• Title/Summary/Keyword: 농업 인력

Search Result 197, Processing Time 0.027 seconds

Sorghum Field Segmentation with U-Net from UAV RGB (무인기 기반 RGB 영상 활용 U-Net을 이용한 수수 재배지 분할)

  • Kisu Park;Chanseok Ryu ;Yeseong Kang;Eunri Kim;Jongchan Jeong;Jinki Park
    • Korean Journal of Remote Sensing
    • /
    • v.39 no.5_1
    • /
    • pp.521-535
    • /
    • 2023
  • When converting rice fields into fields,sorghum (sorghum bicolor L. Moench) has excellent moisture resistance, enabling stable production along with soybeans. Therefore, it is a crop that is expected to improve the self-sufficiency rate of domestic food crops and solve the rice supply-demand imbalance problem. However, there is a lack of fundamental statistics,such as cultivation fields required for estimating yields, due to the traditional survey method, which takes a long time even with a large manpower. In this study, U-Net was applied to RGB images based on unmanned aerial vehicle to confirm the possibility of non-destructive segmentation of sorghum cultivation fields. RGB images were acquired on July 28, August 13, and August 25, 2022. On each image acquisition date, datasets were divided into 6,000 training datasets and 1,000 validation datasets with a size of 512 × 512 images. Classification models were developed based on three classes consisting of Sorghum fields(sorghum), rice and soybean fields(others), and non-agricultural fields(background), and two classes consisting of sorghum and non-sorghum (others+background). The classification accuracy of sorghum cultivation fields was higher than 0.91 in the three class-based models at all acquisition dates, but learning confusion occurred in the other classes in the August dataset. In contrast, the two-class-based model showed an accuracy of 0.95 or better in all classes, with stable learning on the August dataset. As a result, two class-based models in August will be advantageous for calculating the cultivation fields of sorghum.

A Study on the Surface Erosion by the Development of Cropland on the Hillslope in the West Coast Area of North Korea Using Quick Bird Satellite Images (Quick Bird 영상을 이용한 북한 서해안 구릉지 개간에 따른 지표 침식 분석)

  • Lee, Min-Boo;Kim, Nam-Shin;Lee, Gwang-Ryul;Han, Uk
    • Journal of the Korean association of regional geographers
    • /
    • v.11 no.4
    • /
    • pp.453-462
    • /
    • 2005
  • The study deals with surface erosion patterns due to the development of cropland toward hillslope and hilltop in the Oncheon-gun, pyeongbuk province and Nampo city of west coast area in the North Korea, using Quick Bird satellite images with 60cm resolution. In North Korea, for national economic difficult after 1980 year, newly developed croplands have been along the gentle hillslope, in which it is possible for individual man power different from the tideland which needs large scaled man-power and equipment. The new croplands are named Darakbat(terraced farm with embankment) and Bitalbat(titled farm developed on the original hill slope), neighboring with orchard and grouped settlement in lower valley. For supplying agricultural water, irrigation ditches and temporal crop storages have been constructed, connecting Darakbat, Bitalbat and orchard. These cropland developments have caused surface erosion composed of 3 types such as pit, linear and headward erosion, together with rill and gully. Owing to poor management of cropland and irrigation system, topsoil erosion and, collapse and sedimentation of ditch and pool, caused the decrease of agricultural productivity. These analysis using Quick Bird images can suggest original raw data about geographical facts on North Korea agriculture and help to recover their agricultural system and plan future national unified land.

