Semantic segmentation, a fundamental task in remote sensing, plays a crucial role in urban planning, land monitoring, and road vehicle detection. However, compared to conventional images, multispectral remote sensing images present significant challenges due to large-scale variations, multiple bands, and complex details. These challenges manifest in three major issues: low cross-scale object segmentation accuracy, confusion between band information, and difficulties in balancing local and global information. Recognizing that traditional remote sensing indices, such as the Normalized Difference Vegetation Index and the water body index, reveal unique semantic information in specific bands, this paper proposes a feature-decoupling-based pseudo-Siamese semantic segmentation architecture. To evaluate the effectiveness and robustness of the proposed algorithm, comparative experiments were conducted on the Suichang Spatial Remote Sensing Dataset and the Potsdam-S Aerial Remote Sensing Dataset. The results demonstrate that the proposed algorithm outperforms all comparison methods, with average accuracy improvements of 80.719% and 77.856% on the Suichang and Potsdam datasets, respectively.
31 August 2023 in Journal of MICE & Tourism Research
This study was conducted to provide basic data for preparing a development policy for the exhibition and convention industry in the future by empirically analyzing the current status of exhibition and convention holding, regional distribution, and operation status. From 2012 to 2019, China's exhibition and convention industry experienced continuous quantitative growth at an average annual rate of 8-10 % in terms of the total number of exhibitions and conventions, total exhibition area, and total quantity. However, 70% of the exhibition convention centers were distributed among the seven major regions of China, mainly in Hwadong, Hwanam, and Hwabuk. In addition, the operation rate of the exhibition and convention center was above 50% for the top seven, which was less than 2% of the total. Since 2020, due to the COVID-19 pandemic, online exhibition conventions have become an opportunity to emerge with an 11% share of the total.
Distributed fiber optic sensing technology is based on Raman scattering and optical time-domain reflection technologies, and consists of two parts: the demodulation host and the fiber optic cable. The system obtains the structural changes of the building through the sensing fiber optic cable, such as sensing the strain, crack, tilt, settlement and other specific changes of the dam and other buildings. By calculating the structural safety condition of the building, the system determines the structural safety level of the dam and other buildings according to the judgment standard of structural safety of the dam and other buildings and the subsequent treatment and remedial measures. Realize the long-term online monitoring of the structural safety of dams and other buildings, and provide long-term sustainable structural safety guarantee for dams and other buildings.