Accurate detection of objects from LiDAR point clouds is crucial for autonomous driving and environment modeling. However, uncertainties in ground truth labels due to occlusions, sparsity, and truncation can hinder model training and performance. This paper introduces two strategies to address these issues: 1) Soft Regression Loss (SoRL) and 2) Discrete Quantization Sampling (DQS). SoRL utilizes Gaussian distributions for object predictions, measuring uncertainty based on the probability of ground truth labels within these distributions. This method effectively accounts for deviations in object location and orientation. Meanwhile, DQS introduces uncertainty scores for dynamic sample selection, aiming to refine the quality of positive samples for regression. Based on the proposed modules, we design a lightweight multi-stage object detection framework. Notably, these modules can enhance existing 3D object detection methods without affecting significantly inference speeds. Experiments over benchmark datasets show the effectiveness of our method, especially for cars in sparse point clouds.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Exploiting Label Uncertainty for Enhanced 3D Object Detection From Point Clouds


    Beteiligte:
    Sun, Yang (Autor:in) / Lu, Bin (Autor:in) / Liu, Yonghuai (Autor:in) / Yang, Zhenyu (Autor:in) / Behera, Ardhendu (Autor:in) / Song, Ran (Autor:in) / Yuan, Hejin (Autor:in) / Jiang, Haiyan (Autor:in)


    Erscheinungsdatum :

    01.06.2024


    Format / Umfang :

    4691053 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    TOP-DOWN OBJECT DETECTION FROM LIDAR POINT CLOUDS

    SMOLYANSKIY NIKOLAI / OLDJA RYAN / CHEN KE et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    TOP-DOWN OBJECT DETECTION FROM LIDAR POINT CLOUDS

    SMOLYANSKIY NIKOLAI / OLDJA RYAN / CHEN KE et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Top-down object detection from LiDAR point clouds

    SMOLYANSKIY NIKOLAI / OLDJA RYAN / CHEN KE et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    RadarPillars: Efficient Object Detection from 4D Radar Point Clouds

    Musiat, Alexander / Reichardt, Laurenz / Schulze, Michael et al. | IEEE | 2024


    Transformers for Object Detection in Large Point Clouds

    Ruppel, Felicia / Faion, Florian / Glaser, Claudius et al. | IEEE | 2022