CA-CentripetalNet: A novel anchor-free deep learning framework for hardhat wearing detection

TL;DR

This paper introduces CA-CentripetalNet, an innovative anchor-free deep learning framework that improves hardhat wearing detection accuracy in complex construction site videos by enhancing feature extraction and attention mechanisms.

Contribution

The paper proposes a novel anchor-free framework with two schemes—vertical-horizontal corner pooling and bounding constrained center attention—to improve detection performance and generalization.

Findings

Achieves 86.63% mAP in hardhat detection

Performs better on small-scale and non-worn hardhats

Uses less memory and maintains reasonable speed

Abstract

Automatic hardhat wearing detection can strengthen the safety management in construction sites, which is still challenging due to complicated video surveillance scenes. To deal with the poor generalization of previous deep learning based methods, a novel anchor-free deep learning framework called CA-CentripetalNet is proposed for hardhat wearing detection. Two novel schemes are proposed to improve the feature extraction and utilization ability of CA-CentripetalNet, which are vertical-horizontal corner pooling and bounding constrained center attention. The former is designed to realize the comprehensive utilization of marginal features and internal features. The latter is designed to enforce the backbone to pay attention to internal features, which is only used during the training rather than during the detection. Experimental results indicate that the CA-CentripetalNet achieves better performance with the 86.63% mAP (mean Average Precision) with less memory consumption at a reasonable speed than the existing deep learning based methods, especially in case of small-scale hardhats and non-worn-hardhats.