收藏切换
Research of deep learning-based methods for highway traffic accident detection
收藏切换
PDF
Rui Ling1, 2, Kun Yan1, 2, Hongyu Liang1, 2, Zhuoqi Wei1, 2, Hangbo Hao1, 2
Electronic Measurement Technology | 2026, 49(6) : 29 - 38
Less
收藏切换
Electronic Measurement Technology | 2026, 49(6): 29-38
Research and Design
Research of deep learning-based methods for highway traffic accident detection
Full
Rui Ling1, 2, Kun Yan1, 2, Hongyu Liang1, 2, Zhuoqi Wei1, 2, Hangbo Hao1, 2
Affiliations
  • 1.School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China
  • 2.National and Local Joint Engineering Research Center for Satellite Navigation, Positioning and Location Services, Guilin University of Electronic Technology, Guilin 541004, China
doi: 10.19651/j.cnki.emt.2519268
Outline
收藏切换

Existing single-stage deep models for traffic accident detection often suffer from high false alarm rates and computational redundancy in highway scenarios, severely limiting their practical deployment. To address these issues, this paper proposes a two-stage traffic accident detection method tailored for highways, following a "stationary vehicle filtering+appearance-based recognition" strategy. In the first stage, YOLO11 and Bot-SORT are integrated to detect and track vehicles, and inter-frame speed analysis is used to identify stationary vehicles as potential accident candidates. In the second stage, an improved model named YOLO-EA is introduced to perform appearance-based detection exclusively on the stationary vehicles, combined with a multi-frame voting mechanism to enhance stability and robustness. Built upon the YOLO11 architecture, YOLO-EA incorporates an EAS-Stem module and an AWD-Conv module. The former enhances edge and contour extraction in the input stage, while the latter improves downsampling efficiency by retaining critical features and reducing computational cost. Experimental results show that YOLO-EA improves Precision, and :0.95 by 10.9%, 3.4% and 2.8% respectively, while reducing parameter count by 21%. On the constructed accident video dataset, the proposed method achieves an accident recognition rate of 81.25%, with a 24.46% reduction in false alarm rate compared to single-stage detection strategies. This method achieves a favorable balance between accuracy and inference efficiency, demonstrating strong potential for real-world deployment.

traffic safety  /  accident detection  /  multi-object tracking  /  deep learning  /  highway
Rui Ling, Kun Yan, Hongyu Liang, Zhuoqi Wei, Hangbo Hao. Research of deep learning-based methods for highway traffic accident detection[J]. Electronic Measurement Technology, 2026 , 49 (6) : 29 -38 . DOI: 10.19651/j.cnki.emt.2519268
Year 2026 volume 49 Issue 6
PDF
50
10
Cite this Article
BibTeX
Article Info
doi: 10.19651/j.cnki.emt.2519268
  • Receive Date:2025-07-03
  • Online Date:2026-05-15
Article Data
Affiliations
History
  • Received:2025-07-03
Funding
Affiliations
    1.School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China
    2.National and Local Joint Engineering Research Center for Satellite Navigation, Positioning and Location Services, Guilin University of Electronic Technology, Guilin 541004, China
References
Share
https://castjournals.cast.org.cn/joweb/dzcljs/EN/10.19651/j.cnki.emt.2519268
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT