Unmanned Aerial Vehicle (UAV) image object detection holds broad application prospects in environmental protection, remote sensing, intelligent transportation, and many other fields. However, drone-captured aerial images present challenges such as small targets, low resolution, and limited device power consumption, which pose significant demands on the precision of object detection and the lightweight nature of algorithms. This paper proposes an improved lightweight object detection method tailored for drone-captured aerial images. To better extract the features of small objects, a C2fCF module is introduced into the backbone component, and a C2fMDAF module is introduced into the neck component. Experimental results show that the lightweight object detection method proposed in this paper can significantly improve the accuracy of object detection while almost not affecting the detection efficiency.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Lightweight object detection for UAV Images based on multidimensional attention fusion


    Contributors:
    Wang, Shaohe (author) / Han, Rui (author) / Qian, Ping (author) / Li, Chen (author)


    Publication date :

    2024-11-24


    Size :

    400415 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multiscale Feature Fusion Attention Lightweight Facial Expression Recognition

    Jinyuan Ni / Xinyue Zhang / Jianxun Zhang | DOAJ | 2022

    Free access

    FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection

    Xu, Shaoqing / Zhou, Dingfu / Fang, Jin et al. | IEEE | 2021


    A 3D Object Detection Method Based on Cross-Attention Multimodal Feature Fusion

    Tian, Juanxiu / Zhou, Yanping / Peng, Meng et al. | IEEE | 2024


    Multi-Task Cross-Modality Attention-Fusion for 2D Object Detection

    Sun, Huawei / Feng, Hao / Stettinger, Georg et al. | IEEE | 2023


    Lightweight Traffic Accident Detection Algorithm Based on Attention Mechanism

    Hou, XiaoYan / Wen, ShiHuan / Chen, ShengFu et al. | IEEE | 2024