首页 > 论文 > 光学学报 > 40卷 > 16期(pp:1628005--1)

联合连续学习的残差网络遥感影像机场目标检测方法

Airport Detection Method Combined with Continuous Learning of Residual-Based Network on Remote Sensing Image

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

在现有的高分辨率、大尺度目标遥感图像的检测中,传统方法由于提取特征手段单一、速度慢而无法快速并准确地从光学遥感影像中实现机场目标的识别。受人类视觉系统层次认知的启发,提出了一种适用于中高分辨率光学遥感影像的机场目标检测网络(CLRNet)。首先构建深度残差块,并将其作为特征提取网络;然后基于生成的样本核心集,采用连续学习方式从海量遥感数据中逐次迭代,精调机场检测模型;经过连续学习得到了鲁棒性强、遗忘度低的检测模型,该模型可以准确快速地从海量复杂背景下的光学遥感影像中识别出机场目标,而且对薄云遮挡以及卫星拍摄不全的机场有较好的识别效果。选取国产吉林一号卫星影像数据集进行测试,结果表明:所提方法的检测精度mAP(IoU不小于0.5)可达0.9613,每景的检测时间为0.23 s。

Abstract

In the existing high-resolution and large-scale target remote sensing image object detection, the traditional method cannot achieve airport target recognition from optical remote sensing images quickly and accurately due to the single feature extraction and slow speed. Inspired by the hierarchical cognition of the human visual system, the continuous learning of residual-based convolution neural network (CLRNet) suitable for medium and high resolution optical remote sensing images is proposed. Firstly, the depth residual block is constructed as the feature extraction network. Secondly, the continuous learning method is used to fine tune the airport detection model from the massive remote sensing data. After continuous learning process, the model with strong robustness and low forgetting degree is obtained. The model can accurately and quickly identify airport from optical remote sensing images under massive and complex backgrounds. Our model has a better recognition effect for airports covered by thin clouds or incompletely captured by satellites. The domestic Jilin-1 satellite image dataset is selected for testing. Experiments show that the accuracy of the detection method mAP (IoU is not less than 0.5) can reach 0.9613, and the detection speed can reach 0.23 s per scene.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP751.1

DOI:10.3788/AOS202040.1628005

所属栏目:遥感与传感器

基金项目:国家重点研发计划重点专项; 吉林省重点科技研发项目;

收稿日期:2020-03-28

修改稿日期:2020-05-18

网络出版日期:2020-08-01

作者单位    点击查看

李竺强:长光卫星技术有限公司,吉林省卫星遥感应用技术重点实验室, 吉林 长春 130000
朱瑞飞:长光卫星技术有限公司,吉林省卫星遥感应用技术重点实验室, 吉林 长春 130000中国科学院长春光学精密机械与物理研究所, 吉林 长春 130033
马经宇:长光卫星技术有限公司,吉林省卫星遥感应用技术重点实验室, 吉林 长春 130000
孟祥玉:吉林省国土资源调查规划研究院, 吉林 长春 130061
王栋:长光卫星技术有限公司,吉林省卫星遥感应用技术重点实验室, 吉林 长春 130000中国科学院长春光学精密机械与物理研究所, 吉林 长春 130033
刘思言:长光卫星技术有限公司,吉林省卫星遥感应用技术重点实验室, 吉林 长春 130000

联系人作者:李竺强(skybelongtous@foxmail.com)

备注:国家重点研发计划重点专项; 吉林省重点科技研发项目;

【1】Zhong X, An Y, Wang D, et al. Jilin-1 construction of commercial aerospace remote sensing service system Satellite Application[J]. 0, 2020(3): 8-17.
钟兴, 安源, 王栋, 等. 吉林一号商业航天遥感服务体系建设 卫星应用[J]. 0, 2020(3): 8-17.

【2】Wang X, Wang B, Zhang L M. Airport detection in remote sensing images based on visual attention [M]. ∥Neural Information Processing. Berlin, Heidelberg: Springer Berlin Heidelberg. 2011, 475-484.

【3】Koc-San D, Selim S, Aslan N, et al. Automatic citrus tree extraction from UAV images and digital surface models using circular Hough transform [J]. Computers and Electronics in Agriculture. 2018, 150: 289-301.

