R. Sadli, M. Afkir, A. Hadid, A. Rivenq and A. Taleb-Ahmed, "Aggregated Euclidean Distances for a Fast and Robust Real-Time 3D-MOT," in IEEE Sensors Journal, vol. 21, no. 19, pp. 21872-21884, 1 Oct.1, 2021, doi: 10.1109/JSEN.2021.3104390
Aggregated Euclidean Distances for a fast and robust real-time 3D-MOT
|Author:||Sadli, Rahmad1; Afkir, Mohamed2; Hadid, Abdenour3,1;|
1Polytechnic University of Hauts-de-France, 59313 Valenciennes, France
2Transalley Technopôle, 59300 Famars, France
3University of Oulu, 90570 Oulu, Finland
|Online Access:||PDF Full Text (PDF, 6.6 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe202301051597
Institute of Electrical and Electronics Engineers,
|Publish Date:|| 2023-01-05
Autonomous driving systems must have the ability to monitor the kinematic behaviour of multiple obstacles. Therefore, 3D multi-object tracking (3D-MOT) is one of the crucial modules in autonomous driving to detect the presence of potential hazard movements such as human operated vehicles and pedestrians. In this work, we present a novel online 3D multi-tracking system that uses the Aggregated Euclidean Distances (AED) in data association module instead of using Intersection over Union (IoU) as a new metric. AED is used in order to obtain the relationship between predicted tracks and current object detections. There are several benefits from using AED in data association module. Firstly, it can reduce the system’s complexity so that the execution time can be significantly reduced (as calculating Euclidean distances is much faster than obtaining 3D-IoU). Secondly, AED can provide distance measurement even when there is no overlaps between the predicted tracks and the current detections, while 3D-IoU produces zeros for non-overlapping cases. To demonstrate the validity of our proposed method, we performed extensive experiments on KITTI multi-tracking benchmark and nuScenes validation datasets. The experimental results are compared against the open-sourced state of the art 3D MOTs such as AB3DMOT, FANTrack, and mmMOT. Our method clearly outperforms the AB3DMOT baseline method and other methods in terms of accuracy and/or processing speed.
IEEE sensors journal
|Pages:||21872 - 21884|
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
113 Computer and information sciences
This work was supported in part by the European project InDiD: Infrastructure Digitale de Demain and in part by la chaire d’excellence RIVA de la région Hauts de France.
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.