YOLOV5s object detection based on Sim SPPF hybrid pooling

Abstract

Aiming at the problem of low surface defect detection accuracy of industrial products, an object detection method based on simplified spatial pyramid pooling fast (Sim SPPF) hybrid pooling improved you only look once version 5s (YOLOV5s) model is proposed. The algorithm introduces channel attention (CA) module, simplified SPPF feature vector pyramid and efficient intersection over union (EIOU) loss function. Feature vector pyramids fuse high-dimensional and low-dimensional features, which makes semantic information richer. The CA mechanism performs maximum pooling and average pooling operations on the feature map. Hybrid pooling comprehensively improves detection computing efficiency and accurate deployment ability. The results show that the improved YOLOV5s model is better than the original YOLOV5s model. The average test accuracy (mAP) can reach 91.8%, which can be increased by 17.4%, and the detection speed can reach 108 FPS, which can be increased by 18 FPS. The improved model is practicable, and the overall performance is better than other conventional models.

References

[[1]] Wang B Z, Zhao X H. ME-YOLO: improved YOLOv5 for detecting medical personal protective equipment[J]. Applied sciences, 2022, 12(23): 47-53

[[2]] Liang C, Yan Z, Ren M. Improved YOLOv5 infrared tank target detection method under ground background[J]. Scientific reports, 2023, 13(1): 67-70

[[3]] Deng L, Bi L, Li H. Lightweight aerial image object detection algorithm based on improved YOLOv5s[J]. Scientific reports, 2023, 13(1): 45-60,

[[4]] Li J, Tao H. An efficient method of pavement distress detection based on improved YOLOv7[J]. Measurement science and technology, 2023, 34(11): 78-86

[[5]] Yu H, Li X, Feng Y. Multiple attentional path aggregation network for marine object detection[J]. Applied intelligence, 2023, 53(2): 2434-2451,

[[6]] Liu Y, Jiang D, Xu C. Deep learning based 3D target detection for indoor scenes[J]. Applied intelligence, 2022, 53(9): 10218-10231,

[[7]] Li Y, Ni M Z, Lu Y F, et al.. Insulator defect detection for power grid based on light correction enhancement and YOLOv5 model[J]. Energy reports, 2023, 63(13): 1143-1157

[[8]] Lin H. Multi-scale forest fire recognition model based on improved YOLOv5s[J]. Forests, 2022, 18(7): 807-814

[[9]] Dong X, Yan S, Duan C. A lightweight vehicles detection network model based on YOLOv5[J]. Engineering applications of artificial intelligence, 2023, 14(11): 405-411

[[10]] Zhao K, Zhao L, Zhao Y. Study on lightweight model of maize seedling object detection based on YOLOv7[J]. Applied sciences, 2023, 13(13): 734-741,

[[11]] Jin C, Ben X M, Chao J. Apple inflorescence recognition of phenology stage in complex background based on improved YOLOv7[J]. Computers and electronics in agriculture, 2023, 51(23): 211-219

[[12]] Shaikh S A, Chopade J J, Sardey M P. Real-time multi-object detection using enhanced YOLOv5-7S on multi-GPU for high-resolution video[J]. International journal of image and graphics, 2023, 37(15): 89-97

[[13]] Jiang M, Yin S. Facial expression recognition based on convolutional block attention module and multi-feature fusion[J]. International journal of computational vision and robotics, 2023, 13(1): 789-795,

[[14]] Li G. MSFT-YOLO: improved YOLOv5 based on transformer for detecting defects of steel surface[J]. Sensors, 2022, 22(7): 61-67

[[15]] Wei Z, Shi P. A masked-face detection algorithm based on M-EIOU loss and improved ConvNeXt[J]. Expert systems with applications, 2023, 22(5): 571-579

[[16]] Liu Z W, Liu W T, Wang C Q. An anchor-free detector with knowledge distillation for industrial defect detection[J]. IEEE transactions on instrumentation and measurement, 2022, 7(3): 218-227