Yanman Li1, Jun Zhang1, Yang Hu1, Yingnan Zhao2,*, Yi Cao3
Computer Systems Science and Engineering, Vol.43, No.3, pp. 1219-1230, 2022, DOI:10.32604/csse.2022.028224
Abstract Safety helmet-wearing detection is an essential part of the intelligent monitoring system. To improve the speed and accuracy of detection, especially small targets and occluded objects, it presents a novel and efficient detector model. The underlying core algorithm of this model adopts the YOLOv5 (You Only Look Once version 5) network with the best comprehensive detection performance. It is improved by adding an attention mechanism, a CIoU (Complete Intersection Over Union) Loss function, and the Mish activation function. First, it applies the attention mechanism in the feature extraction. The network can learn the weight of… More >