Self-enhancement of automatic tunnel accident detection (TAD) on CCTV by AI deep-learning

TL;DR

This paper presents an improved deep-learning tunnel accident detection system that reduces false alarms by incorporating field data into retraining, enhancing accuracy in CCTV monitoring of tunnels.

Contribution

The study introduces a self-enhancement method for TAD systems by using field data to retrain deep learning models, significantly reducing false detections.

Findings

False detection of pedestrians and fires was significantly reduced.

Field data retraining improved detection accuracy.

System successfully monitored 9 CCTVs at a tunnel site.

Abstract

The deep-learning-based tunnel accident detection (TAD) system (Lee 2019) has installed a system capable of monitoring 9 CCTVs at XX site in November, 2018. The initial deep-learning training was started by studying 70,914 labeled images and label data. However, sunlight, the tail light of a vehicle, and the warning light of the working vehicle were recognized as a fire, and many pedestrians were detected in the lane of the tunnel or a black elongated black object. To solve these problems, as shown in Fig. 1, the false detection data detected in the field were trained with labeled data and reapplied in the field. As a result, false detection of pedestrians and fire could be significantly reduced.