제 2 발표장 / 농업 환경 및 시설 분야 , 농산물 및 식품가공기계 분야 : 식물공장용 포트묘 보식 시스템 개발

류찬석(C . S . Ryu),류관희(K . H . Ryu),한재성(J . S . Han),김기영(G . Y . Kim) 한국농업기계학회 2000 한국농업기계학회 학술발표논문집 Vol.5 No.1

메탄발효 소화액 시용이 벼 생육과 식미에 미치는 영향

류찬석 ( C. S. Ryu ),이충근 ( C. K. Lee ),우메다미키오 ( M. Umeda ),이승규 ( S. K. Lee ) 한국농업기계학회 2009 바이오시스템공학 Vol.34 No.4

메탄발효소화액의 보급을 위한 데이터베이스 구축 및 분석

류찬석 ( C. S. Ryu ),수구리마사히코 ( M. Suguri ),이이다미치히사 ( M. Iida ),우메다미키오 ( M. Umeda ) 한국농업기계학회 2011 한국농업기계학회 학술발표논문집 Vol.16 No.1

하이퍼스펙트럴카메라를 이용한 녹차의 카테킨함유량 추정

류찬석 ( C. S. Ryu ),수구리마사히코 ( M. Suguri ),우메다미키오 ( M. Umeda ) 한국농업기계학회 2011 한국농업기계학회 학술발표논문집 Vol.16 No.1

무인기로 취득한 RGB 영상과 YOLOv5를 이용한 수수 이삭 탐지

박민준,류찬석,강예성,송혜영,백현찬,박기수,김은리,박 진기,장시형 한국농림기상학회 2022 한국농림기상학회지 Vol.24 No.4

The purpose of this study is to detect the sorghum panicle using YOLOv5 based on RGB images acquired by a unmanned aerial vehicle (UAV) system. The high-resolution images acquired using the RGB camera mounted in the UAV on September 2, 2022 were split into 512×512 size for YOLOv5 analysis. Sorghum panicles were labeled as bounding boxes in the split image. 2,000images of 512×512 size were divided at a ratio of 6:2:2 and used to train, validate, and test the YOLOv5 model, respectively. When learning with YOLOv5s, which has the fewest parameters among YOLOv5 models, sorghum panicles were detected with mAP@50=0.845. In YOLOv5m with more parameters, sorghum panicles could be detected with mAP@50=0.844. Although the performance of the two models is similar, YOLOv5s (4 hours 35 minutes) has a faster training time than YOLOv5m (5 hours 15 minutes). Therefore, in terms of time cost, developing the YOLOv5s model was considered more efficient for detecting sorghum panicles. As an important step in predicting sorghum yield, a technique for detecting sorghum panicles using high-resolution RGB images and the YOLOv5 model was presented. 본 연구는 수수의 수확량 추정을 위해 무인기로 취득한 RGB 영상과 YOLOv5를 이용하여 수수 이삭 탐지 모델을 개발하였다. 이삭이 가장 잘 식별되는 9월 2일의 영상 중 512×512로 분할된 2000장을 이용하여 모델의 학습, 검증 및 테스트하였다. YOLOv5의 모델 중 가장 파라미터가 적은 YOLOv5s에서 mAP@50=0.845로 수수 이삭을 탐지할 수 있었다. 파라미터가 증가한 YOLOv5m에서는 mAP@50=0.844로 수수 이삭을 탐지할 수 있었다. 두 모델의 성능이 유사하나 YOLOv5s (4시간 35분)가 YOLOv5m (5시간 15분)보다 훈련시간이 더 빨라 YOLOv5s가 수수 이삭 탐지에 효율적이라고 판단된다. 개발된 모델을 이용하여 수수의 수확량 예측을 위한 단위면적당 이삭 수를 추정하는 알고리즘의 기초자료로 유용하게 활용될 것으로 판단된다. 추가적으로 아직 개발의 초기 단계를 감안하면 확보된 데이터를 이용하여 성능 개선 및 다른 CNN 모델과 비교 검토할 필요가 있다고 사료된다.

