Pedestrian detection is a classic problem in computer vision, which has an essential impact on the safety of urban autonomous driving. Although significant improvement has been made in pedestrian detection recently, small‐scale pedestrian detection is still challenging. To effectively tackle this issue, a multi‐scale pedestrian detector based on self‐attention mechanism and adaptive spatial feature fusion is proposed in this paper. In order to better extract global information, the spatial attention mechanism asymmetric pyramid non‐local block (APNB) module is applied. To achieve scale‐invariance detection, multiple detection branches are designed, which include a high‐resolution detection branch and a low‐resolution detection branch. In integrating multi‐scale features, the adaptively spatial feature fusion (ASFF) method is employed, which can solve the problem of feature inconsistency across different scales. Experimental results show that the proposed method obtains competitive performance on Caltech and CityPersons datasets.


    Access

    Download


    Export, share and cite



    Title :

    Multi‐scale pedestrian detection based on self‐attention and adaptively spatial feature fusion


    Contributors:
    Wang, Minjun (author) / Chen, Houjin (author) / Li, Yanfeng (author) / You, Yuhao (author) / Zhu, Jinlei (author)

    Published in:

    Publication date :

    2021-06-01


    Size :

    13 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Multi‐scale pedestrian detection based on self‐attention and adaptively spatial feature fusion

    Minjun Wang / Houjin Chen / Yanfeng Li et al. | DOAJ | 2021

    Free access

    Attention‐based multi‐scale feature fusion for free‐space detection

    Pengfei Song / Hui Fan / Jinjiang Li et al. | DOAJ | 2022

    Free access

    Attention‐based multi‐scale feature fusion for free‐space detection

    Song, Pengfei / Fan, Hui / Li, Jinjiang et al. | Wiley | 2022

    Free access

    Predicting Pedestrian Crossing Intention With Feature Fusion and Spatio-Temporal Attention

    Yang, Dongfang / Zhang, Haolin / Yurtsever, Ekim et al. | IEEE | 2022


    ADAPTIVELY CONTROLLING TRAFFIC MOVEMENTS FOR PEDESTRIAN SAFETY

    MALKES WILLIAM / OVERSTREET WILLIAMS / PRICE JEFFERY et al. | European Patent Office | 2019

    Free access