  • PDF

Development of Self-propelled Chile harvester (IV) - Factorial Experiment of Drum Type Secondary Picking Part - (자주식 고추수확기 개발을 위한 기초연구 (IV) - 드럼형 2차 탈실부 요인시험 -)

  • Kim, Su Bin;Byun, Jun Hee;Park, Seung Jae;Kang, Young Sun;Kim, Dae Cheol
    • Proceedings of the Korean Society for Agricultural Machinery Conference
    • /
    • 2017.04a
    • /
    • pp.10-10
    • /
    • 2017
  • 우리나라 고추 재배는 ha당 총 노동투하시간 2,436 hr 중 수확작업시간은 954 hr으로 총 노동투하시간의 39.2%를 점유하고 있어 수확작업의 생력화를 위해 고추수확작업의 기계화가 절실히 필요하다. 고추 수확의 기계화를 위해 국내 T사에서 자주식 고추 수확기를 개발 중에 있다. 현재 고추를 기계로 채취하게 되면 많은 양의 줄기달린 고추가 유입되므로 수확 후 분리하는 작업에 있어 많은 인력과 시간이 소요되는 실정이다. 따라서 본 연구에서는 드럼 회전 타입의 2차 탈실부 요인시험 장치를 제작하여 드럼의 회전속도, 드럼과 급치 사이 간격에 대해 요인시험을 수행함으로써 자주식 고추수확기 2차 탈실부의 적정 작업조건을 파악함에 목적을 두었다. 탈실부 요인시험 장치는 급치가 부착된 3개의 드럼 형태의 탈실부와 이송벨트로 구성된다. 공시재료인 고추는 광주광역시 남구 승촌동 소재의 개인농가에서 Plastic 온실로 재배된 '천상' 품종을 사용하였다. 본 요인시험은 드럼의 회전속도(40, 70, 100, 130 rpm)와 드럼과 급치 사이 간격(2, 5, 10 mm)으로 요인을 설정하여 시험을 수행하였다. 시험은 각 요인 당 3반복으로 실시하였으며, 투입되는 시료는 줄기달린 고추를 3가지의 형태로 구분하여 제작하였다. 각 요인에 따라 고추의 탈실률, 손상률에 대해 통계프로그램인 SAS를 이용하여 분석하였다. 드럼의 회전속도에 따른 요인시험결과, 손상 대비 탈실률로 비교했을 때 회전속도 40 rpm에서 탈실률 47.69%, 손상률 8.33%로 성능이 가장 낮았으며, 회전속도 70 rpm에서 탈실률 63.89%, 손상률 12.96%로 성능이 가장 높았다. 드럼과 급치 사이의 간격에 따른 요인시험결과, 간격이 클수록 탈실률 및 손상률이 줄어드는 경향을 보였으며, 5 mm일 때 성능이 가장 높았다. 반복이 있는 이원배치법을 이용하여 분석한 결과, 고추 탈실률과 손상률은 드럼의 회전속도와 드럼과 급치 사이 간격 모두에서 유의차가 발생한다고 나타났다. 요인시험 결과를 종합적으로 고려해 보았을 때, 드럼 회전속도 70 rpm, 드럼과 급치 사이 간격 5 mm에서 가장 높은 성능을 보였다. 고추 탈실률이 낮고, 손상률이 높아 탈실장치로서의 기능에 어려움이 있을 것으로 보이므로 추후 급치 타입의 변경 등 탈실장치의 보완 및 개선이 필요할 것으로 판단된다.

  • PDF

Development of Walk Type Harvest Equipment for Lycium Chinense Mill Using The Hit Method (타격방식을 적용한 보행형 구기자 수확장치 개발)

