Paper Contents
Abstract
Wearing safety helmets can effectively protect workers safetyonconstructionsites. However, workers oftentake off thehelmets because of weak security-conscious and discomfort,then hidden dangers will be brought by this behavior. Hence,detecting safety helmet wearing is a vital step of constructionsitessafetymanagementandasafetyhelmetdetectorwithhighspeed and accuracy is urgently needed. Therefore, this paperproposes a deep learning-based method to detect safety helmetwearing at a satisfactory accuracy with high detection speed.Our method chooses YOLO v5 as the baseline, then the fourthdetection scale is added to predict more bounding boxes forsmall objects and the attention mechanism is adopted in thebackboneofthenetworktoconstructmoreinformativefeaturesforfollowingconcatenationoperations.Theseresultsdemonstratetherobustnessandfeasibilityofourmodel.Whichmeansthemodeliseasytobedeployed?Atlast,afterobtainingasatisfactorymodel,agraphicaluserinterface(GUI)isdesigned tomakeour algorithm moreuser- friendly.
Copyright
Copyright © 2023 Gantasala Sowjanya. This is an open access article distributed under the Creative Commons Attribution License.
