Large, Complex, and Realistic Safety Clothing and Helmet Detection: Dataset and Method

TL;DR

This paper introduces a large, realistic safety clothing and helmet detection dataset from chemical plants, and proposes a flexible attention-based low-light enhancement module that improves detection performance in low-light conditions.

Contribution

The creation of the SFCHD dataset from real chemical plants and the development of the SCALE module for low-light enhancement are novel contributions.

Findings

SFCHD dataset contains 12,373 images and 50,552 annotations.

SCALE module improves detection accuracy under low-light conditions.

Extensive evaluations validate the effectiveness of the proposed methods.

Abstract

Detecting safety clothing and helmets is paramount for ensuring the safety of construction workers. However, the development of deep learning models in this domain has been impeded by the scarcity of high-quality datasets. In this study, we construct a large, complex, and realistic safety clothing and helmet detection (SFCHD) dataset. SFCHD is derived from two authentic chemical plants, comprising 12,373 images, 7 categories, and 50,552 annotations. We partition the SFCHD dataset into training and testing sets with a ratio of 4:1 and validate its utility by applying several classic object detection algorithms. Furthermore, drawing inspiration from spatial and channel attention mechanisms, we design a spatial and channel attention-based low-light enhancement (SCALE) module. SCALE is a plug-and-play component with a high degree of flexibility. Extensive evaluations of the SCALE module on both the ExDark and SFCHD datasets have empirically demonstrated its efficacy in enhancing the performance of detectors under low-light conditions. The dataset and code are publicly available at https://github.com/lijfrank-open/SFCHD-SCALE.