Group regression is commonly used in 3D object detection to predict box parameters of similar classes in a joint head, aiming to benefit from similarities while separating highly dissimilar classes. For query-based perception methods, this has, so far, not been feasible. We close this gap and present a method to incorporate multi-class group regression, especially designed for the 3D domain in the context of autonomous driving, into existing attention and query-based perception approaches. We enhance a transformer based joint object detection and tracking model with this approach, and thoroughly evaluate its behavior and performance. For group regression, the classes of the nuScenes dataset are divided into six groups of similar shape and prevalence, each being regressed by a dedicated head. We show that the proposed method is applicable to many existing transformer based perception approaches and can bring potential benefits. The behavior of query group regression is thoroughly analyzed in comparison to a unified regression head, e.g. in terms of class-switching behavior and distribution of the output parameters. The proposed method offers many possibilities for further research, such as in the direction of deep multi-hypotheses tracking.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Group Regression for Query Based Object Detection and Tracking


    Beteiligte:
    Ruppel, Felicia (Autor:in) / Faion, Florian (Autor:in) / Glaser, Claudius (Autor:in) / Dietmayer, Klaus (Autor:in)


    Erscheinungsdatum :

    24.09.2023


    Format / Umfang :

    1407844 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    AnchorPoint: Query Design for Transformer-Based 3D Object Detection and Tracking

    Liu, Hao / Ma, Yanni / Wang, Hanyun et al. | IEEE | 2023


    Tracking of object with SVM regression

    Weiyu Zhu, / Song Wang, / Ruei-Sung Lin, et al. | IEEE | 2001


    Tracking of Object with SVM Regression

    Zhu, W. / Wang, S. / Lin, R.-S. et al. | British Library Conference Proceedings | 2001


    PMBM-Based Unresolved-Group Object Tracking

    Li, Guchong / Li, Gang / He, You | IEEE | 2024


    Bus tracking query system

    MAO MAOJUN | Europäisches Patentamt | 2015

    Freier Zugriff