Domain Feature Mapping with YOLOv7 for Automated Edge-Based Pallet Racking Inspections

Muhammad Hussain; Hussain Al-Aqrabi; Muhammad Munawar; Richard Hill; Tariq Alsboui

doi:10.3390/s22186927

Domain Feature Mapping with YOLOv7 for Automated Edge-Based Pallet Racking Inspections

Muhammad Hussain, Hussain Al-Aqrabi, Muhammad Munawar, Richard Hill, Tariq Alsboui

Research output: Contribution to journal › Article › peer-review

56 Citations (Scopus)

Abstract

Pallet racking is an essential element within warehouses, distribution centers, and manufacturing facilities. To guarantee its safe operation as well as stock protection and personnel safety, pallet racking requires continuous inspections and timely maintenance in the case of damage being discovered. Conventionally, a rack inspection is a manual quality inspection process completed by certified inspectors. The manual process results in operational down-time as well as inspection and certification costs and undiscovered damage due to human error. Inspired by the trend toward smart industrial operations, we present a computer vision-based autonomous rack inspection framework centered around YOLOv7 architecture. Additionally, we propose a domain variance modeling mechanism for addressing the issue of data scarcity through the generation of representative data samples. Our proposed framework achieved a mean average precision of 91.1%.

Original language	English
Article number	6927
Number of pages	13
Journal	Sensors (Switzerland)
Volume	22
Issue number	18
DOIs	https://doi.org/10.3390/s22186927
Publication status	Published - 13 Sep 2022

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.3390/s22186927Licence: CC BY

Cite this

@article{12c0cfaf59cc40508b8cd89f1e368f5b,

title = "Domain Feature Mapping with YOLOv7 for Automated Edge-Based Pallet Racking Inspections",

abstract = "Pallet racking is an essential element within warehouses, distribution centers, and manufacturing facilities. To guarantee its safe operation as well as stock protection and personnel safety, pallet racking requires continuous inspections and timely maintenance in the case of damage being discovered. Conventionally, a rack inspection is a manual quality inspection process completed by certified inspectors. The manual process results in operational down-time as well as inspection and certification costs and undiscovered damage due to human error. Inspired by the trend toward smart industrial operations, we present a computer vision-based autonomous rack inspection framework centered around YOLOv7 architecture. Additionally, we propose a domain variance modeling mechanism for addressing the issue of data scarcity through the generation of representative data samples. Our proposed framework achieved a mean average precision of 91.1%.",

keywords = "defect detection, deployment, rack damage, Yolov7, architecture, Machine Learning (ML), Smart manufacturing, Warehouse automation",

author = "Muhammad Hussain and Hussain Al-Aqrabi and Muhammad Munawar and Richard Hill and Tariq Alsboui",

note = "Publisher Copyright: {\textcopyright} 2022 by the authors.",

year = "2022",

month = sep,

day = "13",

doi = "10.3390/s22186927",

language = "English",

volume = "22",

journal = "Sensors",

issn = "1424-3210",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "18",

}

TY - JOUR

T1 - Domain Feature Mapping with YOLOv7 for Automated Edge-Based Pallet Racking Inspections

AU - Hussain, Muhammad

AU - Al-Aqrabi, Hussain

AU - Munawar, Muhammad

AU - Hill, Richard

AU - Alsboui, Tariq

PY - 2022/9/13

Y1 - 2022/9/13

N2 - Pallet racking is an essential element within warehouses, distribution centers, and manufacturing facilities. To guarantee its safe operation as well as stock protection and personnel safety, pallet racking requires continuous inspections and timely maintenance in the case of damage being discovered. Conventionally, a rack inspection is a manual quality inspection process completed by certified inspectors. The manual process results in operational down-time as well as inspection and certification costs and undiscovered damage due to human error. Inspired by the trend toward smart industrial operations, we present a computer vision-based autonomous rack inspection framework centered around YOLOv7 architecture. Additionally, we propose a domain variance modeling mechanism for addressing the issue of data scarcity through the generation of representative data samples. Our proposed framework achieved a mean average precision of 91.1%.

AB - Pallet racking is an essential element within warehouses, distribution centers, and manufacturing facilities. To guarantee its safe operation as well as stock protection and personnel safety, pallet racking requires continuous inspections and timely maintenance in the case of damage being discovered. Conventionally, a rack inspection is a manual quality inspection process completed by certified inspectors. The manual process results in operational down-time as well as inspection and certification costs and undiscovered damage due to human error. Inspired by the trend toward smart industrial operations, we present a computer vision-based autonomous rack inspection framework centered around YOLOv7 architecture. Additionally, we propose a domain variance modeling mechanism for addressing the issue of data scarcity through the generation of representative data samples. Our proposed framework achieved a mean average precision of 91.1%.

KW - defect detection

KW - deployment

KW - rack damage

KW - Yolov7

KW - architecture

KW - Machine Learning (ML)

KW - Smart manufacturing

KW - Warehouse automation

UR - http://www.scopus.com/inward/record.url?scp=85138384912&partnerID=8YFLogxK

U2 - 10.3390/s22186927

DO - 10.3390/s22186927

M3 - Article

C2 - 36146273

VL - 22

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 18

M1 - 6927

ER -

Domain Feature Mapping with YOLOv7 for Automated Edge-Based Pallet Racking Inspections

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Custom Lightweight Convolutional Neural Network Architecture For Automated Detection of Damaged Pallet Racking In Warehousing & Distribution Centers

Feature Mapping for Rice Leaf Defect Detection Based on a Custom Convolutional Architecture

Moving toward Smart Manufacturing with an Autonomous Pallet Racking Inspection System Based on MobileNetV2

Cite this