• Journal of Biosystems Engineering
• /
• v.22 no.3
• /
• pp.295-302
• /
• 1997

An ultimate purpose of this study was to develop an automatic system for brown rice quality inspection using image processing technique. In this study emphasis was put on developing an algorithm for discriminating the brown rice kernels depending on their external quality with a color image processing system equipped with an adaptor magnifying the input image and optical fiber for oblique lightening. Primarily, geometical and optical features of images were analyzed with paddy and the various brown rice kernel samples such as a sound, cracked, peen-transparent, green-opaque, colored, white-opaque and brokens. Secondary, geometrical and optical parameters significant for identifying each rice kernels were screened by a statistical analysis(STEPWISE and DISCRIM procedure, SAS wer. 6) and an algorithm fur on- line discrimination of the rice kernels in static state were developed, and finally its performance was evaluated. The results are summarized as follows. 1) It was ascertained that the cracked kernels can be detected when e incident angle of the oblique light is less than 2$0^{\circ}C$ but detectivity was significantly affected by the angle between the direction of the oblique light and the longitudinal axis of the rice kernel and also by the location of the embryo with respect to the oblique light. 2) The most significant Parameters which can discriminate brown rice kernels are area, length and R, B and r values among the several geometrical and optical parameters. 3) Discrimination accuracies of the algorithm were ranged from 90% to 96% for a sound, cracked, colored, broken and unhulled, about 81 % for green-transparent and white-opaque and 75 % for green-opaque, respectively.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.18 no.2
• /
• pp.89-104
• /
• 2015

In order to effectively manage forested areas in South Korea on a national scale, using remotely sensed data is considered most suitable. In this study, utilizing Land coverage maps and Forest type maps of national geographic information instead of collecting field data was tested for conducting supervised classification on SPOT-5 and KOMPSAT-2 imagery focusing on forested areas. Supervised classification were conducted in two ways: analysing a whole area around the study site and/or only forested areas around the study site, using Support Vector Machine. The overall accuracy for the classification on the whole area ranged from 54.9% to 68.9% with kappa coefficients of over 0.4, which meant the supervised classification was in general considered moderate because of sub-classifying forested areas into three categories (i.e. hardwood, conifer, mixed forests). Compared to this, the overall accuracy for forested areas were better for sub-classification of forested areas probably due to less distraction in the classification. To further improve the overall accuracy, it is needed to gain individual imagery rather than mosaic imagery to use more spetral bands and select more suitable conditions such as seasonal timing. It is also necessary to obtain precise and accurate training data for sub-classifying forested areas. This new approach can be considered as a basis of developing an excellent analysis manner for understanding and managing forest landscape.

• Journal of Biosystems Engineering
• /
• v.42 no.4
• /
• pp.283-292
• /
• 2017

Purpose: Japanese Apricot, a type of plum, has various medicinal and economical applications. Plums are quite popular worldwide, but their deseeding remains a serious impediment to their processing. Therefore, a plum (Japanese Apricot) seed remover (PSR) was developed that can use various types of cutters according to the purpose of the plum processing, and its performance was evaluated. Methods: The proposed PSR, which allows multipurpose cutters, namely, zero-, two-, and four-blade cutters, to be installed, was first designed and manufactured. To identify appropriate parameters related to the cutting pressure, plums were harvested from three regions during three harvesting periods, and their geometrical and mechanical properties were measured. After application of the parameters related to the cutting pressure, a performance test was carried out on both fresh and frozen plums by identifying the ratios of the flesh recovery, seed recovery, seed breakage, deseeding efficiency, and machine efficiency. Results: The results show that, using the proper calculation of the processing parameters, 100% deseeding efficiency was facilitated regardless of the type of cutter used. However, in the case of a four-blade cutter, there are significant differences in the flesh recovery ratio according to the plum setting angle. Between the fresh and frozen plums, all cutters showed a significantly better flesh recovery ratio for the case of fresh plums. Conclusions: This machine will advance the plum processing technology, and eventually help the plum industry flourish.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.327-341
• /
• 2022

Cloud removal is often required to construct time-series sets of optical images for environmental monitoring. In regression-based cloud removal, the selection of an appropriate regression model and the impact analysis of the input images significantly affect the prediction performance. This study evaluates the potential of Gaussian process (GP) regression for cloud removal and also analyzes the effects of cloud-free optical images and spectral bands on prediction performance. Unlike other machine learning-based regression models, GP regression provides uncertainty information and automatically optimizes hyperparameters. An experiment using Sentinel-2 multi-spectral images was conducted for cloud removal in the two agricultural regions. The prediction performance of GP regression was compared with that of random forest (RF) regression. Various combinations of input images and multi-spectral bands were considered for quantitative evaluations. The experimental results showed that using multi-temporal images with multi-spectral bands as inputs achieved the best prediction accuracy. Highly correlated adjacent multi-spectral bands and temporally correlated multi-temporal images resulted in an improved prediction accuracy. The prediction performance of GP regression was significantly improved in predicting the near-infrared band compared to that of RF regression. Estimating the distribution function of input data in GP regression could reflect the variations in the considered spectral band with a broader range. In particular, GP regression was superior to RF regression for reproducing structural patterns at both sites in terms of structural similarity. In addition, uncertainty information provided by GP regression showed a reasonable similarity to prediction errors for some sub-areas, indicating that uncertainty estimates may be used to measure the prediction result quality. These findings suggest that GP regression could be beneficial for cloud removal and optical image reconstruction. In addition, the impact analysis results of the input images provide guidelines for selecting optimal images for regression-based cloud removal.

