YOLO-Faster: An efficient remote sensing object detection method based on AMFFN

被引:0
|
作者
Tong, Yicheng [1 ]
Yue, Guan [1 ]
Fan, Longfei [1 ]
Lyu, Guosen [1 ]
Zhu, Deya [1 ]
Liu, Yan [1 ]
Meng, Boyuan [2 ]
Liu, Shu [1 ]
Mu, Xiaokai [3 ,4 ]
Tian, Congling [1 ]
机构
[1] Hangzhou Zhiyuan Res Inst Co Ltd, R&D Dept 4, Hangzhou, Peoples R China
[2] Zhejiang Univ, Polytech Inst, Hangzhou, Peoples R China
[3] Harbin Engn Univ, Qingdao Innovat & Dev Ctr, Qingdao, Peoples R China
[4] Harbin Engn Univ, Natl Key Lab Autonomous Marine Vehicle Technol, Harbin, Peoples R China
基金
中国国家自然科学基金;
关键词
Remote sensing object detection; deep learning; lightweight network; YOLO; IMAGES;
D O I
10.1177/00368504241280765
中图分类号
G40 [教育学];
学科分类号
040101 ; 120403 ;
摘要
As a pivotal task within computer vision, object detection finds application across a diverse spectrum of industrial scenarios. The advent of deep learning technologies has significantly elevated the accuracy of object detectors designed for general-purpose applications. Nevertheless, in contrast to conventional terrestrial environments, remote sensing object detection scenarios pose formidable challenges, including intricate and diverse backgrounds, fluctuating object scales, and pronounced interference from background noise, rendering remote sensing object detection an enduringly demanding task. In addition, despite the superior detection performance of deep learning-based object detection networks compared to traditional counterparts, their substantial parameter and computational demands curtail their feasibility for deployment on mobile devices equipped with low-power processors. In response to the aforementioned challenges, this paper introduces an enhanced lightweight remote sensing object detection network, denoted as YOLO-Faster, built upon the foundation of YOLOv5. Firstly, the lightweight design and inference speed of the object detection network is augmented by incorporating the lightweight network as the foundational network within YOLOv5, satisfying the demand for real-time detection on mobile devices. Moreover, to tackle the issue of detecting objects of different scales in large and complex backgrounds, an adaptive multiscale feature fusion network is introduced, which dynamically adjusts the large receptive field to capture dependencies among objects of different scales, enabling better modeling of object detection scenarios in remote sensing scenes. At last, the robustness of the object detection network under background noise is enhanced through incorporating a decoupled detection head that separates the classification and regression processes of the detection network. The results obtained from the public remote sensing object detection dataset DOTA show that the proposed method has a mean average precision of 71.4% and a detection speed of 38 frames per second.
引用
收藏
页数:22
相关论文
共 50 条
  • [41] SCNet: A Lightweight and Efficient Object Detection Network for Remote Sensing
    Zhu, Shiliang
    Miao, Min
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2024, 21 : 1 - 5
  • [42] A Refined and Efficient CNN Algorithm for Remote Sensing Object Detection
    Liu, Bingqi
    Mo, Peijun
    Wang, Shengzhe
    Cui, Yuyong
    Wu, Zhongjian
    SENSORS, 2024, 24 (22)
  • [43] The geographic object-based method for change detection with remote sensing imagery
    Dian, Yuanyong, 1600, Editorial Board of Medical Journal of Wuhan University (39):
  • [44] A Method of Object Detection for Remote Sensing Imagery Based on Spectral Space Transformation
    Wu Gui-ping
    Xiao Peng-feng
    Feng Xue-zhi
    Wang Ke
    SPECTROSCOPY AND SPECTRAL ANALYSIS, 2013, 33 (03) : 741 - 745
  • [45] A Typical Remote Sensing object detection Method Based on YOLOv3
    Han, Y. C.
    Wang, J.
    Lu, L.
    2019 4TH INTERNATIONAL CONFERENCE ON MECHANICAL, CONTROL AND COMPUTER ENGINEERING (ICMCCE 2019), 2019, : 520 - 523
  • [46] CAW-YOLO: Cross-Layer Fusion and Weighted Receptive Field-Based YOLO for Small Object Detection in Remote Sensing
    Shi, Weiya
    Zhang, Shaowen
    Zhang, Shiqiang
    CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES, 2024, 139 (03): : 3209 - 3231
  • [47] Remote sensing image ship detection based on modified YOLO algorithm
    Wang X.
    Jiang H.
    Lin K.
    Jiang, Hongxu (jianghx@buaa.edu.cn), 1600, Beijing University of Aeronautics and Astronautics (BUAA) (46): : 1184 - 1191
  • [48] A optimized YOLO method for object detection
    Liang Tianjiao
    Bao Hong
    2020 16TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS 2020), 2020, : 30 - 34
  • [49] Object Detection Based on Efficient Multiscale Auto-Inference in Remote Sensing Images
    Zhang, Shaojing
    Mu, Xiaodong
    Kou, Guangjie
    Zhao, Jingyu
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2021, 18 (09) : 1650 - 1654
  • [50] Object Detection Method Based on Improved YOLO Lightweight Network
    Li Chengyue
    Yao Jianmin
    Lin Zhixian
    Yan Qun
    Fan Baoqing
    LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (14)