Research On Lightweight Combined Detection Method For Personal Protective Equipment Based On Improved YOLO

Personal protective equipment(PPE)detection is aimed at real-time and accurate detection,standardized wearing of construction personnel’s safety helmet,safety belt and reflective clothing,which is of great significance to prevent accidents.In order to combined detection of multiple types of safety protective equipment worn by the construction personnel,and improve the problem that complex network can not give consideration to both real-time and detection accuracy on resource-limited edge devices,this paper studies the combined detection method of PPE applications based on improved YOLO algorithm,and lightweight PPE applications for embedded device.To solve the problem that combined detection of multiple safety protective equipment,A high-precision and end-to-end PPE combined detection algorithm,YOLOv4-PPE is designed by improving the class probability activation function,and non-maximum suppression strategy of YOLOv4 algorithm.To solve the problem,which the YOLOv4-PPE has too many parameters,and cannot be detected in real time on embedded devices,two methods of model lightweight were designed:Ghost-Dw-PPE and CLSlim-PPE.The first method was to reconstruct the YOLOv4-PPE model structure.First,Ghost Bottleneck was used to form the backbone feature extraction network,and then the Spatial Pyramid Pooling(SPP)module was inserted into the appropriate position of each detection head.Finally,the convolution module and down-sampling operation of feature fusion structure were redesigned.The second method was to design a channel pruning and layer pruning method(CLSlim),based on BN layer scaling factor.This method applies L1 regularization and gradient sparse training,on the scaling factor of Batch Normalization(BN)layer in the convolution module.A large number of redundant channel compression model parameters were removed by global pruning threshold,and local safety threshold.layer pruning threshold were used to improve inference speed.The CLSlim lightweight be used to improves YOLOv4-PPE and YOLOv4-Tiny-PPE model separately.The results show that the volume of CLSlim-YOLOv4-PPE model is reduced to 4.15MB and mAP decreases by 2.1%;CLSlim-YOLOV4-Tiny-PPE improves in all aspects compared with the original model,among which the model volume is 5.92MB and mAP is 0.8%higher than the original model.However,the volume of Ghost-Dw-PPE model is 44.6MB,and the mAP is reduced by 2.42%compared with the original model.Compared with the two types of model lightweight methods designed in this paper,CLSlim method is more efficient for model compression.Finally,the CLSlim-YOLOv4-Tiny-PPE algorithm was selected for application test on embedded devices with RK3399pro as main processor.The results show that:mAP is 92.3%,the detection speed on the embedded device is 0.0307 seconds,and the frame rate is about 33FPS,which meets the real-time detection requirements of 25 frames per second in practical application.Therefore,the combined detection algorithm of personal protective equipment designed in this paper achieves higher real-time performance and better identification accuracy,which has certain reference value.