• Weed & Turfgrass Science
• /
• v.2 no.1
• /
• pp.1-7
• /
• 2013

Studies were carried out to provide basic information for establishing the weed control in Chungbuk, Korea. The present surveys targeting 260 farmers in Chungbuk province were conducted for the cultivation system, weeds occurrence and usage of herbicides. To estimate the occurring area of herbicide resistant weeds, soil samples from 400 paddy fields were collected twice on August, 2011 and April, 2012. In the results of survey, the 99.6% of farmers used the rice planting machine and the 78% of the farmers disseminated herbicides twice to control weeds before and after planting rice. The most commonly used herbicide were as follows; soil-applied herbicide : butachlor 46.6%, mid-term herbicide : mefenacet + pyrazosulfuron-ethyl 10.7%, foliar herbicides : bentazone 62%. The dominant paddy field weeds included Echinochloa crusgalli (16.2%), Scirpus juncoides (12.2%), Monochoria vaginalis (11.9%) and Sagittaria trifolia (9.5%). Occurrence area of sulfonylurea herbicide resistant weeds was 13,659 ha in 26.8% of the paddy area. Monochoria vaginalis showed the highest with 4,605 ha (36.4%) followed Scirpus juncoides (30.7%), and Lindernia dubia (10.6%) at 2011. Monochoria vaginalis and Scirpus juncoides occurred were evenly distributed and the most problematic weed in Chungbuk, Korea.

• Journal of the Ergonomics Society of Korea
• /
• v.36 no.5
• /
• pp.545-557
• /
• 2017

Objective: The aim of this study was to find risk factors in cultivating ginseng based on risk assessments and suggest safety measures for main risks. Background: Safety education and training is one of the practical and effective methods to prevent occupational accidents and injuries. In agricultural sector, there are few contents of safety education as compared to other industries. Especially, farm work has different cultivation characteristics according to the crops, so it needs special education materials for each crop. Among the various types of crops, ginseng contains various risk factors due to its long cultivating period and unique environment. Therefore, safety education material specified for ginseng is necessary to improve ginseng farmers' safety. Method: Risk assessment for cultivating tasks of ginseng was carried out through data obtained from various methods (site survey, interview, literature survey). To improve objectivity, the risk assessment was applied with 3-criteria (researcher estimate, interview, previous research results). Finally, the three high-risk tasks were selected and safety measures for those tasks were provided. Results: Three tasks, such as 'Mounting, maintenance and removing supports', 'Pest control' and 'Harvest', were selected as risky tasks among total tasks. (1) In 'Mounting' and maintenance and removing supports', the farmers found to be exposed to the risks of musculoskeletal disorders and accidents related to operating the tablet machine. (2) In 'Pest control', agrichemical poisoning, musculoskeletal disorders and hyperthermia were main risks. Finally, (3) In 'Harvest', the farmers are mainly exposed to the possibility of accidents of agricultural machines and risks of musculoskeletal disorders. Thus, it needs to apply appropriate safety measures to those risky tasks, such as safety guidelines, convenience equipment, protective kit, and so on. Conclusion: This study can be used as basic data for agricultural safety and expected that it would be useful for further study. In addition, the results of the research will be produced in the form of animation, which will enhance the safety consciousness for aged farmers. Application: The result of this study can be used in developing safety education materials for ginseng farmers which is essential to prevent occupational accidents and injuries among ginseng farmers.

• Journal of Korea Water Resources Association
• /
• v.56 no.4
• /
• pp.245-259
• /
• 2023

The agricultural reservoir is a critical water supply system in South Korea, providing approximately 60% of the agricultural water demand. However, the reservoir faces several issues that jeopardize its efficient operation and management. To address this issues, we propose a novel deep-learning-based water level recognition model that uses CCTV image data to accurately estimate water levels in agricultural reservoirs. The model consists of three main parts: (1) dataset construction, (2) image segmentation using the U-Net algorithm, and (3) CCTV-based water level recognition using either CNN or ResNet. The model has been applied to two reservoirs G-reservoir and M-reservoir with observed CCTV image and water level time series data. The results show that the performance of the image segmentation model is superior, while the performance of the water level recognition model varies from 50 to 80% depending on water level classification criteria (i.e., classification guideline) and complexity of image data (i.e., variability of the image pixels). The performance of the model can be improved if more numbers of data can be collected.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.26 no.1
• /
• pp.63-74
• /
• 2024