【4】Zhu D, Wang B, Zhang L M. Airport target detection in remote sensing images: a new method based on two-way saliency [J]. IEEE Geoscience and Remote Sensing Letters. 2015, 12(5): 1096-1100.

【5】Aytekin ?, Z?ngür U, Halici U. Texture-based airport runway detection [J]. IEEE Geoscience and Remote Sensing Letters. 2013, 10(3): 471-475.

【6】Yu D H, Zhang N, Zhang B M, et al. Airport detection using convolutional neural network and salient feature Bulletin of Surveying and Mapping[J]. 0, 2019(7): 44-49.
余东行, 张宁, 张保明, 等. 结合卷积神经网络与显著性特征的机场检测 测绘通报[J]. 0, 2019(7): 44-49.

【7】Liu Y, Yao J, Feng C. An efficient method for airplane detection in high-resolution remote sensing images [J]. Journal of Geomatics. 2020, 45(1): 95-100.
刘媛, 姚剑, 冯辰. 一种高效的高分辨率遥感影像飞机目标检测方法 [J]. 测绘地理信息. 2020, 45(1): 95-100.

【8】Chen F. Ren R L, van de Voorde T, et al. Fast automatic airport detection in remote sensing images using convolutional neural networks [J]. Remote Sensing. 2018, 10(3): 443.

【9】Zhang P, Niu X, Dou Y, et al. Airport detection on optical satellite images using deep convolutional neural networks [J]. IEEE Geoscience and Remote Sensing Letters. 2017, 14(8): 1183-1187.

【10】Cai B W, Jiang Z G, Zhang H P, et al. Airport detection using end-to-end convolutional neural network with hard example mining [J]. Remote Sensing. 2017, 9(11): 1198.

【11】Zhu M M, Xu Y L, Ma S P, et al. Airport detection method with improved region-based convolutional neural network [J]. Acta Optica Sinica. 2018, 38(7): 0728001.
朱明明, 许悦雷, 马时平, 等. 改进区域卷积神经网络的机场检测方法 [J]. 光学学报. 2018, 38(7): 0728001.

【12】Zhang Z X, Yang C L, Zhu R F, et al. An algorithm for recognition of airport in remote sensing image based on DCNN model [J]. Electronics Optics & Control. 2018, 25(6): 83-89.
张作省, 杨程亮, 朱瑞飞, 等. 联合深度卷积神经网络的遥感影像机场识别算法 [J]. 电光与控制. 2018, 25(6): 83-89.

【13】Kirkpatrick J, Pascanu R, Rabinowitz N, et al. Overcoming catastrophic forgetting in neural networks [J]. Proceedings of the National Academy of Sciences of the United States of America. 2017, 114(13): 3521-3526.

【14】Lee S W, Kim J H, Jun J, et al. arXiv: 1703 . 08475. https: ∥arxiv. 2017, org/abs/1703: 08475.

【15】Feldman D, Fiat A, Sharir M. Coresets and their applications Tel-Aviv: [D]. Tel-Aviv University. 2010, 100-102.

【16】Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector . [C]∥Computer Vision-ECCV 2016. [S. l.]: Springer. 2016, 21-37.

【17】Redmon J. arXiv: 1804 . 02767. https: ∥arxiv. 2018, org/abs/1804: 02767.

【18】Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks . [C]∥Proceedings of the 28 th International Conference on Neural Information Processing Systems. [S. l.: s. n.]. 2015, 91-99.

【19】Wang X L, Ban Y, Guo H M, et al. Deep learning model for target detection in remote sensing images fusing multilevel features[C]∥2019 IEEE International Geoscience and Remote Sensing Symposium. 28 July-2 Aug. 2019, Yokohama, Japan. New York: , 2019, 250-253.

【20】Tian Z, Shen C H, Chen H, et al. FCOS: , 2019, 9626-9635.

引用该论文

Li Zhuqiang,Zhu Ruifei,Ma Jingyu,Meng Xiangyu,Wang Dong,Liu Siyan. Airport Detection Method Combined with Continuous Learning of Residual-Based Network on Remote Sensing Image[J]. Acta Optica Sinica, 2020, 40(16): 1628005

李竺强,朱瑞飞,马经宇,孟祥玉,王栋,刘思言. 联合连续学习的残差网络遥感影像机场目标检测方法[J]. 光学学报, 2020, 40(16): 1628005

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF