航空学报 > 2024, Vol. 45 Issue (6): 28822-028822   doi: 10.7527/S1000-6893.2023.28822

无人机航拍影像目标检测与语义分割的深度学习方法研究进展

罗旭东, 吴一全(), 陈金林   

  1. 南京航空航天大学 电子信息工程学院,南京 211106
  • 收稿日期:2023-04-06 修回日期:2023-05-04 接受日期:2023-06-01 出版日期:2024-03-25 发布日期:2023-06-09
  • 通讯作者: 吴一全 E-mail:nuaaimage@163.com
  • 基金资助:
    国家自然科学基金(61573183)

Research progress on deep learning methods for object detection and semantic segmentation in UAV aerial images

Xudong LUO, Yiquan WU(), Jinlin CHEN   

  1. College of Electronic and Information Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
  • Received:2023-04-06 Revised:2023-05-04 Accepted:2023-06-01 Online:2024-03-25 Published:2023-06-09
  • Contact: Yiquan WU E-mail:nuaaimage@163.com
  • Supported by:
    National Natural Science Foundation of China(61573183)

摘要:

无人机(UAV)因其小型轻便、操作简单等优点获得了广泛的应用。将深度学习方法与无人机系统相结合,有助于在清晰度高、视野范围广的无人机航拍影像上快速准确地检测出所需目标,相关课题已成为当前的研究热点之一。对近十年来无人机航拍影像目标检测与语义分割的深度学习方法研究进展进行了综述。首先概述了无人机及其航拍影像的特点和广泛的应用场景,简述了无人机航拍影像目标检测与语义分割方法的发展历程。然后对基于深度学习的无人机航拍影像目标检测与语义分割方法按照不同的网络模型进行分类,分别总结了它们的改进策略、应用场景、贡献和局限性。随后收集梳理了近些年无人机航拍影像的数据集,归纳了常用的卷积神经网络模型的评价指标。最后指出了本领域目前存在的相关问题,并对未来的研究趋势进行了展望。

关键词: 无人机航拍影像, 深度学习, 目标检测, 语义分割, 数据集, 性能评价指标

Abstract:

Unmanned Aerial Vehicles (UAV) have been widely used due to their advantages of small size, light weight, and simple operation. The combination of the deep learning method and UAV system can help to quickly and accurately detect the desired target on UAV aerial images with high definition and a wide field of view. Related topics have become one of the current research hotspots. This paper reviews the research progress of deep learning methods for object detection and semantic segmentation in UAV aerial images in the past ten years. First, the characteristics and wide range of application scenarios of UAVs and their aerial images are summarized, and the development process of target detection and semantic segmentation methods for UAV aerial images is briefly described. Then, the object detection and semantic segmentation methods of UAV aerial images based on deep learning are classified according to different network models, and their improvement strategies, application scenarios, contributions, and limitations are summarized. Subsequently, the data sets of aerial images taken by UAVs in recent years are collected and sorted out, and the evaluation indicators of commonly used convolutional neural network models are summarized. Finally, the existing problems in this field are pointed out, and prospects for future research trends are presented.

Key words: Unmanned Aerial Vehicle (UAV), deep learning, object detection, semantic segmentation, data set, performance evaluation indicator

中图分类号: