Multi-Channel Fusion Decision-Making Online Detection Network for Surface Defects in Automotive Pipelines Based on Transfer Learning VGG16 Network

Although approaches for the online surface detection of automotive pipelines exist, low defect area rates, small-sample and long-tailed data, and the difficulty of detection due to the variable morphology of defects are three major problems faced when using such methods. In order to solve these prob...

Full description

Saved in:
Bibliographic Details
Main Authors: Jian Song, Yingzhong Tian, Xiang Wan
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/24/7914
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102764635029504
author Jian Song
Yingzhong Tian
Xiang Wan
author_facet Jian Song
Yingzhong Tian
Xiang Wan
author_sort Jian Song
collection DOAJ
description Although approaches for the online surface detection of automotive pipelines exist, low defect area rates, small-sample and long-tailed data, and the difficulty of detection due to the variable morphology of defects are three major problems faced when using such methods. In order to solve these problems, this study combines traditional visual detection methods and deep neural network technology to propose a transfer learning multi-channel fusion decision network without significantly increasing the number of network layers or the structural complexity. Each channel of the network is designed according to the characteristics of different types of defects. Dynamic weights are assigned to achieve decision-level fusion through the use of a matrix of indicators to evaluate the performance of each channel’s recognition ability. In order to improve the detection efficiency and reduce the amount of data transmission and processing, an improved ROI detection algorithm for surface defects is proposed. It can enable the rapid screening of target surfaces for the high-quality and rapid acquisition of surface defect images. On an automotive pipeline surface defect dataset, the detection accuracy of the multi-channel fusion decision network with transfer learning was 97.78% and its detection speed was 153.8 FPS. The experimental results indicate that the multi-channel fusion decision network could simultaneously take into account the needs for real-time detection and accuracy, synthesize the advantages of different network structures, and avoid the limitations of single-channel networks.
format Article
id doaj-art-1a30d64b78504f4b956b07c0f0c9b016
institution Kabale University
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-1a30d64b78504f4b956b07c0f0c9b0162024-12-27T14:52:25ZengMDPI AGSensors1424-82202024-12-012424791410.3390/s24247914Multi-Channel Fusion Decision-Making Online Detection Network for Surface Defects in Automotive Pipelines Based on Transfer Learning VGG16 NetworkJian Song0Yingzhong Tian1Xiang Wan2Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, ChinaShanghai Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, ChinaInstitute of Applied Physics, Jiangxi Academy of Sciences, Nanchang 330000, ChinaAlthough approaches for the online surface detection of automotive pipelines exist, low defect area rates, small-sample and long-tailed data, and the difficulty of detection due to the variable morphology of defects are three major problems faced when using such methods. In order to solve these problems, this study combines traditional visual detection methods and deep neural network technology to propose a transfer learning multi-channel fusion decision network without significantly increasing the number of network layers or the structural complexity. Each channel of the network is designed according to the characteristics of different types of defects. Dynamic weights are assigned to achieve decision-level fusion through the use of a matrix of indicators to evaluate the performance of each channel’s recognition ability. In order to improve the detection efficiency and reduce the amount of data transmission and processing, an improved ROI detection algorithm for surface defects is proposed. It can enable the rapid screening of target surfaces for the high-quality and rapid acquisition of surface defect images. On an automotive pipeline surface defect dataset, the detection accuracy of the multi-channel fusion decision network with transfer learning was 97.78% and its detection speed was 153.8 FPS. The experimental results indicate that the multi-channel fusion decision network could simultaneously take into account the needs for real-time detection and accuracy, synthesize the advantages of different network structures, and avoid the limitations of single-channel networks.https://www.mdpi.com/1424-8220/24/24/7914transfer learningfusion decision makingfast surface quality screeningsurface defect detection
spellingShingle Jian Song
Yingzhong Tian
Xiang Wan
Multi-Channel Fusion Decision-Making Online Detection Network for Surface Defects in Automotive Pipelines Based on Transfer Learning VGG16 Network
Sensors
transfer learning
fusion decision making
fast surface quality screening
surface defect detection
title Multi-Channel Fusion Decision-Making Online Detection Network for Surface Defects in Automotive Pipelines Based on Transfer Learning VGG16 Network
title_full Multi-Channel Fusion Decision-Making Online Detection Network for Surface Defects in Automotive Pipelines Based on Transfer Learning VGG16 Network
title_fullStr Multi-Channel Fusion Decision-Making Online Detection Network for Surface Defects in Automotive Pipelines Based on Transfer Learning VGG16 Network
title_full_unstemmed Multi-Channel Fusion Decision-Making Online Detection Network for Surface Defects in Automotive Pipelines Based on Transfer Learning VGG16 Network
title_short Multi-Channel Fusion Decision-Making Online Detection Network for Surface Defects in Automotive Pipelines Based on Transfer Learning VGG16 Network
title_sort multi channel fusion decision making online detection network for surface defects in automotive pipelines based on transfer learning vgg16 network
topic transfer learning
fusion decision making
fast surface quality screening
surface defect detection
url https://www.mdpi.com/1424-8220/24/24/7914
work_keys_str_mv AT jiansong multichannelfusiondecisionmakingonlinedetectionnetworkforsurfacedefectsinautomotivepipelinesbasedontransferlearningvgg16network
AT yingzhongtian multichannelfusiondecisionmakingonlinedetectionnetworkforsurfacedefectsinautomotivepipelinesbasedontransferlearningvgg16network
AT xiangwan multichannelfusiondecisionmakingonlinedetectionnetworkforsurfacedefectsinautomotivepipelinesbasedontransferlearningvgg16network