Cross-Layer Feature Fusion and Decentration Aberration Correction of Circular Points for Automated Guided Vehicle Terminal Positioning

To address the visual detection and positioning challenge of the Automated Guided Vehicle (AGV) terminal, this study proposed a high-precision target recognition and positioning strategy based on cross-layer feature fusion and eccentricity error correction. In the remote coarse positioning stage, sm...

Full description

Saved in:
Bibliographic Details
Main Authors: Guiyang Zhang, Lanyu Yang, Kunkang Cao, Zengguang Man, Jian Wu, Boning Li
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10288384/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849417147049050112
author Guiyang Zhang
Lanyu Yang
Kunkang Cao
Zengguang Man
Jian Wu
Boning Li
author_facet Guiyang Zhang
Lanyu Yang
Kunkang Cao
Zengguang Man
Jian Wu
Boning Li
author_sort Guiyang Zhang
collection DOAJ
description To address the visual detection and positioning challenge of the Automated Guided Vehicle (AGV) terminal, this study proposed a high-precision target recognition and positioning strategy based on cross-layer feature fusion and eccentricity error correction. In the remote coarse positioning stage, small number of receiver domains underwent continuous multi-layer convolution, which broadened the receptive field of a single element in the feature map of a small circular target. Next, a cross-layer connection feature pyramid was constructed, and the deconvolution module was utilized to enlarge the feature map and fuse it with the shallow features, focusing more on the fine-grained image recognition and enhancing the applicability of circular marker detection. In the near-end fine positioning stage, the factors impacting the deviation between the projection point of the circular feature center and the fitting center were analyzed. Based on this analysis, the deviation of the iterative fitting center was corrected to approximate the real center projection sub-pixel coordinates. The experimental results demonstrated that the proposed method achieved dynamic positioning accuracy of better than 2.0 mm, static positioning accuracy of better than 1.5 mm, and a false recognition rate of less than 1.33% in the range of 3 m from AGV to the tray. Consequently, this method has significant application potential in enabling rapid and stable terminal vision positioning.
format Article
id doaj-art-e1ca46cab67049d9b8900f914d0b3ef9
institution Kabale University
issn 1943-0655
language English
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-e1ca46cab67049d9b8900f914d0b3ef92025-08-20T03:32:55ZengIEEEIEEE Photonics Journal1943-06552023-01-0115611110.1109/JPHOT.2023.332630510288384Cross-Layer Feature Fusion and Decentration Aberration Correction of Circular Points for Automated Guided Vehicle Terminal PositioningGuiyang Zhang0https://orcid.org/0000-0001-6485-2710Lanyu Yang1https://orcid.org/0009-0002-2488-2258Kunkang Cao2Zengguang Man3Jian Wu4https://orcid.org/0000-0002-8118-5101Boning Li5School of Mechanical Engineering, Changshu Institute of Technology, Suzhou, ChinaSchool of Mechanical Engineering, Changshu Institute of Technology, Suzhou, ChinaOptical Measurement Center, TZTEK Technology Company, Ltd., Suzhou, ChinaSchool of Mechanical Engineering, Changshu Institute of Technology, Suzhou, ChinaSchool of Mechanical Engineering, Changshu Institute of Technology, Suzhou, ChinaDepartment of Electrical and Computer Engineering, Rice University, Houston, TX, USATo address the visual detection and positioning challenge of the Automated Guided Vehicle (AGV) terminal, this study proposed a high-precision target recognition and positioning strategy based on cross-layer feature fusion and eccentricity error correction. In the remote coarse positioning stage, small number of receiver domains underwent continuous multi-layer convolution, which broadened the receptive field of a single element in the feature map of a small circular target. Next, a cross-layer connection feature pyramid was constructed, and the deconvolution module was utilized to enlarge the feature map and fuse it with the shallow features, focusing more on the fine-grained image recognition and enhancing the applicability of circular marker detection. In the near-end fine positioning stage, the factors impacting the deviation between the projection point of the circular feature center and the fitting center were analyzed. Based on this analysis, the deviation of the iterative fitting center was corrected to approximate the real center projection sub-pixel coordinates. The experimental results demonstrated that the proposed method achieved dynamic positioning accuracy of better than 2.0 mm, static positioning accuracy of better than 1.5 mm, and a false recognition rate of less than 1.33% in the range of 3 m from AGV to the tray. Consequently, this method has significant application potential in enabling rapid and stable terminal vision positioning.https://ieeexplore.ieee.org/document/10288384/Automated guided vehicles (AGV)target detectionfeature fusiondecentration aberration correctionvision positioning
spellingShingle Guiyang Zhang
Lanyu Yang
Kunkang Cao
Zengguang Man
Jian Wu
Boning Li
Cross-Layer Feature Fusion and Decentration Aberration Correction of Circular Points for Automated Guided Vehicle Terminal Positioning
IEEE Photonics Journal
Automated guided vehicles (AGV)
target detection
feature fusion
decentration aberration correction
vision positioning
title Cross-Layer Feature Fusion and Decentration Aberration Correction of Circular Points for Automated Guided Vehicle Terminal Positioning
title_full Cross-Layer Feature Fusion and Decentration Aberration Correction of Circular Points for Automated Guided Vehicle Terminal Positioning
title_fullStr Cross-Layer Feature Fusion and Decentration Aberration Correction of Circular Points for Automated Guided Vehicle Terminal Positioning
title_full_unstemmed Cross-Layer Feature Fusion and Decentration Aberration Correction of Circular Points for Automated Guided Vehicle Terminal Positioning
title_short Cross-Layer Feature Fusion and Decentration Aberration Correction of Circular Points for Automated Guided Vehicle Terminal Positioning
title_sort cross layer feature fusion and decentration aberration correction of circular points for automated guided vehicle terminal positioning
topic Automated guided vehicles (AGV)
target detection
feature fusion
decentration aberration correction
vision positioning
url https://ieeexplore.ieee.org/document/10288384/
work_keys_str_mv AT guiyangzhang crosslayerfeaturefusionanddecentrationaberrationcorrectionofcircularpointsforautomatedguidedvehicleterminalpositioning
AT lanyuyang crosslayerfeaturefusionanddecentrationaberrationcorrectionofcircularpointsforautomatedguidedvehicleterminalpositioning
AT kunkangcao crosslayerfeaturefusionanddecentrationaberrationcorrectionofcircularpointsforautomatedguidedvehicleterminalpositioning
AT zengguangman crosslayerfeaturefusionanddecentrationaberrationcorrectionofcircularpointsforautomatedguidedvehicleterminalpositioning
AT jianwu crosslayerfeaturefusionanddecentrationaberrationcorrectionofcircularpointsforautomatedguidedvehicleterminalpositioning
AT boningli crosslayerfeaturefusionanddecentrationaberrationcorrectionofcircularpointsforautomatedguidedvehicleterminalpositioning