Video-Based Traffic Accident Prevention Safety System Using Deep Learning 


Vol. 45,  No. 8, pp. 1399-1406, Aug.  2020
10.7840/kics.2020.45.8.1399


PDF
  Abstract

Intelligent visual monitoring for road vehicles and pedestrians is the key to developing autonomous intelligent traffic systems. Lately, traffic incident detection using image processing and computer vision has drawn much attention. In this paper, an accident prevention system based on deep learning (DL) i.e., YOLOv2-tiny is proposed. The DL-based accident prevention system detects lanes and pedestrians simultaneously, followed by a depth camera that estimates the distance between the pedestrian and the user. The current position of the vehicle is decided on the dot lane marker as a reference. Based on the distance calculation, an accident situation recognition algorithm is developed for an accident prevention system. Detailed experimental results for lanes and pedestrian detection are provided, showing the effectiveness of the proposed DL-based accident prevention system.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

S. H. Han, S. Chae, J. H. Park, S. A. Hassan, T. Rahim, S. Y. Shin, "Video-Based Traffic Accident Prevention Safety System Using Deep Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 8, pp. 1399-1406, 2020. DOI: 10.7840/kics.2020.45.8.1399.

[ACM Style]

Seung Heon Han, Seog Chae, Jae Han Park, Syed Ali Hassan, Tariq Rahim, and Soo Young Shin. 2020. Video-Based Traffic Accident Prevention Safety System Using Deep Learning. The Journal of Korean Institute of Communications and Information Sciences, 45, 8, (2020), 1399-1406. DOI: 10.7840/kics.2020.45.8.1399.

[KICS Style]

Seung Heon Han, Seog Chae, Jae Han Park, Syed Ali Hassan, Tariq Rahim, Soo Young Shin, "Video-Based Traffic Accident Prevention Safety System Using Deep Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 8, pp. 1399-1406, 8. 2020. (https://doi.org/10.7840/kics.2020.45.8.1399)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880