Robust 3D Detection in Traffic Scenario with Tracking-Based Coupling System - Artificial Intelligence Applications and Innovations Access content directly
Conference Papers Year : 2020

Robust 3D Detection in Traffic Scenario with Tracking-Based Coupling System

Zhuoli Zhou
  • Function : Author
  • PersonId : 1242568
Shitao Chen
  • Function : Author
  • PersonId : 1033456
Rongyao Huang
  • Function : Author
  • PersonId : 1242569
Nanning Zheng
  • Function : Author
  • PersonId : 1033459

Abstract

Autonomous driving is conducted in complex scenarios, which requires to detect 3D objects in real time scenarios as well as accurately track these 3D objects in order to get such information as location, size, trajectory, velocity. MOT (Multi-Object Tracking) performance is heavily dependent on object detection. Once object detection gives false alarms or missing alarms, the multi-object tracking would be automatically influenced. In this paper, we propose a coupling system which combines 3D object detection and multi-object tracking into one framework. We use the tracked objects as a reference in 3D object detection, in order to locate objects, reduce false or missing alarms in a single frame, and weaken the impact of false and missing alarms on the tracking quality. Our method is evaluated on kitti dataset and is proved effective.
Fichier principal
Vignette du fichier
497040_1_En_28_Chapter.pdf (3.13 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04050586 , version 1 (29-03-2023)

Licence

Attribution

Identifiers

Cite

Zhuoli Zhou, Shitao Chen, Rongyao Huang, Nanning Zheng. Robust 3D Detection in Traffic Scenario with Tracking-Based Coupling System. 16th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2020, Neos Marmaras, Greece. pp.330-339, ⟨10.1007/978-3-030-49161-1_28⟩. ⟨hal-04050586⟩
11 View
3 Download

Altmetric

Share

Gmail Facebook X LinkedIn More