KEYWORDS: Image segmentation, Data modeling, Semantics, Transformers, Deep learning, Education and training, Image enhancement, Cultural heritage, Convolution
Moss can cause significant damages to stone artifacts. In order to effectively protect stone artifacts, it is crucial to accurately obtain information about the moss growth on the surface of the stone artifacts. In response to the laborious and inefficient process of manually detecting moss coverage on stone artifacts, this paper introduces an enhanced semantic segmentation model that integrates Swin Transformer and convolutional neural networks to accurately detect the moss coverage and growth rate. Through a comparison with current state-of-the-art models, our model outperforms them by the average intersection over union on the LoveDA and moss datasets, reaching a result of 94.79%. on the moss dataset. This indicates that our model can accurately segment rocks and moss, and thus enabling the effective calculation of moss coverage and growth rate on stone artifacts and providing vital support for their preventive protection.
FBG is used to construct pH and strain fiber optic sensors to realize online detection of oxalic acid corrosion process of sandstone artifacts. The pH fiber optic sensor uses a PVA/PAA hydrogel as the sensitive material and the fiber optic is held in a half-open PTFE tube by a UV adhesive. The de-coated FBG is fixed to the surface of the relics with epoxy resin to detect strain in the relics. The research results of this paper will provide an important reference for analyzing the acid dissolution corrosion mechanism of stone cultural relics and preventive protection of cultural relics, and promote the scientific and technological development and engineering application of physicochemical FBG sensors.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.