GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Search: WFRF:(Liu Liping) > GNN-PMB: A Simple b...

Details
MARC

Liu, Jianan (author)

GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles

Article/chapterEnglish2023

Publisher, publication year, extent ...

2023

Numbers

LIBRIS-ID:oai:research.chalmers.se:c7ecafc6-9979-48e8-bc46-bf8ceeb5bfd3
https://doi.org/10.1109/TIV.2022.3217490DOI
https://research.chalmers.se/publication/533163URI

Supplementary language notes

Language:English
Summary in:English

Part of subdatabase

SwePubSwePub

Classification

Subject category:art swepub-publicationtype
Subject category:ref swepub-contenttype

Notes

Multi-object tracking (MOT) is among crucial applications in modern advanced driver assistance systems (ADAS) and autonomous driving (AD) systems. The global nearest neighbor (GNN) filter, as the earliest random vector-based Bayesian tracking framework, has been adopted in most of state-of-the-arts trackers in the automotive industry. The development of random finite set (RFS) theory facilitates a mathematically rigorous treatment of the MOT problem, and different variants of RFS-based Bayesian filters have then been proposed. However, their effectiveness in the real ADAS and AD application is still an open problem. In this paper, it is demonstrated that the latest RFS-based Bayesian tracking framework could be superior to typical random vector-based Bayesian tracking framework via a systematic comparative study of both traditional random vector-based Bayesian filters with rule-based heuristic track maintenance and RFS-based Bayesian filters on the nuScenes validation dataset. An RFS-based tracker, namely Poisson multi-Bernoulli filter using the global nearest neighbor (GNN-PMB), is proposed to LiDAR-based MOT tasks. This GNN-PMB tracker is simple to use, and it achieves competitive results on the nuScenes dataset. Specifically, the proposed GNN-PMB tracker outperforms most state-of-the-art LiDAR-only trackers and LiDAR and camera fusion-based trackers, ranking the $3^{rd}$ among all LiDAR-only trackers on nuScenes 3D tracking challenge leader board 1 1 https://bit.ly/3bQJ2CP at the time of submission. Our code is available at https://github.com/chisyliu/GnnPmbTracker .

Subject headings and genre

NATURVETENSKAP Data- och informationsvetenskap Programvaruteknik hsv//swe
NATURAL SCIENCES Computer and Information Sciences Software Engineering hsv//eng
TEKNIK OCH TEKNOLOGIER Elektroteknik och elektronik Inbäddad systemteknik hsv//swe
ENGINEERING AND TECHNOLOGY Electrical Engineering, Electronic Engineering, Information Engineering Embedded Systems hsv//eng
NATURVETENSKAP Data- och informationsvetenskap Datorseende och robotik hsv//swe
NATURAL SCIENCES Computer and Information Sciences Computer Vision and Robotics hsv//eng
Laser radar
Multi-object tracking
Radar tracking
Bayes methods
Detectors
GNN-PMB
random finite set-based Bayesian filters
Three-dimensional displays
random vector-based Bayesian filters
autonomous driving
Cameras
LiDAR
Feature extraction

Added entries (persons, corporate bodies, meetings, titles ...)

Bai, LipingBeihang University (author)
Xia, Yuxuan,1993Chalmers tekniska högskola,Chalmers University of Technology(Swepub:cth)yuxuanx (author)
Huang, TaoJames Cook University (author)
Zhu, BingBeihang University (author)
Beihang UniversityChalmers tekniska högskola (creator_code:org_t)

Related titles

In:IEEE Transactions on Intelligent Vehicles8:2, s. 1176-11892379-8858

Internet link

Find in a library

IEEE Transactions on Intelligent Vehicles (Search for host publication in LIBRIS)

To the university's database

Find more in SwePub

By the author/editor: Liu, Jianan; Bai, Liping; Xia, Yuxuan, 199 ...; Huang, Tao; Zhu, Bing

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Software Enginee ...

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Electrical Engin ...; and Embedded Systems

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Vision ...

Articles in the publication: IEEE Transaction ...

By the university: Chalmers University of Technology

Search outside SwePub

Extend your search to:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se