Detecting individuals wearing safety helmets in complex environments faces several *** factors include limited detection accuracy and frequent missed or false ***,existing algorithms often have excessive parameter cou...
详细信息
Detecting individuals wearing safety helmets in complex environments faces several *** factors include limited detection accuracy and frequent missed or false ***,existing algorithms often have excessive parameter counts,complex network structures,and high computational *** challenges make it difficult to deploy such models efficiently on resource-constrained devices like embedded *** at this problem,this research proposes an optimized and lightweight solution called FGP-YOLOv8,an improved version of *** YOLOv8 backbone network is replaced with the FasterNet model to reduce parameters and computational demands while local convolution layers are *** modification minimizes computational costs with only a minor impact on accuracy.A new GSTA(GSConv-Triplet Attention)module is introduced to enhance feature fusion and reduce computational *** is achieved using attention weights generated from dimensional interactions within the feature ***,the ParNet-C2f module replaces the original C2f(CSP Bottleneck with 2 Convolutions)module,improving feature extraction for safety helmets of various shapes and *** CIoU(Complete-IoU)is replaced with the WIoU(Wise-IoU)to boost performance further,enhancing detection accuracy and generalization *** results validate the *** proposedmodel reduces the parameter count by 19.9% and the computational load by 18.5%.At the same time,mAP(mean average precision)increases by 2.3%,and precision improves by 1.2%.These results demonstrate the model’s robust performance in detecting safety helmets across diverse environments.
暂无评论