Multi-scale object detection in natural scenes is still challenging. To enhance the multi-scale perception capability, some algorithms combine the lower-level and higher-level information via multi-scale feature fusion strategies. However, the inherent spatial properties among instances and relations between foreground and background are ignored. In addition, the human-defined “center-based” regression quality evaluation strategy, predicting a high-to-low score based on a linear relationship with the distance to the center of ground-truth box, is not robust to scale-variant objects. In this work, we propose a Depth-Guided Progressive Network (DGPNet) for multi-scale object detection. Specifically, besides the prediction of classification and localization, the depth is estimated and used to guide the image features in a weighted manner to obtain a better spatial representation. Therefore, depth estimation and 2D object detection are simultaneously learned via a unified network, where the depth features are merged as auxiliary information into the detection branch to enhance the discrimination among multi-scale objects. Moreover, to overcome the difficulty of empirically fitting the localization quality function, high-quality predicted boxes on scale-variant objects are more adaptively obtained by an IoU-aware progressive sampling strategy. We divide the sampling process into two stages, i.e., “statistical-aware” and “IoU-aware”. The former selects thresholds for positive samples based on statistical characteristics of multi-scale instances, and the latter further selects high-quality samples by IoU on the basis of the former. Therefore, the final ranking scores better reflect the quality of localization. Experiments verify that our method outperforms state-of-the-art methods on the KINS and Cityscapes dataset.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Depth-Guided Progressive Network for Object Detection


    Beteiligte:
    Ma, Jia-Wei (Autor:in) / Liang, Min (Autor:in) / Chen, Song-Lu (Autor:in) / Chen, Feng (Autor:in) / Tian, Shu (Autor:in) / Qin, Jingyan (Autor:in) / Yin, Xu-Cheng (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.10.2022


    Format / Umfang :

    4416932 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    DG-BEV: Depth-Guided BEV 3D Object Detection with Sparse LiDAR Data

    Chen, Sihan / Wang, Keqiu / Wang, Yadong et al. | IEEE | 2024


    Saliency-guided region proposal network for CNN based object detection

    Fattal, Ann-Katrin / Karg, Michelle / Scharfenberger, Christian et al. | IEEE | 2017


    VISUAL BEHAVIOR GUIDED OBJECT DETECTION

    MALLIK APURBAA / NAGASAMY VIJAY / RAVINDRAN ANIRUDDH | Europäisches Patentamt | 2021

    Freier Zugriff

    Visual behavior guided object detection

    MALLIK APURBAA / NAGASAMY VIJAY / RAVINDRAN ANIRUDDH | Europäisches Patentamt | 2023

    Freier Zugriff

    Object Detection for Autonomous Guided Vehicle

    Bhosale, Tanmay / Attar, Ajim / Warang, Prathamesh et al. | BASE | 2022

    Freier Zugriff