https://scholar.dgist.ac.kr/handle/20.500.11750/145 2026-04-05T01:44:10Z 2026-04-05T01:44:10Z Lee, Kyungsu Kim, Jun Hee Lee, Haeyun Park, Juhum Choi, Jihwan P. Hwang, Jae Youn https://scholar.dgist.ac.kr/handle/20.500.11750/15601 2025-07-25T03:31:13Z 2021-12-31T15:00:00Z

Title: Boundary-Oriented Binary Building Segmentation Model With Two Scheme Learning for Aerial Images Author(s): Lee, Kyungsu; Kim, Jun Hee; Lee, Haeyun; Park, Juhum; Choi, Jihwan P.; Hwang, Jae Youn Abstract: Various deep learning-based segmentation models have been developed to segment buildings in aerial images. However, the segmentation maps predicted by the conventional convolutional neural network-based methods cannot accurately determine the shapes and boundaries of segmented buildings. In this article, to improve the prediction accuracy for the boundaries and shapes of segmented buildings in aerial images, we propose the boundary-oriented binary building segmentation model (B3SM). To construct the B3SM for boundary-enhanced semantic segmentation, we present two-scheme learning (Schemes I and II), which uses the upsampling interpolation method (USIM) as a new operator and a boundary-oriented loss function (B-Loss). In Scheme I, a raw input image is processed and transformed into a presegmented map. In Scheme II, the presegmented map from Scheme I is transformed into a more fine-grained representation. To connect these two schemes, we use the USIM operator. In addition, the novel B-Loss function is implemented in B3SM to extract the features of the boundaries of buildings effectively. To perform quantitative evaluation of the shapes and boundaries of segmented buildings generated by B3SM, we develop a new metric called the boundary-oriented intersection over union (B-IoU). After evaluating the effectiveness of two-scheme learning, USIM, and B-Loss for building segmentation, we compare the performance of B3SM to those of other state-of-the-art methods using public and custom datasets. The experimental results demonstrate that the B3SM outperforms other state-of-the-art models, resulting in more accurate shapes and boundaries for segmented buildings in aerial images. IEEE

2021-12-31T15:00:00Z Lee, Yonghwa Choi, Jihwan P. https://scholar.dgist.ac.kr/handle/20.500.11750/15592 2025-07-25T02:35:24Z 2021-11-30T15:00:00Z

Title: Connectivity Analysis of Mega Constellation Satellite Networks with Optical Inter-Satellite Links Author(s): Lee, Yonghwa; Choi, Jihwan P. Abstract: Recently, low earth orbit (LEO) satellite-based systems have attracted tremendous attention and various technologies have been developed for payload miniaturization and optical communications. In addition, mega-constellation architectures are expected to be deployed with LEO satellites for global broadband networks. In this article, we present a thorough analysis of mega-constellation architecture in terms of a change in the number of visible satellites and antenna steering capability to investigate the impact of increase in the constellation size and adoption of optical intersatellite links. The network architecture is evaluated with respect to satellite antenna steering capability and the satellite visibility considering the very narrow beam divergence of optical communications. We analyze the impact of a change in relative positions among the satellites due to continuous satellite movement in the constellation. The results offer guidelines for designing a novel visibility matrix using a time-varying satellite topology. This could defuse the problem of the conventional studies using fixed visibility matrices. The proposed time-varying visibility matrix achieves better performance than the previous preassigned links in terms of end-to-end link distance and hop count of LEO satellite networks. © 1965-2011 IEEE.

2021-11-30T15:00:00Z Jung, Seunghwa Choi, Jihwan P. https://scholar.dgist.ac.kr/handle/20.500.11750/13477 2025-07-25T03:32:57Z 2021-05-31T15:00:00Z

Title: Reliability of Small Satellite Networks with Software-Defined Radio and Enhanced Multiple Access Protocol Author(s): Jung, Seunghwa; Choi, Jihwan P. Abstract: Space missions exploiting small satellite networks with a use of software-defined radio (SDR) and advanced random access (RA) protocols have attracted an increased amount of attentions given their low costs, low latency levels, low complexity, and yet competitive data rates for global network services. In this paper, we derive a mathematical model to demonstrate the reliability of a small satellite network with respect to SDR structures, the transmitted signal power on the uplink/downlink channels, code rates, and packet collisions through an enhanced RA protocol. Our model provides quantitative network reliability with respect to SDR system failure rates, feasible communication parameters and packet loss ratios (PLRs). Our analysis suggests a methodology to evaluate network reliability differences according to changes of communication parameters, and a guideline to sustain a reliable network system with appropriate parameter values. We find out that a robust SDR structure with a state-of-the-art analog-to-digital converter (ADC) can provide reliable network services effectively with reduced power consumption, even with high packet traffic loads, to meet operator-required reliability levels for small satellite networks. IEEE

2021-05-31T15:00:00Z Jung, Seunghwa Choi, Jihwan P. https://scholar.dgist.ac.kr/handle/20.500.11750/12938 2025-07-25T02:34:53Z 2021-02-28T15:00:00Z

Title: End-To-End Reliability of Satellite Communication Network Systems Author(s): Jung, Seunghwa; Choi, Jihwan P. Abstract: Satellite communication networks with onboard processing (OBP) satellites can provide high-speed data transmission rates and global service coverage with reduced propagation delays. This article proposes a means of analyzing the quantitative reliability of the satellite communication network systems. First, we identify the four major factors that affect the quality of network services: the OBP states, uplink channels, downlink channels, and uplink packet collision losses. Based on these four factors, a Markov model is derived to analyze the probability distributions of various network states. Analytic results show the network reliability with respect to the OBP structures and space radiation environments. The relationship between network reliability and throughput according to the packet traffic load is also quantitatively analyzed. Finally, based on the developed model, a method is suggested for iteratively updating the reliability distribution of network systems affected by changes in the four factors as well as network access time changes. The numerical results show an indication of the satellite network reliability to provide references whether adjusted elements of the four factors are eligible to sustain reliable end-to-end services.

2021-02-28T15:00:00Z