Construction of the Invasive Alien Plants Distribution Using Drone and Image Learning (드론과 이미지 학습을 이용한 생태계 교란 식물 분포도 구축 방안 연구)

Dongwoo Kim (김동우); Daeyong Jin (진대용); Yong Myong Song (송영명); Son Seungwoo (손승우); Jeongho Yoon (윤정호); Geunhan Kim (김근한)

doi:10.25202/JAKG.9.1.7

Construction of the Invasive Alien Plants Distribution Using Drone and Image Learning

Journal of the Association of Korean Geographers
Abbr : JAKG
2020, 9(1), pp.103-114
DOI : 10.25202/JAKG.9.1.7
Publisher : Association of Korean Geographers
Research Area : Social Science > Geography
Received : November 27, 2019
Accepted : March 24, 2020
Published : April 30, 2020

Dongwoo Kim ¹, Daeyong Jin ¹, Yong Myong Song ², Son Seungwoo ¹, Jeongho Yoon ¹, Geunhan Kim ¹

¹한국환경정책·평가연구원
²내가시스템 기술연구소

Accredited

ABSTRACT

The invasive alien plants that cause ecological, economic, and public health disturbances are highly reproductive and thus must be controlled at the early stage of development. This study is intended to establish the system to construct the invasive alien plant distribution map based on spatial DBMS (Database Management System), obtain ortho-images using drones, classify invasive alien plants using CNN (Convolution Neural Network)-based image learning, and present how to generate the invasive alien plant distribution map using them. We obtained ortho-images by photographing the area where Sicyos angulatus, one of the invasive alien plants, inhabited in two test areas of Daejeon to examine the applicability of this system. In the first experiment, we conducted the image learning and classification using only the images photographed in test area a. In the second experiment, we conducted the image learning using the image photographed in test area a and classified the images photographed in test area b. In the last experiment, we conducted learning using the images photographed in test area a and the imagse of Sicyos angulatus on web sites and classified the image photographed in test area b. The analysis results showed the average classification accuracy of 95%, 45%, and 61% in the first experiment, the second experiment, and the third experiment, respectively. Construction of the distribution map of invasive alien plants requires the metatable of the ortho-images that contain various invasive alien plants. Additional information on the search targets of invasive alien plants in consideration of the expansion of new invasive alien plants can help to manage them with the spatial DBMS and carry out the automated classification of various invasive alien plants and to manage various ecosystem disturbances. Using them in the analysis system would help control invasive alien plants.

KEYWORDS

Invasive alien plant, Image learning, CNN (Convolution Neural Network), Drone, Spatial DBMS (Database Management System)

Citation status

* References for papers published after 2023 are currently being built.

[journal] 김근한 / 2016 / Providing Service Model Based on Concept and Requirements of Spatial Big Data / 대한공간정보학회지 / 대한공간정보학회 24(4) : 89~96

[journal] 김동우 / 2019 / Analysis of Urban Surface Temperature Change during Heat Wave Using UAV Thermal Infrared Camera / 한국지리학회지 / 한국지리학회 8(1) : 47~60

[journal] 박상헌 / 2018 / A Study on Management and Present-Condition of Invasive Alien Species / 한국산학기술학회논문지 / 한국산학기술학회 19(11) : 488~496

[journal] 손승우 / 2017 / Investigation of Measurement Feasibility of Large-size Wastes Based on Unmanned Aerial System / 대한원격탐사학회지 / 대한원격탐사학회 33(5) : 809~820

[journal] 이근상 / 2017 / Identification of Aquatic Plants in the Muncheon Water Reservoir Using Drone-based Information / 한국환경과학회지 / 한국환경과학회 26(5) : 685~689

[journal] 임종환 / 2017 / An Analysis of the Hail Damages to Korean Forests in 2017 by Meteorology, Species and Topography / 한국농림기상학회지 / 한국농림기상학회 19(4) : 280~292

[report] 한국환경정책･평가연구원 / 2011 / 외래종 생태계위해 관리 기본계획 수립 연구 / 한국환경정책･평가연구원

[report] 한국환경정책･평가연구원 / 2018 / 토지피복지도와 국토환경성평가지도의 정책적 활용 기반 마련 연구 / 한국환경정책･평가연구원

[other] 환경부 / 2018 / 생물다양성 보전 및 이용에 관한 법률(2018년10월 16일 일부개정)

[journal] Araújo, T. / 2017 / Classification of breast cancer histology images using convolutional neural networks / PloS ONE 12(6)

[web] Deshpande, A. / 2016 / A beginner's guide to understanding convolutional neural networks / https://adeshpande3.github.io/A-Beginner%27s-Guide-To-Understanding-Convolutional-Neural-Networks

[journal] Grinblat, G. L. / 2016 / Deep learning for plant identification using vein morphological patterns / Computers and Electronics in Agriculture 127 : 418~424

[journal] Norouzzadeh, M. S. / 2018 / Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning / Proceedings of the National Academy of Sciences of the United States of America 115(25) : E5716~E5725

[journal] Sandino, J. / 2018 / UAVs and machine learning revolutionising invasive grass and vegetation surveys in remote arid lands / Sensors 18(2) : 605~

[journal] Vahdatpour, M. S. / 2018 / Air pollution forecasting from sky images with shallow and deep classifiers / Earth Science Informatics 11(3) : 413~422

[journal] Wang, Y. / 2019 / Automatic detection of individual oil palm trees from UAV images using HOG features and an SVM classifier / International Journal of Remote Sensing : Oil Palms 40(19) : 7356~7370

[web] / 법제처 국가법령정보센터 / www.law.go.kr

KJCKorea
Journal Central

Journal of the Association of Korean Geographers 2023 KCI Impact Factor : 1.35

Construction of the Invasive Alien Plants Distribution Using Drone and Image Learning

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of the Association of Korean Geographers 2023 KCI Impact Factor : 1.35

Construction of the Invasive Alien Plants Distribution Using Drone and Image Learning

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (4)

REFERENCES (17) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.