Towards Safer Highway Work Zones: Insights from Deep Learning Analysis of Thermal Footage

被引:0
|
作者
Bhuyan, Zubin [1 ]
Xie, Yuanchang [2 ]
Liu, Ruifeng [1 ]
Cao, Yu [1 ]
Liu, Benyuan [1 ]
机构
[1] Univ Massachusetts Lowell, Miner Sch Comp & Informat Sci, 1 Univ Ave, Lowell, MA 01854 USA
[2] Univ Massachusetts Lowell, Dept Civil Environm Engn, 1 Univ Ave, Lowell, MA 01854 USA
来源
IFAC PAPERSONLINE | 2024年 / 58卷 / 10期
关键词
Highway work zone; merge control; thermal video; vehicle tracking; safety;
D O I
10.1016/j.ifacol.2024.07.338
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Thermal imaging, when coupled with deep-learning-based analysis, can significantly improve highway work zone management and safety, though data scarcity in this field has been a historical challenge. We collected over 440 hours of thermal footage from highway sites in Massachusetts and New Hampshire and created a vehicle segmentation dataset featuring over 14,000 vehicle instances. We implement effective training strategies for deep learning models and develop algorithms to analyze vehicle trajectories and merging behaviors. Various visualization techniques are illustrated to better understand the extensive analytics data generated for each site, which can lead to development of data-driven strategies to improve traffic management and safety. GitHub repository: https://github.com/z00bean/SmartWorkZoneControl. Copyright (c) 2024 The Authors.
引用
收藏
页码:188 / 193
页数:6
相关论文
共 50 条
  • [41] Towards a Semantic Video Analysis using Deep Learning and Ontology
    Bornia, Jemai
    Mahmoudi, Sidi Ahmed
    Frihida, Ali
    Manneback, Pierre
    2018 4TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING TECHNOLOGIES AND APPLICATIONS (CLOUDTECH), 2018,
  • [42] Deep Learning and Video Quality Analysis: Towards A Unified VQA
    Topiwala, P.
    Dai, W.
    Pian, J.
    APPLICATIONS OF DIGITAL IMAGE PROCESSING XLIII, 2020, 11510
  • [43] Deep Learning in Skin Lesion Analysis Towards Cancer Detection
    Waweru, Anthony Kioria
    Ahmed, Khandakar
    Miao, Yuan
    Kawan, Payam
    2020 24TH INTERNATIONAL CONFERENCE INFORMATION VISUALISATION (IV 2020), 2020, : 740 - 745
  • [44] Sentiment Analysis towards Actionable Intelligence via Deep Learning
    Eletter, Shorouq Fathi
    TEM JOURNAL-TECHNOLOGY EDUCATION MANAGEMENT INFORMATICS, 2020, 9 (04): : 1663 - 1668
  • [45] INTEGRATING DOMAIN KNOWLEDGE WITH DEEP LEARNING MODEL FOR AUTOMATED WORKER ACTIVITY CLASSIFICATION IN MOBILE WORK ZONES
    Tian, Chi
    Chen, Yunfeng
    Zhang, Jiansong
    Feng, Yiheng
    JOURNAL OF INFORMATION TECHNOLOGY IN CONSTRUCTION, 2024, 29 : 264 - 280
  • [46] Detecting Work Zones in SHRP 2 NDS Videos Using Deep Learning Based Computer Vision
    Abodo, Franklin
    Rittmuller, Robert
    Sumner, Brian
    Berthaume, Andrew
    2018 17TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2018, : 679 - 686
  • [47] Naturalistic Scene Modelling: Deep Learning with Insights from Biology
    Kofi Appiah
    Zhiyong Jin
    Lei Shi
    Sze Chai Kwok
    Journal of Signal Processing Systems, 2023, 95 : 1153 - 1165
  • [48] Naturalistic Scene Modelling: Deep Learning with Insights from Biology
    Appiah, Kofi
    Jin, Zhiyong
    Shi, Lei
    Kwok, Sze Chai
    JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2023, 95 (10): : 1153 - 1165
  • [49] Deep insights into MCI diagnosis: A comparative deep learning analysis of EEG time series
    Seker, Mesut
    Ozerdem, Mehmet Sirac
    JOURNAL OF NEUROSCIENCE METHODS, 2024, 403
  • [50] A Method for approximated Deep Learning Towards dynamic sharing from big-data analysis
    Mylavarapu, Raghu T.
    2018 IEEE INTERNATIONAL CONFERENCE ON RESEARCH IN INTELLIGENT AND COMPUTING IN ENGINEERING (RICE III), 2018,