Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (2): 275-284    DOI: 10.11873/j.issn.1004-0323.2021.2.0275
CNN 专栏     
基于优化Faster-RCNN的遥感影像飞机检测
林娜1,2(),冯丽蓉1(),张小青1
1.重庆交通大学 土木工程学院,重庆 400074
2.重庆市地理信息和遥感应用中心,重庆 401147
Aircraft Detection in Remote Sensing Image based on Optimized Faster-RCNN
Na Lin1,2(),Lirong Feng1(),Xiaoqing Zhang1
1.School of Civil Engineering,Chongqing Jiaotong University,Chongqing 400074,China
2.Chongqing Geomatics and Remote Sensing Application Center,Chongqing 401147,China
 全文: PDF(12408 KB)   HTML
摘要:

针对传统飞机检测算法特征学习能力较弱,在背景复杂、目标密集、成像质量较差的遥感影像上检测精度较低的问题,提出了一种基于Faster-RCNN(Faster-Regions with Convolutional Neural Network)框架的遥感影像飞机检测优化算法。以ResNet50为基础特征提取网络,引入空洞残差块进行多层特征融合,构建新的特征提取网络,提高算法的特征提取能力。首先在UCAS-AOD数据集上采用交叉验证训练方法验证模型在不同训练集与测试集上的稳定性,同时比较不同算法的检测性能;然后在NWPU VHR-10数据集上进行飞机检测对比实验,验证模型泛化性。实验结果表明:在UCAS-AOD数据集上优化算法平均精度为97.1%,在NWPU VHR-10数据集上优化算法平均精度为96.2%。该优化算法能够提升遥感影像中飞机的检测精度,且泛化性更强,对实现遥感影像飞机快速检测具有一定的参考意义。

关键词: 深度学习遥感影像目标检测特征融合空洞残差块    
Abstract:

To address the problem that traditional aircraft detection methods have low detection accuracy on remote sensing images with complex backgrounds and dense targets, an improved remote sensing image aircraft target detection algorithm based on Faster-RCNN (Faster-Regions with Convolutional Neural Network) is proposed. ResNet50 is used as the basic feature extraction network of the algorithm, and the dilated bottlenecks are introduced for multi-layer feature fusion to construct a new feature extraction network, which improve the feature extraction capability of the algorithm. First, the cross-validation training method is used on the UCAS-AOD data set to verify the stability of the model on different training sets and test sets, and compare the detection performance of different algorithms. Then, comparative experiment is conducted on the NWPU VHR-10 data set to verify the generalization of the model. Experimental results showed that: The average precision of the proposed algorithm is 97.1% on the UCAS-AOD data set and 96.2% on the NWPU VHR-10 data set. The study indicated that the proposed algorithm in this paper can not only improve the detection accuracy of aircraft in remote sensing images, but also have a stronger generalization, which has certain reference significance to the rapid detection of aircraft in remote sensing images.

Key words: Deep learning    Remote sensing image    Object detection    Feature fusion    Dilated bottleneck
收稿日期: 2020-04-21 出版日期: 2021-05-24
ZTFLH:  TP75  
基金资助: 重庆市教委科技项目(KJQN201800747);重庆交通大学研究生教育创新基金项目(2020S0001)
通讯作者: 冯丽蓉     E-mail: linnawb@126.com;862456630@qq.com
作者简介: 林娜(1981-),女,湖北襄阳人,博士,副教授,主要从事深度学习在遥感图像处理中的应用研究。E?mail: linnawb@126.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
林娜
冯丽蓉
张小青

引用本文:

林娜,冯丽蓉,张小青. 基于优化Faster-RCNN的遥感影像飞机检测[J]. 遥感技术与应用, 2021, 36(2): 275-284.

Na Lin,Lirong Feng,Xiaoqing Zhang. Aircraft Detection in Remote Sensing Image based on Optimized Faster-RCNN. Remote Sensing Technology and Application, 2021, 36(2): 275-284.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.2.0275        http://www.rsta.ac.cn/CN/Y2021/V36/I2/275

图1  Faster-RCNN框架结构
图2  候选区域生成网络(RPN)
阶段结构
14×14,平均池化,1000-d fc,SoftMax
conv17×7,64,步长=2
conv2

