基于改进YOLOv3的合成孔径雷达图像中建筑物检测算法

doi:10.3969/j.issn.1000-1093.2020.07.012

兵工学报 ›› 2020, Vol. 41 ›› Issue (7): 1347-1359.doi: 10.3969/j.issn.1000-1093.2020.07.012

基于改进YOLOv3的合成孔径雷达图像中建筑物检测算法

李响^1，2，苏娟¹，杨龙^1，3

（1.火箭军工程大学核工程学院，陕西西安 710025； 2.96823部队，云南昆明 650000；3.96873部队，陕西宝鸡 721000）

收稿日期:2019-07-05 修回日期:2019-07-05 上线日期:2020-09-23
通讯作者: 苏娟（1973—），女，副教授 E-mail:suj04@mails.tsinghua.edu.cn
作者简介:李响（1995—），女，硕士研究生。E-mail：idmuzi@126.com
基金资助:
国家自然科学基金项目（61302195）

A SAR Image Building Detection Algorithm Based on Improved YOLOv3

LI Xiang^1,2， SU Juan¹， YANG Long^1,3

(1.College of Nuclear Engineering, Rocket Force University of Engineering, Xi'an 710025, Shaanxi, China; 2.Unit 96823 of PLA, Kunming 650000, Yunnan, China; 3.Unit 96873 of PLA, Baoji 721000, Shaanxi, China)

Received:2019-07-05 Revised:2019-07-05 Online:2020-09-23

摘要/Abstract

摘要： 传统合成孔径雷达（SAR）图像中建筑物检测算法主要是在特定场景下通过人工提取特征进行特定类别的建筑物检测，存在平均检测精度不高、检测效率低的问题，为此提出一种基于改进YOLOv3的SAR图像中建筑物检测算法，通过深度学习实现建筑物的自动检测。制作SAR图像中建筑物数据集，针对建筑物的尺寸特点，通过改进的K均值聚类算法重新设置先验框大小；在结构上借鉴深度神经网络的聚合残差转换思想，将YOLOv3骨架网络中用于构建特征层的单路卷积残差模块改进为多路卷积残差模块，提高通道信息利用率的同时降低计算量；加入浅层特征融合模块，增加特征图中建筑物的形状特征所占比重，在特征融合层之前，使用转置卷积进行上采样，增加细节特征；使用改进YOLOv3算法进行建筑物检测模型的训练，并在测试集上进行测试。实验结果表明，相比原始YOLOv3算法，改进YOLOv3算法在SAR图像中建筑物数据集上平均检测精度提高了9.2%，召回率提高了6.3%，同时保持了较快的检测速度。

关键词: 建筑物检测, 合成孔径雷达图像, YOLOv3, 残差模块, 浅层特征融合

Abstract: Since the traditional synthetic aperture radar （SAR）image building detection algorithm is mainly to detect the specific buildings by manually extracting the features in specific scenarios, it always has low average detection accuracy and low detection efficiency. A SAR image building detection algorithm based on improved YOLOv3 is proposed to realize the automatic detection of buildings through deep learning. The SAR image building dataset is produced, and the sizes of priori anchors are re-set by the improved K-means clustering algorithm according to the size characteristics of the buildings. Then the structure of the aggregated residual transformations for deep neural networks is used to construct the feature layer of YOLOv3 skeleton network. The single-channel convolution residual module is improved into a multi-channel convolution residual module to increase the channel information utilization and reduce the computation load. And a shallow feature fusion module is added to increase the contour shape characteristics of buildings in the feature map. The feature layer is upsampled to add detail features before the feature fusion layer through the transposed convolution. The improved YOLOv3 algorithm is used to train the building detection model which is tested on the test dataset. Experimental results show that the improved YOLOv3 algorithm improves the average detection accuracy on SAR image building dataset by 9.2% and the recall rate by 6.3% compared with the original YOLOv3 algorithm, while maintaining a fast detection speed. Key

Key words: buildingdetection, syntheticapertureradarimage, YOLOv3, residualmodule, shallowfeaturefusion

中图分类号:

TP751.1

李响，苏娟，杨龙. 基于改进YOLOv3的合成孔径雷达图像中建筑物检测算法[J]. 兵工学报, 2020, 41(7): 1347-1359.

LI Xiang， SU Juan， YANG Long. A SAR Image Building Detection Algorithm Based on Improved YOLOv3[J]. Acta Armamentarii, 2020, 41(7): 1347-1359.

参考文献

［1］ HU L, ZHANG J, GAO F. A building extraction method using shadow in high resolution multispectral images[C]∥Proceedings of International Geoscience and Remote Sensing Symposium. Vancouver, BC, Canada: IEEE, 2011: 24-29.
[2］ KONSTANTINIDIS D, STATHAKI T, ARGYRIOU V, et al. Building detection using enhanced HOG-LBP features and region refinement processes[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 10(3): 888-905.
[3］刘静, 温显斌. 基于改进MRF的高分辨率SAR图像中建筑物轮廓提取算法[J]. 天津理工大学学报, 2014, 30(6):28-32.
LIU J, WEN X B. Building extraction from very high resolution SAR images based on improved Markov random field models[J]. Journal of Tianjin University of Technology, 2014,30(6):28-32. (in Chinese)
[4］姜萍, 刘修国, 陈启浩, 等. 利用多尺度SVM-CRF模型的极化SAR图像建筑物提取[J]. 遥感技术与应用, 2017, 32(3):475-482.
JIANG P, LIU X G, CHEN Q H, et al. A multi-scale SVM-CRF model for buildings extraction from polarimetric SAR images[J]. Remote Sensing Technology and Application, 2017, 32(3):475-482. (in Chinese)
[5］ DING J, CHEN B, LIU H W, et al. Convolutional neural network with data augmentation for SAR target recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(3): 364-368.
[6］李健伟, 曲长文, 彭书娟,等. 基于卷积神经网络的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2018, 40(9):1953-1959.
LI J W, QU C W, PENG S J, et al. Ship detection in SAR images based on convolutional neural network[J]. Systems Engineering and Electronics, 2018, 40(9):1953-1959. (in Chinese)
[7］郭智, 宋萍, 张义, 等. 基于深度卷积神经网络的遥感图像飞机目标检测方法[J]. 电子与信息学报, 2018, 40(11): 2684-2690.
GUO Z, SONG P, ZHANG Y, et al. Aircraft detection method based on deep convolutional neural network for remote sensing images[J]. Journal of Electronics & Information Technology, 2018, 40(11): 2684-2690. (in Chinese)
[8］ CORENTIN H, MAJID A S, NINA M. Road segmentation in SAR satellite images with deep fully convolutional neural networks[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(12):1867-1871.
[9］ SHAHZAD M, MAURER M, FRAUNDORFER F, et al. Buildings detection in VHR SAR images using fully convolution neural networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 57(2):1100-1116.

[10］ WANG P Y, PATEL V M. Generating high quality visible images from SAR images using CNNs[C]∥Proceedings of 2018 IEEE Radar Conference. Oklahoma City, OK,US: IEEE, 2018:570-575.
[11］ GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]∥Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, US: IEEE, 2014:580-587.
[12］ GIRSHICK R． Fast R-CNN[C]∥Proceedings of IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2015:1440-1448.
[13］ REN S Q, HE K M, GIRSHICK R，et al． Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(6):1137-1149.
[14］ REDMON J, DIVVALA S, GIRSHICK R, et al． You only look once: unified, real-time object detection［C］∥Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, US: IEEE, 2016:779-788.
[15］ LIU W, ANGUELOV D, ERHAN D, et al． SSD: singleshot multibox detector[C]∥Proceedings of European Conference on Computer Vision. Cambridge, MA, US: MIT Press, 2016:21-37．
[16］ REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, US: IEEE, 2017:6517-6525.
[17］ REDMON J, FARHADI A. YOLOv3: an incremental improvement: arXiv: 1804.02767v1[R/OL]. Ithaca, NY, US: Cornell University, (2018-04-08) ［2019-05-15］. https:∥arxiv.org/abs/1804.02767.
[18］李健伟,曲长文,彭书娟,等. 基于生成对抗网络和线上难例挖掘的SAR图像舰船目标检测[J]. 电子与信息学报, 2019, 41(1):143-149.
LI J W, QU C W, PENG S J, et al. Ship detection in SAR images based on generative adversarial network and online hard examples mining[J]. Journal of Electronics and Information Technology, 2019, 41(1):143-149. (in Chinese)
[19］ HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, US: IEEE, 2016:770-778.
[20］ XIE S N, GIRSHICK R, DOLLR P, et al. Aggregated residual transformations for deep neural networks[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, US: IEEE, 2017: 5987-5995.
[21］ SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, Inception-ResNet and the impact of residual connections on learning: arXiv: 1602.07261v2[R/OL]. Ithaca, NY, US: Cornell University, (2016-08-23) ［2019-06-02］. https:∥arxiv.org/abs/1602.07261.
[22］ ZEILER M D, TAYLOR G W, FERGUS R. Adaptive deconvolutional networks for mid and high level feature learning[C]∥Proceedings of 2011 International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011:2018-2025.

第41卷第7期2020 年7月
兵工学报ACTA ARMAMENTARII
Vol.41No.7Jul.2020

[1]	王少博，张成，苏迪，冀瑞静. 基于改进YOLOv3和核相关滤波算法的旋转弹目标探测算法[J]. 兵工学报, 2022, 43(5): 1032-1045.
[2]	于博文，吕明. 改进的YOLOv3算法及其在军事目标检测中的应用[J]. 兵工学报, 2022, 43(2): 345-354.
[3]	徐英，谷雨，彭冬亮，刘俊，陈华杰. 面向合成孔径雷达图像任意方向舰船检测的改进YOLOv3模型[J]. 兵工学报, 2021, 42(8): 1698-1707.
[4]	伍薇, 苏娟. 一种基于双向匹配融合的合成孔径雷达景象匹配算法[J]. 兵工学报, 2019, 40(1): 124-133.
[5]	庞海洋，王岩飞，张健. 基于合成孔径雷达图像的伪装遮障目标特性建模技术[J]. 兵工学报, 2016, 37(3): 559-564.
[6]	袁礼海，宋建林，沈涛. 合成孔径雷达围像特征关键度分析与分类算法研究[J]. 兵工学报, 2007, 28(10): 1186-1190.

基于改进YOLOv3的合成孔径雷达图像中建筑物检测算法

A SAR Image Building Detection Algorithm Based on Improved YOLOv3

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价