An Object Detection-Based Real-Time Analysis and Alert system for Factory Environments 


Vol. 51,  No. 3, pp. 705-712, Mar.  2026
10.7840/kics.2026.51.3.705


PDF Full-Text
  Abstract

This paper presents a real-time alert system for factory environments that leverages YOLOv8-based object detection and TensorRT optimization to process multiple CCTV streams in parallel. A perspective-correct grid is automatically generated using camera intrinsic parameters and projection matrices, enabling accurate spatial risk assessment for forklift proximity, pathway noncompliance, and helmet absence. Detected risk events are scored, stored in a database, and visualized on a web-based dashboard. Upon detection of a forklift-related hazard, an immediate warning is issued to nearby workers via LoRa wireless communication to activate on-board alarms. Experiments in a real factory demonstrate an average detection-to-alert latency of 0.349 s with 100% communication reliability. The system’s risk score visualization proved effective in raising safety awareness among workers.

  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.


  Related Articles
  Cite this article

[IEEE Style]

J. Kang, J. Jang, J. Kim, Y. Yoo, "An Object Detection-Based Real-Time Analysis and Alert system for Factory Environments," The Journal of Korean Institute of Communications and Information Sciences, vol. 51, no. 3, pp. 705-712, 2026. DOI: 10.7840/kics.2026.51.3.705.

[ACM Style]

Jung-heon Kang, Jin-ho Jang, Ji-myeong Kim, and Younghwan Yoo. 2026. An Object Detection-Based Real-Time Analysis and Alert system for Factory Environments. The Journal of Korean Institute of Communications and Information Sciences, 51, 3, (2026), 705-712. DOI: 10.7840/kics.2026.51.3.705.

[KICS Style]

Jung-heon Kang, Jin-ho Jang, Ji-myeong Kim, Younghwan Yoo, "An Object Detection-Based Real-Time Analysis and Alert system for Factory Environments," The Journal of Korean Institute of Communications and Information Sciences, vol. 51, no. 3, pp. 705-712, 3. 2026. (https://doi.org/10.7840/kics.2026.51.3.705)
Vol. 51, No. 3 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880