  • Lee, Seung-Kee;Han, Jae-Woong;Kim, Woong;Jeon, Myong-Jin
    • Proceedings of the Korean Society for Agricultural Machinery Conference
    • /
    • 2017.04a
    • /
    • pp.90-90
    • /
    • 2017
  • 생력화를 위한 구기자의 수확 기계화는 열악한 수확작업환경을 쾌적한 작업환경으로 개선하고 노동력 감소, 생산비 절감을 할 수 있다. 관행 손 수확과 진동 고리형 수확기 방법보다 높은 작업 능률 향상으로 영농규모의 확대 촉진 및 안정적인 영농 구조를 구축하여 재배농가의 생산비를 절감하여 경쟁력을 높일 수 있으며, 기존 인력에 의존하였던 수확작업을 기계화함으로서 전업농 및 대단위 경작이 가능하게 함으로서 국내에서 생산한 양질의 구기자를 국민에게 안정적으로 제공할 수 있다. 따라서, 본 연구는 구기자 수확작업의 생력화를 위하여 개발 보급된 수목형의 재배법 특성을 분석하고 이를 토대로 타격장치를 적용한 보행형 구기자 수확기를 개발하는데 목적이 있다. 수목형 구기자나무의 분지에 착과되어 있는 숙과를 주행하면서 탈과 할 수 있는 탈과 장치를 제작하기 위하여 타격형 탈과 장치를 3D 모델링 작업(Inventor V.11, Autodesk, USA) 후 시작기를 제작, 구기자 수확 시작기는 주행부, 타격장치, 집과부, 분지유인부로 구성하였다. 구기자 수확 시작기의 최대 높이는 형태학적 특성을 토대로 타격봉의 높이를 900 mm 이하로 제한하였으며, 조향장치의 높이는 800 mm로 하였다. 주행부는 구기자 재식 조사결과를 이용하여 고랑 폭 1,500 mm 이하에서 자유롭게 전 후진 이동이 가능하고 경사로 등을 주행 시에도 안전성을 높이기 위해 자동브레이크 기능이 있으며 타격장치의 타격 봉은 알루미늄 재질로 지름 100 mm, 길이 400 mm로 설계 제작하였으며, 구기자 분지 타격 시 분지와 타격 봉이 수직 상태로 타격이 가능하도록 제작, 집과장치는 포장의 두둑, 고랑은 일괄 표준화가 되어 있지않아 청양구기자시험장에서 측정한 재배법을 바탕으로 설계된 수집부 프레임의 적용범위는 폭 450 mm, 길이 720 mm, 높이 1,500 mm를 집과 범위로 하여 설계 제작하였다. 타격 방식을 적용한 구기자 수확기 성능평가 결과 조숙기에 30초 이상의 탈과 시 87.5 % 이상 탈과는 어려울 것으로 판단되었으며, 성숙기에는 타격시간에 관계없이 92 %의 매우 우수한 탈과율이 나타났다. 성숙기의 주행속도 48 m/h 일 때 탈과율과 집과율은 89 %, 92 %로 나타났다.단위작업시간당 최대 수확 능력은 관행작업 2.9 kg/hr, 진동고리형 수확기 5.2 kg/hr, 타격방식을 적용한 구기자 수확기는 최소 7.6 kg/hr, 최대 24.1 kg/hr로 관행작업과 비교하여 주행속도와 시기별 최소 2.6배, 최대 8.3배의 작업 성능 차이가 나타났다. 재배양식에서는 기계화 수목형이 적합한 것으로 나타났고, 타격방식을 적용한 보행형 구기자 수확기를 이용하여 수형별 시간대별 수확성능을 시험한 결과 우수한 결과가 나타났다. 이에 따라 구기자 재배 농가에 기계화수목형 재배법을 보급하고 타격방식을 적용한 구기자 수확기를 이용하면 작업환경 개선과 노동력, 인건비 절감을 통한 영농규모의 확대 촉진 및 안정적인 영농 구조로 구기자 경쟁력 제고를 할 수 있을 것으로 판단되어진다.

  • PDF

Synthesis and Ion Exchange Capacity of 4-Vinylpyridine-vinylsulfonic Acid Resin (Para-Vinylpyridine-vinylsulfonic Acid 수지(樹脂)의 합성(合成)과 이온 교환능(交換能))

  • Sung, Nack Do;Song, Hea Young;Park, Byung Kwan
    • Korean Journal of Agricultural Science
    • /
    • v.9 no.2
    • /
    • pp.584-590
    • /
    • 1982
  • Copolymerization of the 4-vinylpyridine with vinylacetate and divinylbenzene initiated by azobis-isobutyronitrile was carried out in DMF in presence $BaCl_2$ at $98^{\circ}C$. Ion exchange res in, poly 4-vinylpyridine-vinylsulfonic acid-divinylbenzene was prepared by sulfonation of 4-vinylpyridine-vinylacetatp-divinylbenzene with concentrated sulfuric acid. The compositions of each synthetic resin were identified by means of ir adsorption spectroscopy. Anion and cation capacities of 4-vinylpyridine-vinylsulfonic acid-divinylbenzene ion exchanger were 2.5meq/g and 4.8meq/g, respectively. Adsorption of Cd(II) and Cu(II) ions have showed larger quantity in alkalie media. A study also was made of the influence of alcohol on the distribution coefficient of Cd(II) and Cu(II) ions between the synthetic ion exchanger, and solution containing hydrochloric acid, various alcohols and water. The distribution coefficients of metal ions decrease generally as the number of branches of carbon in the molecule of butyl alcohol increase. (t-BuOH

