Cover Image

Object Detection Model Training Framework for Very Small Datasets Applied to Outdoor Industrial Structures

Computer vision; Convolutional neural networks; Deep neural networks; Digital devices; Feature extraction; Image enhancement; Inspection; Object recognition; Convolutional neural network; Deep learning; Detection models; Industrial inspections; Industrial structures; Model training; Objects detectio...

Full description

Saved in:
Bibliographic Details
Main Authors: Baharuddin M.Z., How D.N.T., Sahari K.S.M., Abas A.Z., Ramlee M.K.
Other Authors: 35329255600
Format: Conference Paper
Published: Springer Science and Business Media Deutschland GmbH 2023
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-26439
record_format dspace
spelling my.uniten.dspace-264392023-05-29T17:10:32Z Object Detection Model Training Framework for Very Small Datasets Applied to Outdoor Industrial Structures Baharuddin M.Z. How D.N.T. Sahari K.S.M. Abas A.Z. Ramlee M.K. 35329255600 57212923888 57218170038 57361520800 57361480700 Computer vision; Convolutional neural networks; Deep neural networks; Digital devices; Feature extraction; Image enhancement; Inspection; Object recognition; Convolutional neural network; Deep learning; Detection models; Industrial inspections; Industrial structures; Model training; Objects detection; Retinanet; Small data set; Training framework; Object detection Visual inspection of electrical utility assets is crucial in ensuring the continuous operation of a system or plant. With the advent of digital imagery using mobile devices, it has become easy to collect a vast amount of asset pictures from sites. To further enhance inspection efficiency, we propose RetinaNet, a deep learning-based object detection model that can be trained to automatically detect specific objects and features from images of outdoor industrial structures. The model is capable of detecting features such as intrusions, tree or bushes in the vicinity of the lattice towers. We also introduce a model training framework for use with very small datasets which consists of rigorous data augmentation, image pre-sizing, focal loss function, progressive resizing, learning rate finder, and the Ranger optimizer. Experiment results show that the proposed model used in conjunction with the aforementioned training framework results in the lowest validation loss and highest mean average precision of 31.36 � 2021, Springer Nature Switzerland AG. Final 2023-05-29T09:10:32Z 2023-05-29T09:10:32Z 2021 Conference Paper 10.1007/978-3-030-90235-3_47 2-s2.0-85120535591 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85120535591&doi=10.1007%2f978-3-030-90235-3_47&partnerID=40&md5=79270ebc59d894f4345b18d068536a90 https://irepository.uniten.edu.my/handle/123456789/26439 13051 LNCS 540 551 Springer Science and Business Media Deutschland GmbH Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
description Computer vision; Convolutional neural networks; Deep neural networks; Digital devices; Feature extraction; Image enhancement; Inspection; Object recognition; Convolutional neural network; Deep learning; Detection models; Industrial inspections; Industrial structures; Model training; Objects detection; Retinanet; Small data set; Training framework; Object detection
author2 35329255600
author_facet 35329255600
Baharuddin M.Z.
How D.N.T.
Sahari K.S.M.
Abas A.Z.
Ramlee M.K.
format Conference Paper
author Baharuddin M.Z.
How D.N.T.
Sahari K.S.M.
Abas A.Z.
Ramlee M.K.
spellingShingle Baharuddin M.Z.
How D.N.T.
Sahari K.S.M.
Abas A.Z.
Ramlee M.K.
Object Detection Model Training Framework for Very Small Datasets Applied to Outdoor Industrial Structures
author_sort Baharuddin M.Z.
title Object Detection Model Training Framework for Very Small Datasets Applied to Outdoor Industrial Structures
title_short Object Detection Model Training Framework for Very Small Datasets Applied to Outdoor Industrial Structures
title_full Object Detection Model Training Framework for Very Small Datasets Applied to Outdoor Industrial Structures
title_fullStr Object Detection Model Training Framework for Very Small Datasets Applied to Outdoor Industrial Structures
title_full_unstemmed Object Detection Model Training Framework for Very Small Datasets Applied to Outdoor Industrial Structures
title_sort object detection model training framework for very small datasets applied to outdoor industrial structures
publisher Springer Science and Business Media Deutschland GmbH
publishDate 2023
_version_ 1806425495757127680
score 13.222552

Similar Items