Experiments of Individual Tree and Crown Width Extraction by Band Combination Using Monthly Drone Images

Lim, Ye Seul; Eo, Yang Dam; Jeon, Min Cheol; Lee, Mi Hee; Pyeon, Mu Wook

doi:10.7319/kogsis.2016.24.4.067

Cited by 3 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…드론영상과 인공지능학습을 이용한 산불연료 모니터링 연구가 대표적 이며, 제거목 공간 분석 및 선별 등 산불피해저감을 위한 산불연료관리 의사결정시스템 개발 연구가 이루어지고 있 다 (Cruz et al, 2002;David, 2010). 한편, 국내에서는 산림공 간분석, 수종분류 등 산림정보 자료 구축을 위한 기초적인 연구는 간헐적으로 수행되고 있으나 (Lim et al, 2016;Park and Jang, 2018;Kim and Kwon, 2020) (Jan et al, 2017;Pabi et al, 2020;Kim et al, 2021). 본 연구결과와 비교해 봤을 때, 대조구 임분은 기존 선행연구결과 평균 수고 오차 대비 최대 157% 높은 오차율을 보인 반면, 간벌 40% 시험구는 기존 선행연구결과 대비 최대 50% 낮은 오차 율을 보였다.…”

Section: 서 론unclassified

Drone-Image-Based Method of Estimating Forest-Fire Fuel Loads

Lee¹,

Woo²,

Kim³

et al. 2021

J. Korean Soc. Hazard Mitig

View full text Add to dashboard Cite

A method of estimating forest-fire fuel loads was developed using drones to collect information about the height and diameter-at-breast-height (DBH) of individual trees. It was conducted for forest fire prevention monitoring (Control, 20% thinned, and 40% thinned area) located in Goseong-gun, Gangwon-do. Object-based images and 3D-model red/green/blue band characteristics were superimposed to select and extract individual trees. A digital crown height model was developed based on the difference between the heights of digital surface and terrain models. In addition, the DBH was estimated based on the crown area. The 40%-thinned area exhibited the highest accuracy (95%) for extracting individual trees, and the difference between the field-survey and drone-image heights was in the range of 0.64-2.02 m. The goodness-of-fit of the DBH-crown area model was 0.61. The difference between the imageand field-survey-based forest-fire fuel loads ranged from -1.20 to 0.40 ton/ha.

show abstract

Section: 서 론unclassified