Research on Tunnel Quality Defect Detection Based on Improved Yolov5s

Жу, Анфу; Wang, Bin; Ma, Congxiao; Xie, Jiaxiao

doi:10.2139/ssrn.4281615

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PANet structure is used without considering the importance of different feature information, which makes it difficult to effectively filter out the information that is beneficial to model training. BiFPN uses the idea of bidirectional fusion 11 , constructs top-to-bottom and bottom-to-top bi-directional channels to fuse feature maps at multiple scales, unifies feature resolution scales by up-and down-sampling, achieves more accurate multi-scale feature fusion, and effectively enhances the correlation between local features of smoke branch images, so the BiFPN structure is used instead of the PANet structure.…”

Section: Feature Fusion Module Improvementsmentioning

confidence: 99%

Research on improved YOLOv5-based defect detection algorithm for cigarette air thinning head

Wang,

Li,

Han

et al. 2023

Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023)

View full text Add to dashboard Cite

Cigarette empty thin head defect detection is an important step to ensure product quality in tobacco factories. To address the current problems about detecting thin head with little content and low accuracy, a cigarette empty thin head defect detection algorithm based on improved YOLOv5s is proposed. Firstly, a convolutional block attention mechanism is introduced between neck and head to emphasize the extraction of empty thin head defect features; then a weighted bidirectional feature pyramid structure is used to improve the neck network and enhance the feature fusion capability of the model; finally, a lightweight module is designed to reduce the computational complexity of the model. The experimental results show that the improved algorithm can effectively detect cigarette hollow-head defects with an improved accuracy of 2.1%, and the model parameters are only 5.35M, which can provide technical support for subsequent cigarette hollow-head defect detection.

show abstract

Section: Feature Fusion Module Improvementsmentioning

confidence: 99%