Yield Prediction of Chinese Cabbage (Brassicaceae) Using Broadband Multispectral Imagery Mounted Unmanned Aerial System in the Air and Narrowband Hyperspectral Imagery on the Ground

강예성,류찬석,김성헌,전새롬,장시형,박준우,Tapash Kumar Sarkar,송혜영 한국농업기계학회 2018 바이오시스템공학 Vol.43 No.2

Purpose: A narrowband hyperspectral imaging sensor of high-dimensional spectral bands is advantageous for identifying the reflectance by selecting the significant spectral bands for predicting crop yield over the broadband multispectral imaging sensor for each wavelength range of the crop canopy. The images acquired by each imaging sensor were used to develop the models for predicting the Chinese cabbage yield. Methods: The models for predicting the Chinese cabbage (Brassica campestris L.) yield, with multispectral images based on unmanned aerial vehicle (UAV), were developed by simple linear regression (SLR) using vegetation indices, and forward stepwise multiple linear regression (MLR) using four spectral bands. The model with hyperspectral images based on the ground were developed using forward stepwise MLR from the significant spectral bands selected by dimension reduction methods based on a partial least squares regression (PLSR) model of high precision and accuracy. Results: The SLR model by the multispectral image cannot predict the yield well because of its low sensitivity in high fresh weight. Despite improved sensitivity in high fresh weight of the MLR model, its precision and accuracy was unsuitable for predicting the yield as its R2 is 0.697, root-mean-square error (RMSE) is 1170 g/plant, relative error (RE) is 67.1%. When selecting the significant spectral bands for predicting the yield using hyperspectral images, the MLR model using four spectral bands show high precision and accuracy, with 0.891 for R2, 616 g/plant for the RMSE, and 35.3% for the RE. Conclusions: Little difference was observed in the precision and accuracy of the PLSR model of 0.896 for R2, 576.7 g/plant for the RMSE, and 33.1% for the RE, compared with the MLR model. If the multispectral imaging sensor composed of the significant spectral bands is produced, the crop yield of a wide area can be predicted using a UAV.

Estimating Moisture Content of Cucumber Seedling Using Hyperspectral Imagery

강정균,류찬석,김성훈,강예성,Tapash Kumar Sarkar,강동현,김동억,구양규 한국농업기계학회 2016 바이오시스템공학 Vol.41 No.3

Purpose: This experiment was conducted to detect water stress in terms of the moisture content of cucumber seedlings under water stress condition using a hyperspectral image acquisition system, linear regression analysis, and partial least square regression (PLSR) to achieve a non-destructive measurement procedure. Methods: Changes in the reflectance spectrum of cucumber seedlings under water stress were measured using hyperspectral imaging techniques. A model for estimating moisture content of cucumber seedlings was constructed through a linear regression analysis that used the moisture content of cucumber seedlings and a normalized difference vegetation index (NDVI). A model using PLSR that used the moisture content of cucumber seedlings and reflectance spectrum was also created. Results: In the early stages of water stress, cucumber seedlings recovered completely when sub-irrigation was applied. However, the seedlings suffering from initial wilting did not recover when more than 42 h passed without irrigation. The reflectance spectrum of seedlings under water stress decreased gradually, but increased when irrigation was provided, except for the seedlings that had permanently wilted. From the results of the linear regression analysis using the NDVI, the model excluding wilted seedlings with less than 20% (n=97) moisture content showed a precision (R² and R²a) of 0.573 and 0.568, respectively, and accuracy (RE) of 4.138% and 4.138%, which was higher than that for models including all seedlings (n=100). For PLS regression analysis using the reflectance spectrum, both models were found to have strong precision (R²) with a rating of 0.822, but accuracy (RMSE and RE) was higher in the model excluding wilted seedlings as 5.544% and 13.65% respectively. Conclusions: The estimation model of the moisture content of cucumber seedlings showed better results in the PLSR analysis using reflectance spectrum than the linear regression analysis using NDVI.

