When we apply neural networks to safety-critical systems such as self-driving cars, the reliability of their predictions must be considered. However, recent deep neural networks have tended to output biased confidence. Additionally, the extent of confidence bias estimated by object detectors varies depending on factors such as the detected object’s position and size. To address this problem, many researchers have proposed methods for calibrating confidences estimated by object detectors. In this study, we investigate the factors that may cause bias in the confidence of LiDAR-based 3D object detectors and show that our calibration method compensates for the effect of these factors to provide reliable confidence estimations, regardless of the neural network model used or the situations in which objects are detected.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Conditional Confidence Calibration Method for 3D Point Cloud Object Detection


    Contributors:


    Publication date :

    2022-06-05


    Size :

    845451 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Confidence Calibration for Object Detection and Segmentation

    Küppers, Fabian / Haselhoff, Anselm / Kronenberger, Jan et al. | Springer Verlag | 2022

    Free access

    MULTICLASS CONFIDENCE AND LOCALIZATION CALIBRATION FOR OBJECT DETECTION

    PATHIRAJA BIMSARA / GUNAWARDHANA MALITHA / KHAN MUHAMMAD HARIS | European Patent Office | 2025

    Free access

    Real-Time Point Cloud Object Detection via Voxel-Point Geometry Abstraction

    Shi, Guangsheng / Wang, Ke / Li, Ruifeng et al. | IEEE | 2023


    Adaptivity of conditional random field based outdoor point cloud classification

    Lang, D. / Friedmann, S. / Paulus, D. | British Library Online Contents | 2016


    OBJECT DETECTION AND DETECTION CONFIDENCE SUITABLE FOR AUTONOMOUS DRIVING

    KOIVISTO TOMMI / JANIS PEKKA / KUOSMANEN TERO et al. | European Patent Office | 2025

    Free access