딥러닝 기반의 국토모니터링 웹 서비스 개발
Development of Deep Learning-based Land Monitoring Web Service
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Land monitoring involves systematically understanding changes in land use, leveraging spatial information such as satellite imagery and aerial photographs. Recently, the integration of deep learning technologies, notably object detection and semantic segmentation, into land monitoring has spurred active research. This study developed a web service to facilitate such integrations, allowing users to analyze aerial and drone images using CNN models. The web service architecture comprises AI, WEB/WAS, and DB servers and employs three primary deep learning models: DeepLab V3, YOLO, and Rotated Mask R-CNN. Specifically, YOLO offers rapid detection capabilities, Rotated Mask R-CNN excels in detecting rotated objects, while DeepLab V3 provides pixel-wise image classification. The performance of these models fluctuates depending on the quantity and quality of the training data. Anticipated to be integrated into the LX Corporation's operational network and the Land-XI system, this service is expected to enhance the accuracy and efficiency of land monitoring.
Abstract
Land monitoring involves systematically understanding changes in land use, leveraging spatial information such as satellite imagery and aerial photographs. Recently, the integration of deep learning technologies, notably object detection and semantic segmentation, into land monitoring has spurred active research. This study developed a web service to facilitate such integrations, allowing users to analyze aerial and drone images using CNN models. The web service architecture comprises AI, WEB/WAS, and DB servers and employs three primary deep learning models: DeepLab V3, YOLO, and Rotated Mask R-CNN. Specifically, YOLO offers rapid detection capabilities, Rotated Mask R-CNN excels in detecting rotated objects, while DeepLab V3 provides pixel-wise image classification. The performance of these models fluctuates depending on the quantity and quality of the training data. Anticipated to be integrated into the LX Corporation's operational network and the Land-XI system, this service is expected to enhance the accuracy and efficiency of land monitoring.
참고문헌 (14)
- "AI hub"[URL]
- Chen, L. C., "Rethinking Atrous Convolution for Semantic Image Segmentation", arXiv Pre-print, 2017, arXiv:1706.05587, ~ (2017)
- 하종우, "딥러닝 기반의 분할과 객체탐지를 활용한 도로균열 탐지시스템 개발", 한국전자거래학회지, 26(1), pp.93~106 (2021), 한국전자거래학회[DOI]
- A Study on the Implementation Plan of National Land using Survey for LX Future Business Model Discovery, "Jeon, J. B.", LX Spatial Information Research Institute, ~ (2020)
- 조원호, "U-Net을 이용한 딥러닝 기반의 토지피복 변화탐지", 대한지리학회지, 57(3), pp.297~306 (2022), 대한지리학회[DOI]
- Kornienko, D. V., "Principles of Securing RESTful API Web Services Developed with Python Frameworks", Journal of Physics: Conference Series, 2094(3), pp.032016~ (2021), IOP Publishing
- A Study on Monitoring for Restricted Development Zone, "Lee, J. H.", LX Spatial Information Research Institute, ~ (2020)
- 모준상, "항공영상을 이용한 딥러닝 기반 건물객체 추출 기법들의 비교평가", 한국측량학회지, 39(3), pp.157~165 (2021), 한국측량학회[DOI]
- Pack, H. J., "A Study on Implementation of Web-based Machine Learning Platform and Applications", pp.2020
- 박상철, "YOLO 알고리즘 기반 국토위성영상의 선박 모니터링 가능성 평가 연구: 부산 신항과 캘리포니아 오클랜드항을 대상으로", 대한원격탐사학회지, 38(6), pp.1463~1478 (2022), 대한원격탐사학회
- Redmon, J., "You Only Look Once: Unified, Real-Time Object Detection", arXiv Pre-print, 2015, arXiv:1506.02640, ~ (2015)
- Wang, P., "Enhanced Rotated Mask R-CNN for Chromo-some Segmentation", 43rd Annual International Confer-ence of the IEEE Engineering in Medicine & Biology Society (EMBC), pp.2769~2772 (2021)
- 유정상, "스프링 프레임워크 환경에서 스프링 데이터 JPA기반의 엔터프라이즈 시스템 플랫폼의 설계", 융합정보논문지, 9(12), pp.39~46 (2019), 중소기업융합학회[DOI]
- Zhang, F., "Design and Implementation of Energy Management System Based on Spring Boot Framework", Information, 12(11), pp.457~ (2021)