Street scene change detection continues to capture researchers' interests in the computer vision community. It aims to identify the changed regions of the paired street-view images captured at different times. The state-of-the-art network based on the encoder-decoder architecture leverages the feature maps at the corresponding level between two channels to gain sufficient information of changes. Still, the efficiency of feature extraction, feature correlation calculation, even the whole network requires further improvement. This paper proposes the temporal attention and explores the impact of the dependency-scope size of temporal attention on the performance of change detection. In addition, based on the Temporal Attention Module (TAM), we introduce a more efficient and light-weight version - Dynamic Receptive Temporal Attention Module (DRTAM) and propose the Concurrent Horizontal and Vertical Attention (CHVA) to improve the accuracy of the network on specific challenging entities. On street scene datasets ‘GSV’, ‘TSUNAMI’ and ‘VL-CMU-CD’, our approach gains excellent performance, establishing new state-of-the-art scores without bells and whistles, while maintaining high efficiency applicable in autonomous vehicles.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    DR-TANet: Dynamic Receptive Temporal Attention Network for Street Scene Change Detection


    Beteiligte:
    Chen, Shuo (Autor:in) / Yang, Kailun (Autor:in) / Stiefelhagen, Rainer (Autor:in)


    Erscheinungsdatum :

    11.07.2021


    Format / Umfang :

    4009154 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    ChangeSAM: Adapting the Segment Anything Model to Street Scene Image Change Detection

    Bauer, Adrian / Krabbe, Jan-Christoph / Kummert, Anton | IEEE | 2024


    Single Network Panoptic Segmentation for Street Scene Understanding

    de Geus, Daan / Meletis, Panagiotis / Dubbelman, Gijs | IEEE | 2019


    Time-Causal and Time-Recursive Spatio-Temporal Receptive Fields

    Lindeberg, T. | British Library Online Contents | 2016


    Dynamic scene understanding using temporal association rules

    Talha, A. M. / Junejo, I. N. | British Library Online Contents | 2014


    Hybrid receptive field network for small object detection on drone view

    CHEN, Zhaodong / JI, Hongbing / ZHANG, Yongquan et al. | Elsevier | 2025

    Freier Zugriff