  • PDF

Effect of the Transplanting Date and Seeding Age on the Flowering and Grain Yield of Rice under Mechanical Transplanting (수도(水稻)의 기계이앙시기(機械移秧時期)와 묘령(苗令)이 출수(出穗) 및 수량(收量)에 미치는 영향(影響))

  • Choi, Chang Yeol;Ahn, Su Bong;Park, Jong Seong;Choe, Bong Ho
    • Korean Journal of Agricultural Science
    • /
    • v.9 no.1
    • /
    • pp.231-238
    • /
    • 1982
  • The study was done to determine the proper transplanting dates and seedling ages of rice when mechanical transplanting was attempted. Heading dates of the Milyang #23, developed from Tong-il rice was delayed by delayed transplanting and the percent of filling grain was also low. The proper heading dates for the variety should be the first part of August and the transplanting should be done by the end of May. The presumed last days for the transplantation was considered early part of June. 30 to 40 days old seedlings were very effective to have healthy rooting systems. However, the Milyang #15 had shown more tolerance to the late transplantation than Milyang #23 and the degree of delaying heading dates due to the delayed transplantation was rather smaller than that of the Milyang #23. Even when the Milyang #15 was transplanted on June 30, the heading dates were around the middle of August and the ripening percentage was comparatively high and yield was also high. Therefore, the proper heading dates of the Milyang #15 might be around the middle of August and transplanting dates should be the first part of June. The possible last dates of transplantation of the Milyang #15 was assumed to be the last days of June and the proper seedling ages would be 20 to 30 day after sowing.

  • PDF

A Study on the Improvement of HACCP Evaluation Items in Small Scale Meat Packaging Plant (소규모 식육포장처리업 HACCP 평가항목 개선 연구)

  • Jung, Sung-Won;Cho, Seok-Hyun;Back, Seung-Hee;Kong, Hong-Sik;Nam, In-Sik
    • Korean Journal of Organic Agriculture
    • /
    • v.27 no.4
    • /
    • pp.437-452
    • /
    • 2019
  • The HACCP evaluation standards for the meat packaging plant are divided into general scale HACCP evaluation standard and small scale HACCP evaluation standard. There are 69 evaluation items in the general scale HACCP evaluation criteria, of which 54 items in the prerequisite management and 15 items in the HACCP management are included. The number of small scale HACCP evaluation items are 20 and about 29% of the general scale HACCP evaluation items. This may not be enough to produce a safety livestock products for the purpose of implementing the HACCP system due to the nature of the meat packaging plant, which does not show much difference in the production process or method of product depending on the scale. To improve the small scale HACCP evaluation standard, the importance of each item was compared with the small scale HACCP evaluation based on the rate of non-compliance and the severity levels in the general scale HACCP evaluation items. As a result of the study, 8 items were derived from the prerequisites management, 2 items were derived from the HACCP management, and some similar evaluation items were grouped together. Finally, 10 items were added to the 20 items of the existing small scale HACCP evaluation items. In this study, study on the safety management of domestic livestock products are continuously carried out, so that it is possible to provide safety livestock products to consumers and contributes to securing competitiveness of domestic livestock industry.

