, NASRABADI N M, ZHANG Yanning, et al. Multi-view automatic target recognition using joint sparse representation[J]. IEEE Transactions on Aerospace and Electronic Systems, 2012, 48(3): 2481–2497. doi: 10.1109/TAES.2012.6237604
[18]	MA Wenping, WEN Zelian, WU Yue, et al. Remote sensing image registration with modified SIFT and enhanced feature matching[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(1): 3–7. doi: 10.1109/LGRS.2016.2600858
[19]	XIANG Yuming, WANG Feng, WAN Ling, et al. An advanced multiscale edge detector based on Gabor filters for SAR imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(9): 1522–1526. doi: 10.1109/LGRS.2017.2720684
[20]	PAUL S and PATI U C. A Gabor odd filter-based ratio operator for SAR image matching[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(3): 397–401. doi: 10.1109/LGRS.2018.2872979
[21]	张之光, 雷宏. 基于SAR图像样本的本征维数检测人造目标[J]. 电子测量技术, 2016, 39(9): 34–39. doi: 10.3969/j.issn.1002-7300.2016.09.009 ZHANG Zhiguang and LEI Hong. Man-made targets detection based on intrinsic dimension of SAR image samples[J]. Electronic Measurement Technology, 2016, 39(9): 34–39. doi: 10.3969/j.issn.1002-7300.2016.09.009
[22]	ZHANG Tianwen, ZHANG Xiaoling, KE Xiao, et al. HOG-ShipCLSNet: A novel deep learning network with HOG feature fusion for SAR ship classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5210322. doi: 10.1109/TGRS.2021.3082759
[23]	OLUKANMI P O and TWALA B. K-means-sharp: Modified centroid update for outlier-robust k-means clustering[C]. 2017 Pattern Recognition Association of South Africa and Robotics and Mechatronics, Bloemfontein, South Africa, 2017: 14–19,
[24]	WU Xin, HONG Danfeng, TIAN Jiaojiao, et al. ORSIm detector: A novel object detection framework in optical remote sensing imagery using spatial-frequency channel features[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 57(7): 5146–5158. doi: 10.1109/TGRS.2019.2897139