Snow is one of the toughest adverse weather conditions for object detection (OD). Currently, not only there is a lack of snowy OD datasets to train cutting-edge detectors, but also these detectors have difficulties of learning latent information beneficial for detection in snow. To alleviate the two above problems, we first establish a real-world snowy OD dataset, named RSOD. Besides, we develop an unsupervised training strategy with a distinctive activation function, called $Peak Act$ , to quantitatively evaluate the effect of snow on each object. Peak Act helps grade the images in RSOD into four-difficulty levels. To our knowledge, RSOD is the first quantitatively evaluated and graded real-world snowy OD dataset. Then, we propose a novel Cross Fusion (CF) block to construct a lightweight OD network based on YOLOv5s (called CF-YOLO). CF is a plug-and-play feature aggregation module, which integrates the advantages of Feature Pyramid Network and Path Aggregation Network in a simpler yet more flexible form. Both RSOD and CF lead our CF-YOLO to possess an optimization ability for OD in real-world snow. That is, CF-YOLO can handle unfavorable detection problems of vagueness, distortion and covering of snow. Experiments show that our CF-YOLO achieves better detection results on RSOD, compared to SOTAs. The code and dataset are available at https://github.com/qqding77/CF-YOLO-and-RSOD.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather With a High-Quality Real Snow Dataset


    Beteiligte:
    Ding, Qiqi (Autor:in) / Li, Peng (Autor:in) / Yan, Xuefeng (Autor:in) / Shi, Ding (Autor:in) / Liang, Luming (Autor:in) / Wang, Weiming (Autor:in) / Xie, Haoran (Autor:in) / Li, Jonathan (Autor:in) / Wei, Mingqiang (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2023-10-01


    Format / Umfang :

    4268738 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Real Time Object Detection using YOLO Algorithm

    Haritha, I.V.Sai Lakshmi / Harshini, M. / Patil, Shruti et al. | IEEE | 2022


    Tiny-YOLO object detection supplemented with geometrical data

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


    Mob-YOLO: A Lightweight UAV Object Detection Method

    Liu, Yilin / Liu, Datong / Wang, Benkuan et al. | IEEE | 2022



    Improved YOLO-based algorithm for urban traffic object detection

    Zhang, Liguo / Yan, Xu / Jin, Mei | SPIE | 2024