Preparation of blocking ultraviolet mica composites using Nano-TiO2 (Nano-TiO2를 이용한 자외선차단 마이카 복합체 제조)

  • Yun, Ki Hoon;Lee, Jaebok;Moon, Young-Jin;Go, Hee Kyoung;Lee, Yi;Lee, Dong-Kyu
    • Journal of the Korean Applied Science and Technology
    • /
    • v.35 no.4
    • /
    • pp.1197-1205
    • /
    • 2018
  • UV protection cosmetics belong to functional cosmetics and contain organic or inorganic UV blocking pigments. The inorganic UV blocking pigments are mainly zinc oxide and titanium dioxide. It is known that inorganic UV blocking pigment has a diameter of 60 to 100 nm and has good blocking ability of UVA and UVB. Also, it has high inactivity against sunlight including UV and is excellent in safety. In addition, it is not absorbed or accumulated on the skin like organic pigments and does not cause skin irritation or allergy. In this study, mica, a plate-shaped inorganic pigment, nanosized titanium dioxide, an UV blocking material, and hydrophobic silica were surface-treated with surfactants. And then, titanium dioxide nanoparticles and silica were physically adsorbed on the mica by non-chemical mutual attraction due to differences in charge. Thereafter, the mica complex was surface-treated with silane to prepare a hydrophobic UV blocking pigment complex. The plate-shaped UV blocking composite improves the cohesiveness of a general nanoparticle material titanium dioxide, enhances UV blocking effect due to uniform dispersion, and can greatly improve dispersion stability in cosmetic formulations by surface treatment with hydrophobic property. The surface charge of the pigment was evaluated by zeta potential. The properties of the UV blocking pigment complex were evaluated by FE-SEM, XRD, FT-IR and UV-VIS.

Development of Mask-RCNN Model for Detecting Greenhouses Based on Satellite Image (위성이미지 기반 시설하우스 판별 Mask-RCNN 모델 개발)

  • Kim, Yun Seok;Heo, Seong;Yoon, Seong Uk;Ahn, Jinhyun;Choi, Inchan;Chang, Sungyul;Lee, Seung-Jae;Chung, Yong Suk
    • Korean Journal of Agricultural and Forest Meteorology
    • /
    • v.23 no.3
    • /
    • pp.156-162
    • /
    • 2021
  • The number of smart farms has increased to save labor in agricultural production as the subsidy become available from central and local governments. The number of illegal greenhouses has also increased, which causes serious issues for the local governments. In the present study, we developed Mask-RCNN model to detect greenhouses based on satellite images. Greenhouses in the satellite images were labeled for training and validation of the model. The Mask-RC NN model had the average precision (AP) of 75.6%. The average precision values for 50% and 75% of overlapping area were 91.1% and 81.8%, respectively. This results indicated that the Mask-RC NN model would be useful to detect the greenhouses recently built without proper permission using a periodical screening procedure based on satellite images. Furthermore, the model can be connected with GIS to establish unified management system for greenhouses. It can also be applied to the statistical analysis of the number and total area of greenhouses.

A Quality Prediction Model for Ginseng Sprouts based on CNN (CNN을 활용한 새싹삼의 품질 예측 모델 개발)

  • Lee, Chung-Gu;Jeong, Seok-Bong
    • Journal of the Korea Society for Simulation
    • /
    • v.30 no.2
    • /
    • pp.41-48
    • /
    • 2021
  • As the rural population continues to decline and aging, the improvement of agricultural productivity is becoming more important. Early prediction of crop quality can play an important role in improving agricultural productivity and profitability. Although many researches have been conducted recently to classify diseases and predict crop yield using CNN based deep learning and transfer learning technology, there are few studies which predict postharvest crop quality early in the planting stage. In this study, a early quality prediction model is proposed for sprout ginseng, which is drawing attention as a healthy functional foods. For this end, we took pictures of ginseng seedlings in the planting stage and cultivated them through hydroponic cultivation. After harvest, quality data were labeled by classifying the quality of ginseng sprout. With this data, we build early quality prediction models using several pre-trained CNN models through transfer learning technology. And we compare the prediction performance such as learning period and accuracy between each model. The results show more than 80% prediction accuracy in all proposed models, especially ResNet152V2 based model shows the highest accuracy. Through this study, it is expected that it will be able to contribute to production and profitability by automating the existing seedling screening works, which primarily rely on manpower.