In agriculture, frost can be devastating, which is why observation and forecasting are so important. According to a recent report analyzing frost observation data from the Korea Meteorological Administration, despite global warming due to climate change, the late frost date in spring has not been accelerated, and the frequency of frost has not decreased. Therefore, it is important to automate and continuously operate frost observation in risk areas to prevent agricultural frost damage. In the existing frost observation using leaf wetness sensors, there is a problem that the reference voltage value fluctuates over a long period of time due to contamination of the observation sensor or changes in the humidity of the surrounding environment. In this study, a datalogger program was implemented to automatically solve these problems. The established frost observation system can stably and automatically accumulate time-resolved observation data over a long period of time. This data can be utilized in the future for the development of frost diagnosis models using machine learning methods and the production of frost occurrence prediction information for surrounding areas.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.82-82
• /
• 2017

현대농업에서 잡초를 조기에 제거하지 못할 경우 작물의 성장에 장애를 초래하므로 제초작업은 매우 중요하다. 최근 친환경 고품질 농산물에 대한 소비자의 관심과 고품질 농산물에 대한 가격 차별화 등으로 제초제를 사용하지 않은 친환경 재배가 주목을 받고 있다. 제초제는 농작물에 따라 분류가 되어있어 종류마다 효과가 다르고 사용방법이 종류에 따라 어떻게 사용되는지 알기가 쉽지 않아 이에 따른 피해 또한 무시 할 수 없다. 현재 상용화되어 있는 제초기는 굴곡이 있는 고랑의 잡초를 효율적으로 제거하기 어려워 밭작물 제초작업에 사용하기 부적합하다. 밭작물 재배 기간에 행해지는 고랑의 제초작업은 평지보다 더 많은 힘이 필요하고 일반적인 제초기로는 좋은 결과를 얻기 어렵다. 또한 제초 작업시 농작물 피해와 멀칭 비닐을 손상시키는 문제가 발생 하고 있다. 따라서 밭작물에 효율적인 잡초를 제거하기 위해 굴곡이 있는 지형의 잡초를 제거하기 위한 제초기 개발이 반드시 필요하다. 밭작물용 제초기를 개발하기 위해 굴곡이 있는 고랑의 잡초 제거가 가능한 제초날의 형상 설계가 우선되어야 하며, 고랑의 잡초제거를 위한 제초날 형상설계를 하기 위해 우리나라 주요 밭작물 재배지의 이랑 넓이, 고랑 깊이 및 고랑 폭을 조사 분석하였다. 조사 작물 대상은 양파, 마늘, 무, 배추, 고추, 당근, 감자 총 7가지 작물을 대상으로 조사하였으며, 각 작물들의 이랑 넓이와 고랑 깊이 및 폭의 평균치를 구하여 제초날 설계에 적용하고자 하였다. 범위가 있는 수치는 높은 수치를 기준으로 계산하였으며 고랑의 평균 폭은 34.2cm이고, 고랑의 평균 깊이는 22.1cm가 나타났다. 잡초를 효과적으로 제거하기 위해 제초날의 형상은 고랑의 크기 및 형태에 맞게 원형으로 설계를 하여야 한다. 형상 설계는 밭작물 고랑 평균직경 및 평균높이를 고려하고, 제초작업시 제초날이 작물 및 멀칭비닐의 손상 하지 않도록 하기 위해 직경은 고랑 평균 폭의 75% 정도 치수로 형상을 설계하고, 제초날 깊이는 고랑의 굴곡형태을 고려할 때 제초날 반경의 70%정도로 설계하여 원형제초날 폭 250mm, 제초날 깊이 87.5mm로 설계해야 할 것으로 분석 되었다.

• Korean journal of applied entomology
• /
• v.22 no.2 s.55
• /
• pp.130-137
• /
• 1983

A wide variety of pathogens are known io be seedborne, carried either as infectious mycelium internally or as contaminants on the seed coat. When seed is infected with a pathogen, the seed nay be rendered nonviable or it may remain viable but produce weak seedling. In some cases, the Infected seedling nay not be severely weakened, but nay serve as a source of primary inoculum within a community of plants. A recent problem nay be the dissemination of seedborne pathogens occurring as a result of the massive movements of seed, as a part of the 'Green revolution' Disease of great danger to agriculture may be introduced with seed from other parts of world. Seed treatment with organic mercury compounds in liquid form had become popular since about 1955. Organic mercury compounds contributed considerably to the increase in production of many crops and vegetables. In 1975, however, the use of organic mercury compound was forbidden because of doubts regarding their residual mammalian toxicity in agricultural products. Benomyl-thiram mixture, thiophanate methyl-;hiram mixture and TCMB have now been registered as seed disinfectants for the use of rice blast, brown spot and Bakanae disease. Oxathiinsthiram mixture has been registered as seed disinfectant for barley and wheat loose smut and leaf stripe of barley. Agricultural techniques have made such rapid progress that the nursery methods changed from the use of paddy nursery to box nursery designed for machine-transplanting. The spread of rice transplanting machines has caused increase of seedborne diseases. Among seedborne diseases, Bakanae disease has remarkably increased and causes much damage recently. In order to counter this trend, seed disinfectants must also be diversified. First, effective non-selective disinfectants need to be developed, and second, appropriate control methods always need to be prepared in parallel with the development of new techniques for cultivation.