3×3,最大池化,步长=2

1×1??643×3??641×1?256×3,步长=1

conv31×1?1283×3?1281×1?512×4,步长=2
conv41×12563×32561×11024×6,步长=2
conv51×15123×35121×12048×3,步长=2
表1  ResNet50网络结构
图3  Faster-RCNN与ResNet50结合
图4  改进后的特征提取网络
图5  实验数据示例图
实验方法准确率召回率AP(0.50)AP(0.75)AP(0.85)
Faster-RCNN+VGG均值88.392.589.246.723.2
方差0.0200.0520.0200.0760.068
Faster-RCNN+ResNet50均值91.794.692.852.325.4
方差0.0040.0280.0080.0280.032
优化Faster-RCNN均值97.698.797.158.930.4
方差0.0320.0280.0380.0200.044
表2  UCAS-AOD数据集上交叉验证测试结果对比
图6  UCAS-AOD数据集上测试结果对比图
实验方法准确率召回率AP (0.50)
Faster-RCNN+VGG92.894.189.3
Faster-RCNN+ ResNet5093.294.992.6
优化Faster-RCNN96.897.696.2
表3  飞机检测结果对比
图7  NWPU VHR-10数据集上检测结果图
1 Yu Donghang, Guo Haitao, Zhang Baoming, et al. Aircraft Detection in Remote Sensing Images Using Cascade Convolutional Neural Networks[J]. Acta Geodaetica et Cartographica Sinica, 2019,48(8):1046-1058.
1 余东行, 郭海涛, 张保明, 等. 级联卷积神经网络的遥感影像飞机目标检测[J]. 测绘学报, 2019, 48(8):1046-1058.
2 Li Wenbin, He Ran. Aircraft Detection Models of Remote Sensing Images based on FCN and CNN[J]. Computer Engineering,2020-03-11. doi:10.19678/j.issn.1000-3428.057070.
doi: 10.19678/j.issn.1000-3428.0057070
2 李文斌, 何冉. 基于FCN与CNN的遥感影像飞机目标检测方法[J].计算机工程,2020-03-11. doi:10.19678/j.issn.1000-3428.0057070.
doi: 10.19678/j.issn.1000-3428.0057070
3 Cai Hongping, Geng Zhenwei, Su Yi. A New Method to Detect Airplanes in Remote Sensing Image: Circle- Frequency Filter[J]. Signal Processing, 2007, 33(4): 539-543.蔡红苹, 耿振伟, 粟毅. 遥感图像飞机检测新方法——圆周频率滤波法[J]. 信号处理, 2007(4):539-543.
4 Qiu Jianbin , Li Shijin, Wang Wei. A New Approach to Detect Aircrafts in Remote Sensing Images based on Corner and Edge Information Fusion[J]. Microelectornics and Computer, 2011, 28(9):214-216.
4 仇建斌, 李士进, 王玮. 角点与边缘信息相结合的遥感图像飞机检测新方法[J]. 微电子学与计算机, 2011, 28(9):214-216.
5 Lin Yudong, He Hongjie, Yin Zhongke, et al. Air-plane Detection in Optical Remote Sensing Image based on Sparse-Representation[J]. Act Photonica Sinica, 2014, 43(9):1-6.
5 林煜东, 和红杰, 尹忠科, 等.基于稀疏表示的可见光遥感图像飞机检测算法[J]. 光子学报, 2014, 43(9):1-6.
6 Girshick R, Donahue J, Darrell T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]∥ Proceedings of the IEEE Conference on Computer Vision and Pattern Recog-nition. IEEE, 2014:580-587. doi:10.1109/CVPR.2014.81.
doi: 10.1109/CVPR.2014.81
7 Girshick R. Fast R-CNN[C]∥ Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2015:1440-1448. doi:10.1109/ICCV.2015.169.
doi: 10.1109/ICCV.2015.169
8 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, 2015, 39(6):1137-1149. doi :10.1109/TPAMI.2016.2577031.
doi: 10.1109/TPAMI.2016.2577031
9 Redmon J, Divvala S, Girshick R, et al. You only Look Once: Unified, Real-time Object Detection[C]∥ IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society,2016:779-788. doi:10.1109/CVPR. 2016.91.
doi: 10.1109/CVPR. 2016.91
10 Liu Wei, Anguelov D, Erhan D, et al. SSD: Single Shot MultiBox Detector[M]. Computer Vision-ECCV 2016. Springer International Publishing, 2016:21-37. doi: 10.1007/978-3-319-46448-0_2.
