Pedestrian detection in the wild remains a challenging problem especially for scenes containing serious occlusion. In this paper, we propose a novel feature learning method in the deep learning framework, referred to as Feature Calibration Network (FC-Net), to adaptively detect pedestrians under various occlusions. FC-Net is based on the observation that the visible parts of pedestrians are selective and decisive for detection, and is implemented as a self-paced feature learning framework with a self-activation (SA) module and a feature calibration (FC) module. In a new self-activated manner, FC-Net learns features which highlight the visible parts and suppress the occluded parts of pedestrians. The SA module estimates pedestrian activation maps by reusing classifier weights, without any additional parameter involved, therefore resulting in an extremely parsimony model to reinforce the semantics of features, while the FC module calibrates the convolutional features for adaptive pedestrian representation in both pixel-wise and region-based ways. Experiments on CityPersons and Caltech datasets demonstrate that FC-Net improves detection performance on occluded pedestrians up to 10% while maintaining excellent performance on non-occluded instances.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Feature Calibration Network for Occluded Pedestrian Detection


    Beteiligte:
    Zhang, Tianliang (Autor:in) / Ye, Qixiang (Autor:in) / Zhang, Baochang (Autor:in) / Liu, Jianzhuang (Autor:in) / Zhang, Xiaopeng (Autor:in) / Tian, Qi (Autor:in)


    Erscheinungsdatum :

    01.05.2022


    Format / Umfang :

    3909912 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Mask-Guided Attention Network for Occluded Pedestrian Detection

    Pang, Yanwei / Xie, Jin / Khan, Muhammad Haris et al. | ArXiv | 2019

    Freier Zugriff

    Human-Cascaded network for Robust Detection of Occluded Pedestrian

    Xu, Zhewei / Fu, Xiufeng / Feng, Dacheng et al. | IEEE | 2022



    Collision Avoidance System Simulation for Occluded Pedestrian

    Roșu, Ioana-Alexandra / Buzdugan, Ioana-Diana / Antonya, Csaba | Springer Verlag | 2024