딥러닝 신경망 기술을 중심으로 한 국내외 스마트 농업 현황 분석
Analysis of Domestic and Overseas Smart Agriculture Status Focusing on Deep Learning Neural Network Technology
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
한국 농촌의 인구 감소에 따른 공동화와 고령화는 농업 생산성을 크게 떨어뜨리며 국가 경제의 큰 부담으로 작용하고 있다. 이에 정부는 스마트 기술을 접목한 기술 혁신으로 농촌의 고질적인 인력 부족 현상을 해소하고 고부가가치 농업으로의 변신을 꾀하고 있으나 기대하는 성과를 내고 있지 못하는 실정이다. 이러한 현상의 저변에는 다양한 원인이 있지만 한국 실정에 맞는 스마트 팜 발전 방안의 부재를 꼽을 수 있다. 본 논문에서는 한국의 미래 농업이 AI 기반의 무인 자동화를 지향한다고 보고 딥러닝 기술 중심의 국내외 스마트팜 기술 현황을 살펴보았다. 그 결과 질병 검출, 작물 분류, 에너지 절감 등을 목적으로 딥러닝 분석 기술이 효과적으로 적용되고 있고 한국 농업에도 시사하는 바가 큼을 확인할 수 있었다. 덧붙여 한국 정부의 스마트팜 육성 노력에도 불구하고 만족스런 상황을 만들지 못하는 원인과 문제점을 분석하였다. 본 논문에서는 이러한 현황 분석을 거쳐서 한국의 스마트팜 추진의 문제점을 열거하고 한국의 미래 농업을 위한 스마트팜 발전 방안을 제안하고자 한다.
Abstract
The hollowing out and aging of Korea's rural areas due to population decline are greatly reducing agricultural productivity and are acting as a major burden on the national economy. Accordingly, Korean government is attempting to resolve the chronic manpower shortage in rural areas and transform it into high-value-added agriculture through technological innovation incorporating smart technology, but the expected results are not being achieved. There are various causes underlying this phenomenon, but one possible reason is the absence of a smart farm development plan suited to Korea's circumstances. In this paper, we believe that Korea's future agriculture is aimed at AI-based unmanned automation and examine the current status of domestic and overseas smart farm technology centered on deep learning technology. As a result, it was confirmed that deep learning analysis technology is being effectively applied for the purposes of disease detection, crop classification, and energy saving, and has significant implications for Korean agriculture. In addition, we analyzed the causes and problems that failed to create a satisfactory situation despite the Korean government's efforts to foster smart farms. In this paper, after analyzing the current situation, we will list the problems of Korea's smart farm promotion and propose smart farm development plans for Korea's future agriculture.
참고문헌 (37)
- "Research on ways to foster smart agriculture" (2020)[URL]
- "Measures to strengthen farmers’ capabilities in response to the spread of smart agriculture" (2022)[URL]
- "Promotion and information service in food, agriculture, forestry and fisheries (EPIS)" (2023)[URL]
- A plan to establish precision agricultural system to enhance agricultural competitiveness ,isbn={9791161494197}, "Korea Rural Economic Institute", KREI, ~, pp.KREI Research Report R904 (2020)
- S. O'Shaughnessy, "Towards smart farming solutions in the U.S. and South Korea: A comparison of the current status", Journal of Geography and Sustainability, 2(4), pp.312~327 (2021)[DOI]
- D. Shon, "Characteristics of smart farms for architectural planning and design", J, of Buildings, 13(93) (2023)[DOI]
- Y. Akkem, "Smart farming monitoring using ML and MLOps", International Conference on Innovative Computing and Communications, Lecture Notes in Networks and System, 703, pp.665~667 (2023)
- "Introduction to smart farm"[URL]
- Analysis on the status and future development of Smart Farming projects, "National Assembly Budget Office of Korea", ~ (2022)
- "Results of the 2022agriculture, forestry and fisheries survey" (2022)[URL]
- "Benefits and evolution of precision agriculture" (2023)[URL]
- "Precision agriculture definition" (2023)[URL]
- "Precision agriculture" (2023)[URL]
- "GIS in agriculture – Two important uses" (2023)[URL]
- Current status and challenges of smart farm expansion and distribution projects – Focusing on ICT convergence projects in the agricultural field, "National Assembly Research Service (NARS)of Korea", ~, pp.NARS Analysis of Current Issues, No. 95 (2019)
- "The International Information Center for Civil Engineers" (2023)[URL]
- S. Haug, "A crop", weed field image dataset for the evaluation of computer vision based precision agriculture tasks, 2014, 105~116
- A. Sharma, "Machine learning applications for precision agriculture: A comprehensive review", IEEE Access, pp.4843~4873 (2020)
- M. Altalak, "Smart Agriculture applications using deep learning technologies: a survey", Applied Sciences, 12(12), pp.5919~ (2022)[DOI]
- M. H. Saleem, "Plant disease detection and classification by deep learning", Plants, 8(11), pp.468~ (2019)
- J. Amara, "datenbanksysteme für business, technologie und web, Lecture Notes in Informatics (LNI)", pp.79~88 (2017), Gesellschaft für Informatik
- D. Wang, "Early detection of tomato spotted wilt virus by hyperspectral imaging and outlier removal auxiliary classifier generative adversarial nets (OR-AC-GAN)", Sci Rep, 9, pp.4377~ (2019)
- M. Dipali, "Automation and integration of growth monitoring in plants (with disease prediction) and crop prediction", Mater. Today Proc, 43, pp.3922~3927 (2021)
- A. Brilhador, "Classification of weeds and crops at the pixel-level using convolutional neural networks and data augmentation", 2019 IEEE Latin American Conference on Computational Intelligence (LA-CCI), pp.1~6 (2019)
- M. Dyrmann, "Pixel-wise classification of weeds and crops in images by using a fully convolutional neural network", CIGR-AgEng conference (2016)
- N. Kussul, "Deep learning classification of land cover and crop types using remote sensing data", IEEE Geoscience and Remote Sensing Letters, 14(5), pp.778~782 (2017)
- H. Shin, "Intelligent Green house control system based on deep learning for saving electric power consumption", Journal of IKEEE, 22(1), pp.53~60 (2018)
- K. Ko, "Real-time tomato instance tracking algorithm by using deep learning and probability model", Journal of Korea Robotics Society, 16(1), pp.49~55 (2021)
- J. Bang, "A system for determining the growth stage of fruit tree using a deep learning-based object detection model", Smart Media Journal, 11(4) (2022)
- M. Oquab, "Learning and transferring mid-level image representations using convolutional neural networks", 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp.1717~1724 (2014)
- Z. Yao, "Optimal control based on temperature dynamic model of greenhouse crop germination period", ICICIP, pp.267~270 (2013)
- J. Jeong, "Automated operation algorithm for reducing power consumption and gaining benefit in smart farm environment with energy storage system", The Journal of Korean Institute of Communications and Information Sciences, 45(10) (2020)
- M. Choi, "Smart farm control system for improving energy efficiency", Journal of Digital Convergence, 19(12), pp.331~337 (2021)
- "Roboflow 100: A rich, multi-domain object detection benchmark" (2022)[URL]
- "The PASCAL visual object classes homepage" (2012)[URL]
- Smart agriculture, "KISTEP", Korea Institute of S&T Evaluation and Planning, ~, pp.KISTEP Technology Trend Brief, No. 2021-03 (2021)