Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Check

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kuan, Sheng-Yao, Cheng, Jen-Hao, Huang, Hsiang-Wei, Chai, Wenhao, Yang, Cheng-Yen, Latapie, Hugo, Liu, Gaowen, Wu, Bing-Fei, Hwang, Jenq-Neng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910535022280704
author Kuan, Sheng-Yao
Cheng, Jen-Hao
Huang, Hsiang-Wei
Chai, Wenhao
Yang, Cheng-Yen
Latapie, Hugo
Liu, Gaowen
Wu, Bing-Fei
Hwang, Jenq-Neng
author_facet Kuan, Sheng-Yao
Cheng, Jen-Hao
Huang, Hsiang-Wei
Chai, Wenhao
Yang, Cheng-Yen
Latapie, Hugo
Liu, Gaowen
Wu, Bing-Fei
Hwang, Jenq-Neng
contents In the domain of autonomous driving, the integration of multi-modal perception techniques based on data from diverse sensors has demonstrated substantial progress. Effectively surpassing the capabilities of state-of-the-art single-modality detectors through sensor fusion remains an active challenge. This work leverages the respective advantages of cameras in perspective view and radars in Bird's Eye View (BEV) to greatly enhance overall detection and tracking performance. Our approach, Camera-Radar Associated Fusion Tracking Booster (CRAFTBooster), represents a pioneering effort to enhance radar-camera fusion in the tracking stage, contributing to improved 3D MOT accuracy. The superior experimental results on the K-Radaar dataset, which exhibit 5-6% on IDF1 tracking performance gain, validate the potential of effective sensor fusion in advancing autonomous driving.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13937
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Check
Kuan, Sheng-Yao
Cheng, Jen-Hao
Huang, Hsiang-Wei
Chai, Wenhao
Yang, Cheng-Yen
Latapie, Hugo
Liu, Gaowen
Wu, Bing-Fei
Hwang, Jenq-Neng
Computer Vision and Pattern Recognition
In the domain of autonomous driving, the integration of multi-modal perception techniques based on data from diverse sensors has demonstrated substantial progress. Effectively surpassing the capabilities of state-of-the-art single-modality detectors through sensor fusion remains an active challenge. This work leverages the respective advantages of cameras in perspective view and radars in Bird's Eye View (BEV) to greatly enhance overall detection and tracking performance. Our approach, Camera-Radar Associated Fusion Tracking Booster (CRAFTBooster), represents a pioneering effort to enhance radar-camera fusion in the tracking stage, contributing to improved 3D MOT accuracy. The superior experimental results on the K-Radaar dataset, which exhibit 5-6% on IDF1 tracking performance gain, validate the potential of effective sensor fusion in advancing autonomous driving.
title Boosting Online 3D Multi-Object Tracking through Camera-Radar Cross Check
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.13937