초분광 영상을 이용한 의사결정 트리 기반 봄감자(Solanum tuberosum)의 염해 판별

강경석,류찬석,장시형,강예성,전새롬,박준우,송혜영,이수환 한국농림기상학회 2019 한국농림기상학회지 Vol.21 No.4

Salinity which is often detected on reclaimed land is a major detrimental factor to crop growth. It would be advantageous to develop an approach for assessment of salinity and drought damages using a non-destructive method in a large landfills area. The objective of this study was to examine applicability of the decision tree classifier using imagery for classifying for spring potatoes (Solanum tuberosum) damaged by salinity or drought at vegetation growth stages. We focused on comparing the accuracies of OA (Overall accuracy) and KC (Kappa coefficient) between the simple reflectance and the band ratios minimizing the effect on the light unevenness. Spectral merging based on the commercial band width with full width at half maximum (FWHM) such as 10 nm, 25 nm, and 50 nm was also considered to invent the multispectral image sensor. In the case of the classification based on original simple reflectance with 5 nm of FWHM, the selected bands ranged from 3-13 bands with the accuracy of less than 66.7% of OA and 40.8% of KC in all FWHMs. The maximum values of OA and KC values were 78.7% and 57.7%, respectively, with 10 nm of FWHM to classify salinity and drought damages of spring potato. When the classifier was built based on the band ratios, the accuracy was more than 95% of OA and KC regardless of growth stages and FWHMs. If the multispectral image sensor is made with the six bands (the ratios of three bands) with 10 nm of FWHM, it is possible to classify the damaged spring potato by salinity or drought using the reflectance of images with 91.3% of OA and 85.0% of KC. 본 연구는 초분광 영상을 이용하여 간척지에서 주로 발생하는 염해 및 한해를 봄감자의 주요 생육단계에서 판별할 수 있는지를 검토하는 것이다. 영양생장기(VP), 괴경형성기(RFP) 및 괴경비대기(RGP)에 취득한 초분광 영상 내 봄감자 캐노피 영역의 반사율과 반사율의 불균일성을 최소화하기 위해 밴드 비로 변환하였다. 소형 다중분광 영상센서 개발을 고려하여 FWHM 5 nm의 단일 밴드를 상용화되어있는 밴드패스필터 기준으로 10 nm, 25 nm와 50 nm 평준화한 후 똑같이 밴드 비로 변화하였다. 의사결정트리법을 이용하여 각 FWHM에서 염해 판별에 유의한 단일 밴드 및 밴드 비를 추출하였고 그 분류 정확도는 OA와 KC로 나타내어졌다. 염해, 한해 및 정상 여부를 분류하기 위해 선택된 밴드는 최소 3개에서 최대 13개로 모든 FWHM에서 OA 66.7%와 KC 40.8% 이하의 정확도를 나타내었다. 괴경비대기(RGP)에서만 공통으로 440 nm가 선택되었고 동일 밴드는 아니지만 영양생장기(VP)에는 530 nm 또는 540 nm, 괴경비대기(RGP)에서는 추가로 710 nm 또는 720 nm가 선택되었다. 영양생장기(VP)에 비해 생식생장기(RFP 및 RGP)에 분류 정확도가 높지만 상용화가 용이한 10 nm 이상의 FWHM에서 OA 및 KC값이 각각 78.7%, 57.7% 이하로 나타났다. 밴드 비를 이용하여 염해, 한 해 및 정상을 분류하기 위해 선택된 밴드 비는 최소 2개에서 최대 6개로 원래 밴드(5 nm FWHM)의 비를 이용할 경우 생육 시기 및 FWHM에 관계없이 OA 및 KC가 95% 이상으로 나타났다. 영양생장기에서 FWHM에 관계없이 790 nm와 800 nm의 비가 선택되었고 동일 밴드는 아니지만 각 생육단계에서 Red, Red-edge 및 NIR 영역에서 유사밴드가 선택되었다. 모든 생육 시기에서 10 nm의 FWHM을 가진 3개 이하의 밴드 비를 이용한다면 OA 91.3%와 KC 85.0% 이상의 분류 정확도로 봄감자의 염해, 한해 및 정상여부 판별이 가능할 것으로 판단된다. 이 결과는 넓은 면적에서 염해 및 한해 피해를 받은 작물 필지를 소형 다중분광 카메라로 판별하여 빠르고 유연하게 제염기술을 투입하거나 그 피해 대책을 위한 정책 활용에 이용될 수 있을 것이다.

