Rotating object detection in remote-sensing environment

被引:0
|
作者
Sixian Chan
Jingcheng Zheng
Lina Wang
Tingting Wang
Xiaolong Zhou
Yinkun Xu
Kai Fang
机构
[1] Zhejiang University of Technology,College of computer science and technology
[2] Southeast Digital Economic Development Institute,Faculty of Information Technology
[3] Macau University of Science and Technology,College of Electrical and Information Engineering
[4] Quzhou College,undefined
来源
Soft Computing | 2022年 / 26卷
关键词
Deep learning; Object detection; Remote sensing; Arbitrary orientation;
D O I
暂无
中图分类号
学科分类号
摘要
Deep learning models have become the mainstream algorithm for processing computer vision tasks. In the tasks of object detection, the detection box is usually set as a rectangular box aligned with the coordinate axis, so as to achieve the complete packaging of the object. However, when facing some objects with large aspect ratio and angle, the bounding box must be enlarged, which makes the bounding box contain a large amount of useless background information. In this study, a different approach based on YOLOv5 is adopted. By this means, the angle information dimension is added at the head, and angle regression is also added at the same time of the boundary regression. Then the loss of the boundary box is calculated by combining ciou and smoothl1, so that the obtained boundary box is more closely suitable for the actual object. At the same time, the original dataset tags are also pre-processed to calculate the angle information of interest. The purpose of these improvements is to realize object detection with angles in remote-sensing images, especially for objects with large aspect ratios, such as ships, airplanes, and automobiles. Compared with the traditional and other state-of-the-art arbitrarily oriented object detection model based on deep learning, experimental results show that the proposed method has a unique effect in detecting rotating objects.
引用
收藏
页码:8037 / 8045
页数:8
相关论文
共 50 条
  • [21] Optimized Point Set Representation for Oriented Object Detection in Remote-Sensing Images
    Song, Junjie
    Miao, Lingjuan
    Zhou, Zhiqiang
    Ming, Qi
    Dong, Yunpeng
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2023, 20
  • [22] Boundary-Aware Salient Object Detection in Optical Remote-Sensing Images
    Yu, Longxuan
    Zhou, Xiaofei
    Wang, Lingbo
    Zhang, Jiyong
    ELECTRONICS, 2022, 11 (24)
  • [23] A Pyramid Attention Network With Edge Information Injection for Remote-Sensing Object Detection
    Zhang, Junjie
    Ding, Anqi
    Li, Guanyi
    Zhang, Liangang
    Zeng, Dan
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2023, 20
  • [24] Detection of Fake Remote-Sensing Data
    M. V. Gashnikov
    A. V. Kuznetsov
    Optical Memory and Neural Networks, 2022, 31 : 16 - 21
  • [25] Detection of Fake Remote-Sensing Data
    Gashnikov, M., V
    Kuznetsov, A., V
    OPTICAL MEMORY AND NEURAL NETWORKS, 2022, 31 (01) : 16 - 21
  • [26] REMOTE-SENSING DETECTION OF HYDROCARBONS IN THE SEA
    WADSWORTH, A
    ANALUSIS, 1992, 20 (06) : M67 - M69
  • [27] ESTIMATION OF THE EARTH ENVIRONMENT BY REMOTE-SENSING TECHNOLOGY
    OKAYAMA, H
    JAPANESE JOURNAL OF TOXICOLOGY AND ENVIRONMENTAL HEALTH, 1995, 41 (01): : 24 - 34
  • [28] REMOTE-SENSING OF ENVIRONMENT - ACHIEVEMENTS AND PROGNOSIS FOR FUTURE
    HUH, OK
    NOBLE, VE
    NAVAL RESEARCH REVIEWS, 1977, 30 (07): : 1 - 18
  • [29] REMOTE-SENSING OF TERRESTRIAL ENVIRONMENT - PEEL,RF
    CLAYTON, KM
    GEOGRAPHY, 1978, 63 (279) : 148 - 148
  • [30] INTRODUCTION TO REMOTE-SENSING OF THE ENVIRONMENT - RICHASON,BF
    THROWER, NJW
    PROFESSIONAL GEOGRAPHER, 1979, 31 (03): : 328 - 329