doi: 10.1007/978-3-319-46448-0_2
11 Yin Wenbin, Wang Chengbo, Yuan Cui, et al. A Method of Aircraft Recognition in Remote Sensing Images[J]. Bulletin of Surveying and Mapping,2017(3):34-37.殷文斌,王成波, 袁翠,等.一种飞机目标的遥感识别方法[J].测绘通报, 2017(3):34-37.
12 Zhu Mingming, Xu Yuelei, Ma Shiping, et al. Airplane Detection based on Feature Fusion and Soft Decision in Remote Sensing Images[J]. Acta Optica Sinica, 2019, 39(2):71-77.
12 朱明明, 许悦雷, 马时平, 等. 基于特征融合与软判决的遥感图像飞机检测[J]. 光学学报, 2019, 39(2):71-77.
13 Xu Y L, Zhu M M, Peng X, et al. Rapid Airplane Detection in Remote Sensing Images based on Multilayer Feature Fusion in Fully Convolutional Neural Networks[J].Sensors,2018, 18(7):2335-2347. doi:10.33 90/s18072335.
doi: 10.33 90/s18072335
14 Zhang Zhongbao, Wang Hongyuan, Zhang Ji, et al. Remote Sensing Image Aircraft Detection Algorithm based on Faster RCNN[J]. Journal of Nanjing Normal University(Natural Science Edition) , 2018, 41(4):79 -86.
14 张中宝, 王洪元, 张继, 等. 基于 Faster-RCNN 的遥感图像飞机检测算法[J]. 南京师大学报(自然科学版), 2018, 41(4):79-86.
15 Dai Yuan, Yi Benshun. Xiao Jinsheng, et al.Object Detection of Remote Sensing Image based on Improved Rotation Region Proposal Network[J].Acta Optica Si-nica,2020,40(1):270-280.
15 戴媛, 易本顺, 肖进胜, 等.基于改进旋转区域生成网络的遥感图像目标检测[J].光学学报, 2020, 40(1):270-280.
16 Li Shumin, Feng Quanlong, Liang Qichun, et al. Aircraft Auto-detection in Domestic High Resolution Remote Sensing Images Using Deep Learning[J].Remote Sensing Technology and Application,2018,33(6):1095-1102.
16 李淑敏, 冯权泷, 梁其椿, 等. 基于深度学习的国产高分遥感影像飞机目标自动检测[J]. 遥感技术与应用, 2018, 33(6):1095 -1102.
17 Pei Wei, Xu Yanming, Zhu Yongying, et al. The Target Detection Method of Aerial Photography Images with Improved SSD[J]. Journal of Software,2019,30(3):738-758.
17 裴伟, 许晏铭, 朱永英, 等. 改进的SSD航拍目标检测方法. 软件学报, 2019, 30(3):738-758.
18 Yao Qunli, Hu Xian, Lei Hong. Aircraft Detection in Remote Sensing Imagery with Multi-scale Feature Fusion Convolutional Neural Networks[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(10):1266-1274.
18 姚群力, 胡显, 雷宏. 基于多尺度融合特征卷积神经网络的遥感图像飞机目标检测[J]. 测绘学报, 2019, 48(10):1266-1274.
19 He K M, Zhang X Y, Ren S Q, et al. Deep Residual Learning for Image Recognition[C]∥ Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, United States: IEEE, 2016:770-778. doi:10.1109/CVPR.2016.90.
doi: 10.1109/CVPR.2016.90
20 Zeiler M D, Fergus R. Visualizing and Understanding Convolutional Networks[C]∥ European Conference on Computer Vision. Zurich: Springer,2014:818-833.
21 Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-scale Image Recognition[C]∥ International Conference on Learning Representations. San Diego:IEEE, 2015:1-14.
22 Ren S Q, He K M, Girshick R, et al. Object Detection Networks on Convolutional Feature Maps[J]. IEEE Transactions on Pattern Analysis and Machin-e Intelligence, 2016, 39(7):1476-1481. doi: 10.1109/TP-MAI.2016.2601099.
