There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.endPage | 635 | - |
dc.citation.number | 8 | - |
dc.citation.startPage | 628 | - |
dc.citation.title | 제어.로봇.시스템학회 논문지 | - |
dc.citation.volume | 29 | - |
dc.contributor.author | 박태욱 | - |
dc.contributor.author | 신희중 | - |
dc.contributor.author | 오현동 | - |
dc.date.accessioned | 2023-12-21T11:47:47Z | - |
dc.date.available | 2023-12-21T11:47:47Z | - |
dc.date.created | 2023-08-24 | - |
dc.date.issued | 2023-08 | - |
dc.description.abstract | Fiducial markers are used to localize camera positions and are widely employed in various fields where fast and highly accurate positioning is required, including AR (Augmented Reality), VR (Virtual Reality), PCB (Printed Circuit Board) design factories, and robot localization research. Over the past 20 years, many fiducial marker designs and detection algorithms have been proposed to improve detection rates, broaden the same marker family, or save computational resources. However, most of these algorithms work well in constrained environments, such as well-lit conditions, minimal motion blur, or no shadows. These limitations can be addressed by using learning-based methods, but they often suffer from high computational loads or the need for collecting training datasets. To overcome these limitations, we introduce a novel fiducial marker detection algorithm along with a neural network compression. By using a feature detection network with a simple circular-shape based fiducial marker, training datasets can be fully synthesized considering real-world noise without the effort of collecting and labeling datasets. Since many fiducial marker applications run on computationally constrained embedded systems, TD (Tensor Decomposition) and QAT (Quantization Aware Training) are applied to the neural network to reduce the number of parameters and improve the inference speed of the network. We demonstrate that our neural network compression approach preserves overall performance while reducing network parameters by 55.48% and accelerating inference speed by 569% on an NVIDIA Jetson Xavier NX. Furthermore, we validate our methods by testing them on real-world images taken by a flying drone. | - |
dc.identifier.bibliographicCitation | 제어.로봇.시스템학회 논문지, v.29, no.8, pp.628 - 635 | - |
dc.identifier.doi | 10.5302/J.ICROS.2023.23.0054 | - |
dc.identifier.issn | 1976-5622 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/65317 | - |
dc.language | 한국어 | - |
dc.publisher | 제어·로봇·시스템학회 | - |
dc.title.alternative | Detection of Fiducial Marker With Neural Network Compression | - |
dc.title | 인공 신경망 경량화 알고리듬을 활용한 마커 인식 연구 | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.identifier.kciid | ART002984821 | - |
dc.description.journalRegisteredClass | scopus | - |
dc.description.journalRegisteredClass | kci | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | computer vision | - |
dc.subject.keywordAuthor | fiducial marker | - |
dc.subject.keywordAuthor | pose estimation | - |
dc.subject.keywordAuthor | neural network quantization | - |
dc.subject.keywordAuthor | neural network compression | - |
dc.subject.keywordAuthor | . | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.