A Helmet Detection Algorithm Based on Transformers with Deformable Attention Module  

作　　者：Songle Chen Hongbo Sun Yuxin Wu Lei Shang Xiukai Ruan 

机构地区：[1]Engineering Research Center of Post Big Data Technology and Application of Jiangsu Province,Nanjing University of Posts and Telecommunications,Nanjing 210003,China [2]State Key Lab for Novel Software Technology,Nanjing University,Nanjing 210023,China [3]Institute of Intelligent Locks,Wenzhou University,Wenzhou 325035,China

出　　处：《Chinese Journal of Electronics》2025年第1期229-241,共13页电子学报(英文版)

基　　金：supported by the Innovation Foundation of State Key Lab for Novel Software Technology of China(Grant No.KFKT2022B19);the Natural Science Foundation of Nanjing University of Posts and Telecommunications(Grant Nos.NY220213 and NY221105)。

摘　　要：Wearing a helmet is one of the effective measures to protect workers'safety.To address the challenges of severe occlusion,multi-scale,and small target issues in helmet detection,this paper proposes a helmet detection algorithm based on deformable attention transformers.The main contributions of this paper are as follows.A compact end-to-end network architecture for safety helmet detection based on transformers is proposed.It cancels the computationally intensive transformer encoder module in the existing detection transformer(DETR)and uses the transformer decoder module directly on the output of feature extraction for query decoding,which effectively improves the efficiency of helmet detection.A novel feature extraction network named Swin transformer with deformable attention module(DSwin transformer)is proposed.By sparse cross-window attention,it enhances the contextual awareness of multi-scale features extracted by Swin transformer,and keeps high computational efficiency simultaneously.The proposed method generates the query reference points and query embeddings based on the joint prediction probabilities,and selects an appropriate number of decoding feature maps and sparse sampling points for query decoding,which further enhance the inference capability and processing speed.On the benchmark safety-helmet-wearing-dataset(SHWD),the proposed method achieves the average detection accuracy mAP@0.5 of 95.4%with 133.35G floating-point operations per second(FLOPs)and 20 frames per second(FPS),the state-of-the-art method for safety helmet detection.

关 键 词：HELMET Object detection Deformable attention TRANSFORMER DECODER 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]