We present a novel vehicle detection and tracking system that works solely on 3D LiDAR information. Our approach segments vehicles using a dual-view representation of the 3D LiDAR point cloud on two independently trained convolutional neural networks, one for each view. A bounding box growing algorithm is applied to the fused output of the networks to properly enclose the segmented vehicles. Bounding boxes are grown using a probabilistic method that takes into account also occluded areas. The final vehicle bounding boxes act as observations for a multi-hypothesis tracking system which allows to estimate the position and velocity of the observed vehicles. We thoroughly evaluate our system on the KITTI benchmarks both for detection and tracking separately and show that our dual-branch classifier consistently outperforms previous single-branch approaches, improving or directly competing to other state of the art LiDAR-based methods.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Dual-Branch CNNs for Vehicle Detection and Tracking on LiDAR Data




    Publication date :

    2021-11-01


    Size :

    10198351 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Pruning CNNs for LiDAR-based Perception in Resource Constrained Environments

    Vemparala, Manoj Rohit / Singh, Anmol / Mzid, Ahmed et al. | IEEE | 2021


    IMAGE-BASED VEHICLE TRACKING FROM ROADSIDE LIDAR DATA

    J. Zhang / W. Xiao / B. Coifman et al. | DOAJ | 2019

    Free access

    LiDAR Based Real Time Multiple Vehicle Detection and Tracking

    Zhongzhen Luo / Saeid Habibi / Martin v. Mohrenschildt | BASE | 2016

    Free access

    LiDAR-Based Vehicle Detection and Tracking for Autonomous Racing

    Cellina, Marcello / Corno, Matteo / Savaresi, Sergio Matteo | ArXiv | 2025

    Free access

    Dual Viewpoint Passenger State Classification Using 3D CNNs

    Tu, Ian / Bhalerao, Abhir / Griffiths, Nathan et al. | IEEE | 2018