Detecting objects from aerial images poses significant challenges due to the following factors: 1) Aerial images typically have very large sizes, generally with millions or even hundreds of millions of pixels, while computational resources are limited. 2) Small object size leads to insufficient information for effective detection. 3) Non-uniform object distribution leads to computational resource wastage. To address these issues, we propose YOLC (You Only Look Clusters), an efficient and effective framework that builds on an anchor-free object detector, CenterNet. To overcome the challenges posed by large-scale images and non-uniform object distribution, we introduce a Local Scale Module (LSM) that adaptively searches cluster regions for zooming in for accurate detection. Additionally, we modify the regression loss using Gaussian Wasserstein distance (GWD) to obtain high-quality bounding boxes. Deformable convolution and refinement methods are employed in the detection head to enhance the detection of small objects. We perform extensive experiments on two aerial image datasets, including Visdrone2019 and UAVDT, to demonstrate the effectiveness and superiority of our proposed approach.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images


    Contributors:

    Published in:

    Publication date :

    2024-10-01


    Size :

    5018057 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Lightweight and Efficient Tiny-Object Detection Based on Improved YOLOv8n for UAV Aerial Images

    Min Yue / Liqiang Zhang / Juan Huang et al. | DOAJ | 2024

    Free access

    Automatic aircraft object detection in aerial images

    Li, Yingchun / Chen, Hexin / Mei, Yunhuan et al. | SPIE | 2003


    Tiny-YOLO object detection supplemented with geometrical data

    Khokhlov, Ivan / Davydenko, Egor / Osokin, Ilya et al. | IEEE | 2020


    Toward Efficient Detection and Tracking for Tiny Airborne Object

    Liu, Zhunga / Lyu, Yanyi / Guo, Dongxiu et al. | IEEE | 2025


    A Research of object detection on UAVs aerial images

    Xie, Xiaozhu / Lu, Gang | IEEE | 2021