SDVTracker: Real-Time Multi-Sensor Association and Tracking for Self-Driving Vehicles

被引:7
|
作者
Gautam, Shivam [1 ]
Meyer, Gregory P. [2 ]
Vallespi-Gonzalez, Carlos [1 ]
Becker, Brian C. [1 ]
机构
[1] Aurora Innovat Inc, Pittsburgh, PA 15222 USA
[2] Motional, Boston, MA USA
来源
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021) | 2021年
关键词
D O I
10.1109/ICCVW54120.2021.00336
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Accurate motion state estimation of Vulnerable Road Users (VRUs), is a critical requirement for autonomous vehicles that navigate in urban environments. Due to their computational efficiency, many traditional autonomy systems perform multi-object tracking using Kalman Filters which frequently rely on hand-engineered association. However, such methods fail to generalize to crowded scenes and multi-sensor modalities, often resulting in poor state estimates which cascade to inaccurate predictions. We present a practical and lightweight tracking system, SDV-Tracker, that uses a deep learned model for association and state estimation in conjunction with an Interacting Multiple Model (IMM) filter. The proposed tracking method is fast, robust and generalizes across multiple sensor modalities and different VRU classes. In this paper, we detail a model that jointly optimizes both association and state estimation with a novel loss, an algorithm for determining ground-truth supervision, and a training procedure. We show this system significantly outperforms hand-engineered methods on a real-world urban driving dataset while running in less than 2.5 ms on CPU for a scene with 100 actors, making it suitable for self-driving applications where low latency and high accuracy is critical.
引用
收藏
页码:3012 / 3021
页数:10
相关论文
共 50 条
  • [41] MUSE: A Real-Time Multi-Sensor State Estimator for Quadruped Robots
    Nistico, Ylenia
    Soares, Joao Carlos Virgolino
    Amatucci, Lorenzo
    Fink, Geoff
    Semini, Claudio
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2025, 10 (05): : 4620 - 4627
  • [42] Research on real-time gait phase measuring based on multi-sensor
    Zhang, Jin-Yu
    Wang, Lan
    Zhang, Li-Xun
    Harbin Gongcheng Daxue Xuebao/Journal of Harbin Engineering University, 2007, 28 (02): : 218 - 221
  • [43] A MULTI-SENSOR APPROACH FOR REAL-TIME DETECTION AND CLASSIFICATION OF IMPACT SOUNDS
    Stefanakis, Nikolaos
    Mouchtaris, Athanasios
    2015 23RD EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2015, : 2038 - 2042
  • [44] Design of a Multi-Sensor Framework for the Real-time Monitoring of Social Interactions
    Davila-Montero, Sylmarie
    Parsnejad, Sina
    Ashoori, Ehsan
    Goderis, Derek
    Mason, Andrew J.
    2022 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS 22), 2022, : 615 - 619
  • [45] Real-Time Road Lane Detection for Self-driving Cars Using Computer Vision
    Gupta, Meenu (Meenu.e9406@cumail.in), 1600, Springer Science and Business Media Deutschland GmbH (831):
  • [46] Improved Tracking of Articulated Vehicles in Self-Driving Applications Using Phantom Observations
    Xu, Cuichun
    Kingston, Peter
    Djuric, Nemanja
    2023 IEEE 26TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, ITSC, 2023, : 3699 - 3705
  • [47] A Model of a Multi-sensor System for Detection and Tracking of Vehicles and Drones
    Garvanov, Ivan
    Garvanova, Magdalena
    Borissova, Daniela
    Garvanova, Gabriela
    BUSINESS MODELING AND SOFTWARE DESIGN, BMSD 2023, 2023, 483 : 299 - 307
  • [48] A multi-sensor acquisition architecture and real-time reference for sensor and fusion methods benchmarking
    Kais, Mikael
    Millescamps, Damien
    Betaille, David
    Lusetti, Benoit
    Chapelon, Antoine
    2006 IEEE INTELLIGENT VEHICLES SYMPOSIUM, 2006, : 418 - 418
  • [49] Real-Time Hand Gesture Tracking for Human-Computer Interface Based on Multi-Sensor Data Fusion
    Li, Jie
    Liu, Xiaofeng
    Wang, Zhelong
    Zhang, Tingting
    Qiu, Sen
    Zhao, Hongyu
    Zhou, Xu
    Cai, Huili
    Ni, Rongrong
    Cangelosi, Angelo
    IEEE SENSORS JOURNAL, 2021, 21 (23) : 26642 - 26654
  • [50] Multi-sensor tracking and lane estimation in highly automated vehicles
    Thomaidis, George
    Kotsiourou, Christina
    Grubb, Grant
    Lytrivis, Panagiotis
    Karaseitanidis, Giannis
    Amditis, Angelos
    IET INTELLIGENT TRANSPORT SYSTEMS, 2013, 7 (01) : 160 - 169