회전익 무인기에 탑재된 다중분광 센서를 이용한 콩의 생체중, 건물중, 엽면적 지수 추정

장시형,류찬석,강예성,전새롬,박준우,송혜영,강경석,강동우,쩌우쿤옌,전태환 한국농림기상학회 2019 한국농림기상학회지 Vol.21 No.4

Soybean is one of the most important crops of which the grains contain high protein content and has been consumed in various forms of food. Soybean plants are generally cultivated on the field and their yield and quality are strongly affected by climate change. Recently, the abnormal climate conditions, including heat wave and heavy rainfall, frequently occurs which would increase the risk of the farm management. The real-time assessment techniques for quality and growth of soybean would reduce the losses of the crop in terms of quantity and quality. The objective of this work was to develop a simple model to estimate the growth of soybean plant using a multispectral sensor mounted on a rotor-wing unmanned aerial vehicle(UAV). The soybean growth model was developed by using simple linear regression analysis with three phenotypic data (fresh weight, dry weight, leaf area index) and two types of vegetation indices (VIs). It was found that the accuracy and precision of LAI model using GNDVI (R2= 0.789, RMSE=0.73 m2/m2, RE=34.91%) was greater than those of the model using NDVI (R2= 0.587, RMSE=1.01 m2/m2, RE=48.98%). The accuracy and precision based on the simple ratio indices were better than those based on the normalized vegetation indices, such as RRVI (R2= 0.760, RMSE=0.78 m2/m2, RE=37.26%) and GRVI (R2= 0.828, RMSE=0.66 m2/m2, RE=31.59%). The outcome of this study could aid the production of soybeans with high and uniform quality when a variable rate fertilization system is introduced to cope with the adverse climate conditions. 콩은 식량작물 중 단백질 함량이 매우 높고 식생활에서 여러가지 형태로 소비되기 때문에 매우 중요한 식량자원 중 하나이다. 콩은 일반적으로 노지에서 재배되기 때문에 콩의 생산량 및 품질은 갑작스런 기후 변화에 큰 영향을 받는다. 최근 폭염 및 폭우 등과 같은 이상기후로 인해 콩의 생산량이 불안정해짐에 따라 콩의 생육을 실시간으로 추정하여 품질저하를 예방할 수 있는 기술 개발이 필요하다. 본 연구에서는 회전익 무인기에 장착된 다중분광 센서를 이용하여 콩 생육을 추정하기 위해 수행되었다. 반사값을 이용하여 산출된 정규화 식생지수(NDVI, GNDVI)와 단순비 식생지수(RRVI, GRVI)와 콩 생육 데이터(생체중, 건물중, 엽면적지수)로 선형회귀분석을 실시하여 생육 추정 모델을 개발하였다. 그 결과, 정규화 식생지수인 NDVI를 이용한 엽면적 지수 추정 모델(R2=0.587, RMSE=1.01 m2/m2, RE=48.98%)보다 GNDVI를 이용한 엽면적 지수 추정 모델(R2=0.789, RMSE=0.73 m2/m2, RE=34.91%)이 높은 정밀도가 나타났으며, 단순비 식생지수를 이용한 엽면적 지수 추정 모델 (RRVI (R2=0.760, RMSE=0.78 m2/m2, RE=37.26%) GRVI (R2=0.828, RMSE=0.66 m2/m2, RE=31.59%)과 비교 했을 때, 단순비 식생지수에서 높은 정밀도가 나타났다. 기후변화에 대체하기 위해 재식밀도 및 변량 시비와 같은 재배관리법이 적용된다면, 고품질의 콩을 생산하는데 도움이 될 것으로 판단된다.

Influence of Digital Music on Chemical Properties in Red Leaf Lettuce

강예성,김성헌,류찬석 경상대학교 농업생명과학연구원 2016 농업생명과학연구 Vol.50 No.5

The purpose of this study was to investigate alteration of chemical properties in red leaflettuces(Lactuca sativa L.) exposed to digital music every day. The red leaf lettuces werecultivated in two hydroponic systems composed of two layers. In the first experiment, the redleaf lettuces with treatment were exposed to the digital music, while the lettuces under controlcondition were not exposed to the digital music. At harvest(6 weeks after planting), fresh weightand chlorophyll content were measured and compared the treatment with the control group. Subsequently, red leaf lettuces of the next experiment were compared to fresh weight,chlorophyll, ascorbic acid and anthocyanin content during different vegetation growth stages(4weeks and 6 weeks after planting). The comparison of data for all experiment was also dividedinto upper and lower parts because of the difference of temperature in hydroponic systems. Asa results, fresh weight and anthocyanin of the red leaf lettuces might be influenced by thedifference of temperature variations. Chlorophyll of the red leaf lettuces was not easilyinfluenced by digital music and difference of temperature. It was also shown that ascorbic acidas inactive molecule was not easily influenced by physical response like music.