Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (12): 3558-3562.DOI: 10.11772/j.issn.1001-9081.2020040579

• Artificial intelligence • Previous Articles     Next Articles

Remote sensing image target detection and identification based on deep learning

SHI Wenxu1,2, BAO Jiahui3, YAO Yu1,2   

  1. 1. Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu Sichuan 610081, China;
    2. University of Chinese Academy of Sciences, Beijing 100049, China;
    3. Glasgow College, University of Electronic Science and Technology of China, Chengdu Sichuan 611731, China
  • Received:2020-05-06 Revised:2020-08-04 Online:2020-12-10 Published:2020-08-21
  • Supported by:
    This work is partially supported by the New Generation of Artificial Intelligence Major Program of Sichuan Province (2018GZDZX0036), the Key Research and Development Project of Sichuan Science and Technology Department (2018SZ0040).

基于深度学习的遥感图像目标检测与识别

史文旭1,2, 鲍佳慧3, 姚宇1,2   

  1. 1. 中国科学院 成都计算机应用研究所, 成都 610081;
    2. 中国科学院大学, 北京 100049;
    3. 电子科技大学 格拉斯哥学院, 成都 611731
  • 通讯作者: 姚宇(1979-),男,四川宜宾人,研究员,博士,主要研究方向:深度学习、医学图像处理。yaoyu@casit.com.cn
  • 作者简介:史文旭(1995-),男,河南焦作人,硕士研究生,主要研究方向:深度学习、智能信息处理;鲍佳慧(1999-),女,四川成都人,主要研究方向:智能信息处理
  • 基金资助:
    四川省新一代人工智能重大专项(2018GZDZX0036);四川省科技厅重点研发项目(2018SZ0040)。

Abstract: In order to improve the precision and speed of existing remote sensing image target detection algorithms in small-scale target detection, a remote sensing image target detection and identification algorithm based on deep learning was proposed. Firstly, a dataset of remote sensing images with different scales was constructed for model training and testing. Secondly, based on the original Single Shot multibox Detector (SSD) network model, the shallow feature fusion module, shallow feature enhancement module and deep feature enhancement module were designed and fused. Finally, the focal loss function was introduced into the training strategy to solve the problem of the imbalance of positive and negative samples in the training process, and the experiment was carried out on the remote sensing image dataset. Experimental results on high-resolution remote sensing image dataset show that the detection mean Average Precision (mAP) of the proposed algorithm achieves 77.95%, which is 3.99 percentage points higher than that of SSD network model, and has the detection speed of 33.8 frame/s. In the extended experiment, the performance of the proposed algorithm is better than that of SSD network model for the detection of fuzzy targets in high-resolution remote sensing images. Experimental results show that the proposed algorithm can effectively improve the precision of remote sensing image target detection.

Key words: deep learning, target detection, remote sensing image, Convolutional Neural Network (CNN), feature fusion

摘要: 为解决目前的遥感图像目标检测算法存在的对小尺度目标检测精度低和检测速度慢等问题,提出了一种基于深度学习的遥感图像目标检测与识别算法。首先,构建一个含有不同尺度大小的遥感图像的数据集用于模型的训练和测试;其次,基于原始的多尺度单发射击(SSD)网络模型,融入了设计的浅层特征融合模块、浅层特征增强模块和深层特征增强模块;最后,在训练策略上引入聚焦分类损失函数,以解决训练过程中正负样本失衡的问题。在高分辨率遥感图像数据集上进行实验,结果表明所提算法的检测平均精度均值(mAP)达到77.95%,相较于SSD网络模型提高了3.99个百分点,同时检测速度为33.8 frame/s。此外,在拓展实验中,改进算法对高分辨率遥感图像中模糊目标的检测效果也优于原多尺度单发射击网络模型。实验结果说明,所提改进算法能够有效地提高遥感图像目标检测的精度。

关键词: 深度学习, 目标检测, 遥感图像, 卷积神经网络, 特征融合

CLC Number: