A Multi-Stream Approach to Mixed-Traffic Accident Recognition Using Deep Learning

被引：0
|
作者：
Fu, Swee Tee [1 ]
Theng, Lau Bee [1 ]
Shiong, Brian Loh Chung [1 ]
Mccarthy, Chris [2 ]
Tsun, Mark Tee Kit [1 ]
机构：
[1] Swinburne University of Technology, Faculty of Engineering, Computing and Science, Sarawak,Sarawak Campus, Kuching,93350, Malaysia
[2] Swinburne University of Technology, School of Science, Computing and Engineering Technologies (SoSCET), Melbourne Campus, Hawthorn,VIC,3122, Australia
来源：
IEEE Access | 2024年 / 12卷
关键词：
Road traffic accidents are a leading cause of injuries and fatalities globally; prompting extensive research into deep learning-based accident recognition models for their superior performance in computer vision tasks. However; most studies focus on non-mixed traffic environments; where detection is simpler due to predictable traffic patterns and uniform vehicle types. In contrast; mixed-traffic scenarios present greater challenges as diverse vehicles; motorcyclists; and pedestrians move unpredictably. Models relying on a single type of perception are effective in structured traffic but struggle to handle the complexities of mixed-traffic environments. This study proposes a novel multi-stream deep learning model called Accident Recognition in Mixed-Traffic Scene (ARMS); which integrates three distinct streams: the first stream analyzes the overall accident scene; the second focuses on mixed-traffic accident features; and the third examines vehicle motion abnormalities through object detection and tracking; aimed at improving road accident recognition accuracy in mixed-traffic environments at intersections. This model is trained and evaluated using datasets from CADP; UA-DETRAC; and supplementary online sources. The results demonstrate that the ARMS model achieves an accuracy of 93.3%; with performance improving significantly through the fusion of the individual streams. Additionally; the ARMS model was evaluated using two publicly available standard datasets; which further highlights its improved performance in recognizing mixed-traffic accidents compared to existing studies. © 2013 IEEE;
D O I：
10.1109/ACCESS.2024.3512794
中图分类号：
学科分类号：
摘要：
引用
下载
收藏
页码：185232 / 185249
相关论文
共 50 条
  • [1] Multimodal Multi-stream Deep Learning for Egocentric Activity Recognition
    Song, Sibo
    Chandrasekhar, Vijay
    Mandal, Bappaditya
    Li, Liyuan
    Lim, Joo-Hwee
    Babu, Giduthuri Sateesh
    San, Phyo Phyo
    Cheung, Ngai-Man
    PROCEEDINGS OF 29TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, (CVPRW 2016), 2016, : 378 - 385
  • [2] A Multi-Stream Feature Fusion Approach for Traffic Prediction
    Li, Zhishuai
    Xiong, Gang
    Tian, Yonglin
    Lv, Yisheng
    Chen, Yuanyuan
    Hui, Pan
    Su, Xiang
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (02) : 1456 - 1466
  • [3] A multi-stream approach to audiovisual automatic speech recognition
    Hasegawa-Johnson, Mark
    2007 IEEE NINTH WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING, 2007, : 328 - 331
  • [4] Multi-stream Deep Networks for Vehicle Make and Model Recognition
    Besbes, Mohamed Dhia Elhak
    Kessentini, Yousri
    Tabia, Hedi
    PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 5: VISAPP, 2020, : 413 - 419
  • [5] A novel multi-stream method for violent interaction detection using deep learning
    Li, Hongchang
    Wang, Jing
    Han, Jianjun
    Zhang, Jinmin
    Yang, Yushan
    Zhao, Yue
    MEASUREMENT & CONTROL, 2020, 53 (5-6): : 796 - 806
  • [6] Multi-stream Architecture with Symmetric Extended Visual Rhythms for Deep Learning Human Action Recognition
    Tacon, Hemerson
    Brito, Andre de Souza
    Chaves, Hugo de Lima
    Vieira, Marcelo Bernardes
    Villela, Saulo Moraes
    Maia, Helena de Almeida
    Concha, Darwin Ttito
    Pedrini, Helio
    PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 5: VISAPP, 2020, : 351 - 358
  • [7] A Multi-Stream Sequence Learning Framework for Human Interaction Recognition
    Haroon, Umair
    Ullah, Amin
    Hussain, Tanveer
    Ullah, Waseem
    Sajjad, Muhammad
    Muhammad, Khan
    Lee, Mi Young
    Baik, Sung Wook
    IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS, 2022, 52 (03) : 435 - 444
  • [8] Multi-scale multi-stream deep network for car logo recognition
    Snehal Surwase
    Meenakshi Pawar
    Evolutionary Intelligence, 2023, 16 : 485 - 492
  • [9] Multi-scale multi-stream deep network for car logo recognition
    Surwase, Snehal
    Pawar, Meenakshi
    EVOLUTIONARY INTELLIGENCE, 2023, 16 (02) : 485 - 492
  • [10] Multi-stream Deep Learning Framework for Automated Presentation Assessment
    Li, Junnan
    Wong, Yongkang
    Kankanhalli, Mohan S.
    PROCEEDINGS OF 2016 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM), 2016, : 222 - 225
12345