YOLOv8-UCB: Visual Detection of Pouch Battery Using Improved YOLOv8

The aluminum laminate pouch of pouch batteries is highly prone to deformation, which can cause various surface defects, thereby affecting their service life and potentially posing safety hazards. To address this problem, we propose an algorithm named YOLOv8-UCB for detecting surface defects in pouch...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao Hao, Xiang Yu
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10807296/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037656750129152
author Hao Hao
Xiang Yu
author_facet Hao Hao
Xiang Yu
author_sort Hao Hao
collection DOAJ
description The aluminum laminate pouch of pouch batteries is highly prone to deformation, which can cause various surface defects, thereby affecting their service life and potentially posing safety hazards. To address this problem, we propose an algorithm named YOLOv8-UCB for detecting surface defects in pouch batteries, which is based on the YOLOv8 model. First, while retaining the original network structure, we replaced the backbone of YOLOv8 with the UniRepLKNet feature extraction network to achieve a larger receptive field. Second, we constructed a distributed focal detection head CLLAHead, to better capture the features at different scales. Additionally, after each Concat layer in the head, we incorporated BiFormer attention mechanisms to enhance content-aware perception. Finally, we replaced the loss function with Slide Loss to address the issue of sample classification imbalance. The experimental results indicate that the improved algorithm achieved significant increases in precision, recall, mAP@0.5 and mAP@0.5:0.95, with improvements of 11.7%, 8.2%, 8.9% and 6.5% respectively, over the baseline model. In comparative studies against contemporaneous methodologies, the refined algorithm exhibited pronounced superiority in detection capabilities.
format Article
id doaj-art-8dac3c01f1cc4b0db548a7bfc1f41ed0
institution DOAJ
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-8dac3c01f1cc4b0db548a7bfc1f41ed02025-08-20T02:56:47ZengIEEEIEEE Access2169-35362024-01-011219489919491010.1109/ACCESS.2024.352018110807296YOLOv8-UCB: Visual Detection of Pouch Battery Using Improved YOLOv8Hao Hao0https://orcid.org/0000-0001-8904-877XXiang Yu1https://orcid.org/0009-0005-6933-3182School of Economics and Management, Shanghai Polytechnic University, Shanghai, ChinaSchool of Computer and Information Engineering, Shanghai Polytechnic University, Shanghai, ChinaThe aluminum laminate pouch of pouch batteries is highly prone to deformation, which can cause various surface defects, thereby affecting their service life and potentially posing safety hazards. To address this problem, we propose an algorithm named YOLOv8-UCB for detecting surface defects in pouch batteries, which is based on the YOLOv8 model. First, while retaining the original network structure, we replaced the backbone of YOLOv8 with the UniRepLKNet feature extraction network to achieve a larger receptive field. Second, we constructed a distributed focal detection head CLLAHead, to better capture the features at different scales. Additionally, after each Concat layer in the head, we incorporated BiFormer attention mechanisms to enhance content-aware perception. Finally, we replaced the loss function with Slide Loss to address the issue of sample classification imbalance. The experimental results indicate that the improved algorithm achieved significant increases in precision, recall, mAP@0.5 and mAP@0.5:0.95, with improvements of 11.7%, 8.2%, 8.9% and 6.5% respectively, over the baseline model. In comparative studies against contemporaneous methodologies, the refined algorithm exhibited pronounced superiority in detection capabilities.https://ieeexplore.ieee.org/document/10807296/Pouch battery defect detectionYOLOv8feature extraction networkdetection headattention mechanismloss function
spellingShingle Hao Hao
Xiang Yu
YOLOv8-UCB: Visual Detection of Pouch Battery Using Improved YOLOv8
IEEE Access
Pouch battery defect detection
YOLOv8
feature extraction network
detection head
attention mechanism
loss function
title YOLOv8-UCB: Visual Detection of Pouch Battery Using Improved YOLOv8
title_full YOLOv8-UCB: Visual Detection of Pouch Battery Using Improved YOLOv8
title_fullStr YOLOv8-UCB: Visual Detection of Pouch Battery Using Improved YOLOv8
title_full_unstemmed YOLOv8-UCB: Visual Detection of Pouch Battery Using Improved YOLOv8
title_short YOLOv8-UCB: Visual Detection of Pouch Battery Using Improved YOLOv8
title_sort yolov8 ucb visual detection of pouch battery using improved yolov8
topic Pouch battery defect detection
YOLOv8
feature extraction network
detection head
attention mechanism
loss function
url https://ieeexplore.ieee.org/document/10807296/
work_keys_str_mv AT haohao yolov8ucbvisualdetectionofpouchbatteryusingimprovedyolov8
AT xiangyu yolov8ucbvisualdetectionofpouchbatteryusingimprovedyolov8