Improvement of Helmet Detection Algorithm Based on YOLOv8

Abstract In order to solve the problems of safety helmets in complex factory environments due to the complex background, dense targets, etc., which cause the YOLOv8s algorithm to be prone to leakage and misdetection, and low recognition accuracy, a safety casque detection algorithm based on the YOLOv8s improved YOLOv8s-improved is proposed. By incorporating a deformable convolutional module into the backbone network of YOLOv8s, the occurrences of false negatives and false positives are effectively reduced, and detection accuracy is enhanced. To tackle the issue of small target detection being easily disturbed by image backgrounds and noise, the CBAM attention mechanism is embedded to sift out the relatively important information from a large amount of information, and enhances the ability of helmet information extraction; for the problem that the loss of small target classification and localization is not easy to calculate, a new For the problem of small target classification and localization loss is not easy to calculate, a new IoU loss function is introduced to improve the training effect of the model. The experiment shows that the detection accuracy mAP of the improved YOLOv8s algorithm in this paper is 1.3% higher than that of the original YOLOv8s algorithm. Experimental results have shown that the improved algorithm proposed in this paper not only reduces false positives and false negatives in helmet wearing detection, but also enhances the detection capability for small targets, thus improving the performance of helmet wearing detection to a certain extent.