TF-YOLO: A Transformer–Fusion-Based YOLO Detector for Multimodal Pedestrian Detection in Autonomous Driving Scenes

Author:

Chen Yunfan1ORCID,Ye Jinxing1,Wan Xiangkui1

Affiliation:

1. Hubei Key Laboratory for High-Efficiency Utilization of Solar Energy and Operation Control of Energy Storage System, Hubei University of Technology, Wuhan 430068, China

Abstract

Recent research demonstrates that the fusion of multimodal images can improve the performance of pedestrian detectors under low-illumination environments. However, existing multimodal pedestrian detectors cannot adapt to the variability of environmental illumination. When the lighting conditions of the application environment do not match the experimental data illumination conditions, the detection performance is likely to be stuck significantly. To resolve this problem, we propose a novel transformer–fusion-based YOLO detector to detect pedestrians under various illumination environments, such as nighttime, smog, and heavy rain. Specifically, we develop a novel transformer–fusion module embedded in a two-stream backbone network to robustly integrate the latent interactions between multimodal images (visible and infrared images). This enables the multimodal pedestrian detector to adapt to changing illumination conditions. Experimental results on two well-known datasets demonstrate that the proposed approach exhibits superior performance. The proposed TF-YOLO drastically improves the average precision of the state-of-the-art approach by 3.3% and reduces the miss rate of the state-of-the-art approach by about 6% on the challenging multi-scenario multi-modality dataset.

Funder

Natural Science Foundation of Hubei Province, China

Open Foundation of Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System

Publisher

MDPI AG

Subject

Automotive Engineering

Reference30 articles.

1. Balsa-Barreiro, J., Valero-Mora, P.M., Berné-Valero, J.L., and Varela-García, F.-A. (2019). GIS mapping of driving behavior based on naturalistic driving data. ISPRS Int. J. Geo-Inf., 8.

2. Extraction of naturalistic driving patterns with geographic information systems;Mehmood;Mob. Netw. Appl.,2020

3. Deep neural network based vehicle and pedestrian detection for autonomous driving: A survey;Chen;IEEE Trans. Intell. Transp. Syst.,2021

4. Pedestrian Behavior Prediction Using Deep Learning Methods for Urban Scenarios: A Review;Zhang;IEEE Trans. Intell. Transp. Syst.,2023

5. (2021, October 04). Pedestrian Safety: Prevent Pedestrian Crashes, Available online: https://www.nhtsa.gov/road-safety/pedestrian-safety.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3