Junjie Bao, Shihua Li, Guanglong Wang, Jianmin Xiong, Sailai Li
{"title":"Improved YOLOV8 Network and Application in Safety Helmet Detection","authors":"Junjie Bao, Shihua Li, Guanglong Wang, Jianmin Xiong, Sailai Li","doi":"10.1088/1742-6596/2632/1/012012","DOIUrl":null,"url":null,"abstract":"Abstract This paper proposes a research method to enhance the accuracy and real-time capability of helmet detection in complex industrial environments, aiming to address the engineering challenges of poor robustness and significant occurrences of both false positives and false negatives in existing detection methods. In this study, the C2F (faster version of CSP Bottleneck with two convolutions) module and FE (FasterNet with EMA) module are integrated into the network architecture of YOLOV8 to form a new attention mechanism module called C2F-FE. This module enhances the model’s perception of safety helmet targets by fusing feature information from different levels and incorporating attention mechanisms while reducing computational overhead. Furthermore, the model is trained and optimized on publicly available safety helmet datasets. Experimental results demonstrate that the improved model exhibits stronger robustness, achieving an accuracy rate of 94.6% and a mAP50 of 99.1% for safety helmet detection in complex construction scenarios, with an inference time of 0.7 ms.","PeriodicalId":44008,"journal":{"name":"Journal of Physics-Photonics","volume":null,"pages":null},"PeriodicalIF":4.6000,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Physics-Photonics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1088/1742-6596/2632/1/012012","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"OPTICS","Score":null,"Total":0}
引用次数: 0
Abstract
Abstract This paper proposes a research method to enhance the accuracy and real-time capability of helmet detection in complex industrial environments, aiming to address the engineering challenges of poor robustness and significant occurrences of both false positives and false negatives in existing detection methods. In this study, the C2F (faster version of CSP Bottleneck with two convolutions) module and FE (FasterNet with EMA) module are integrated into the network architecture of YOLOV8 to form a new attention mechanism module called C2F-FE. This module enhances the model’s perception of safety helmet targets by fusing feature information from different levels and incorporating attention mechanisms while reducing computational overhead. Furthermore, the model is trained and optimized on publicly available safety helmet datasets. Experimental results demonstrate that the improved model exhibits stronger robustness, achieving an accuracy rate of 94.6% and a mAP50 of 99.1% for safety helmet detection in complex construction scenarios, with an inference time of 0.7 ms.
针对现有检测方法鲁棒性差、假阳性和假阴性现象严重的工程难题,提出了一种提高复杂工业环境下头盔检测精度和实时性的研究方法。本研究将C2F (faster version of CSP Bottleneck with two convolutions)模块和FE (FasterNet with EMA)模块集成到YOLOV8的网络架构中,形成新的注意机制模块C2F-FE。该模块通过融合不同层次的特征信息,结合注意机制,增强了模型对安全帽目标的感知能力,同时减少了计算开销。此外,该模型在公开可用的安全帽数据集上进行训练和优化。实验结果表明,改进后的模型具有更强的鲁棒性,在复杂施工场景下的安全帽检测准确率为94.6%,mAP50为99.1%,推理时间为0.7 ms。