doi: 10.1109/TP-MAI.2016.2601099
23 Li Z M, Chao P, Yu G, et al. DetNet: A Backbone Network for Object Detection[J/OL].(2018-04-19)[2019-04-26]. .
24 Zhu H G, Chen X G, Dai W Q, et al. Orientation Robust Object Detection in Aerial Images Using Deep Convolutional Neural Network[C]∥ Proceedings of the IEEE International Conference on Image Processing. Quebec,2015: 3735-3739.
25 Cheng G, Han J W, Zhou P C, et al. Multi-class Geospatial Object Detection and Geographic Image Classification based on Collection of Part Detectors[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 98(1):119-132. doi: 10.1016/j.isprsjprs.2014.10.002.
doi: 10.1016/j.isprsjprs.2014.10.002
26 Cheng G, Han J W. 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.
doi: 10.1016/j.isprsjprs.2016.03.014
27 Cheng G, Zhou P C, Han J W. Learning Rotation-Invariant Convolutional Neural Networks for Object Detection in VHR Optical Remote Sensing Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016,54(12):7405-7415. doi: 10.1109/TGRS.2016.2601 622.
doi: 10.1109/TGRS.2016.2601 622
28 Zhang Le, Jin Xiu, Fu Leiyang, et al. Recognition Method for Weeds in Rapeseed Field based on Faster R-CNN Deep Network[J]. Laser & Optoelectronics Progress, 2020,57(2):304-312.
28 张乐,金秀,傅雷扬,等.基于Faster R-CNN深度网络的油菜田间杂草识别方法[J].激光与光电子学进展,2020,57(2):304-312.
29 Wang Yingjie, Zhang Qiao, Zhang Yanmei, et al. Oil Tank Detection from Remote Sensing Images based on Deep Convolutional Neural Network[J]. Remote Sensing Technology and Application, 2019, 34(4):727-735.
29 王颖洁, 张荞, 张艳梅, 等. 基于深度卷积神经网络的油罐目标检测研究[J]. 遥感技术与应用, 2019, 34(4): 727-735.
[1] 陈敏,潘佳威,李江杰,徐璐,刘加敏,韩健,陈奕云. 结合VGGNet与Mask R-CNN的高分辨率遥感影像建设用地检测[J]. 遥感技术与应用, 2021, 36(2): 256-264.
[2] 胡乃勋,陈涛,甄娜,牛瑞卿. 基于卷积神经网络的面向对象露天采场提取[J]. 遥感技术与应用, 2021, 36(2): 265-274.
[3] 徐瑾昊,冯敏,王建邦,冉有华,祁元,杨联安,李新. 基于高分遥感数据和深度学习的石冰川自动提取研究[J]. 遥感技术与应用, 2020, 35(6): 1329-1336.
[4] 张永宏,曹海啸,阚希. 基于FY-4A/AGRI时空特征融合的新疆地区积雪判识[J]. 遥感技术与应用, 2020, 35(6): 1337-1347.
[5] 柴栋,许夙晖,罗畅,鲁彦辰. 使用贝叶斯优化对遥感影像目标进行精确定位[J]. 遥感技术与应用, 2020, 35(6): 1377-1385.
[6] 杨瑞,祁元,苏阳. 深度学习U-Net方法及其在高分辨卫星影像分类中的应用[J]. 遥感技术与应用, 2020, 35(4): 767-774.
[7] 王卓,闫浩文,禄小敏,冯天文,李亚珍. 一种改进U-Net的高分辨率遥感影像道路提取方法[J]. 遥感技术与应用, 2020, 35(4): 741-748.
[8] 连喜红,祁元,王宏伟,张金龙,杨瑞. 基于面向对象的青海湖环湖区居民地信息自动化提取[J]. 遥感技术与应用, 2020, 35(4): 775-785.
[9] 张峰极,吴艳兰,姚雪东,梁泽毓. 基于改进DenseNet网络的多源遥感影像露天开采区智能提取方法[J]. 遥感技术与应用, 2020, 35(3): 673-684.
[10] 李越帅,郑宏伟,罗格平,杨辽,王伟胜,桂东伟. 集成U-Net方法的无人机影像胡杨树冠提取和计数[J]. 遥感技术与应用, 2019, 34(5): 939-949.
[11] 曹小杰,江洪,张兆明,何国金,赵晶晶. Landsat8卫星影像大气校正及其植被指数与SEVI性能比较[J]. 遥感技术与应用, 2019, 34(5): 983-991.
[12] 刘天福,陈学泓,董琪,曹鑫,陈晋. 深度学习在GlobeLand30-2010产品分类精度优化中应用研究[J]. 遥感技术与应用, 2019, 34(4): 685-693.
[13] 林志玮,丁启禄,黄嘉航,涂伟豪,胡典,刘金福. 基于DenseNet的无人机光学图像树种分类研究[J]. 遥感技术与应用, 2019, 34(4): 704-711.
[14] 崔先亮,陈立福,邢学敏,袁志辉. 基于频带特征融合的GL-CNN遥感图像场景分类[J]. 遥感技术与应用, 2019, 34(4): 712-719.
[15] 王颖洁,张荞,张艳梅,蒙印,郭文. 基于深度卷积神经网络的油罐目标检测研究[J]. 遥感技术与应用, 2019, 34(4): 727-735.