• Journal of Mushroom
• /
• v.18 no.4
• /
• pp.297-302
• /
• 2020

Five varieties of mushrooms, including Sae-do, were examined using farm field tests to determine their morphological characteristics and quality by performing harvest flush. Considering the cultivation characteristics of the varieties studied, the parts related to mushroom generation and production showed almost similar characteristics. Overall, the mycelial forces were similar; however, in the evaluation of plantation tests performed by farmers, "saedo" was found to be the strongest and "saehan" was considered to be the weakest. Weights of fruiting bodies were related more for compost status and regimen of use than for breeding, and it was difficult to distinguish between the weights of fruiting bodies of the varieties studied. Regardless of the variety, pileus diameter, pileus thickness, and stem length of Dalseong-gun, Yongin-si, and Boryeong-si decreased as the harvest flush progressed. However, stem thickness tended to increase in the second and third flush compared to that in the first flush, regardless of the variety. However, the Gyeongju-si farms could not identify any trends attributable to varieties and harvest flushes. The pileus size and stem length of the fruiting bodies of varieties from Buyeo farms decreased with the progression of the harvest flush. However, pileus thickness and stem thickness did not show any specific tendency of growth among the varieties studied. The differences in the morphological characteristics of mushroom varieties in each harvest cycle are expected to be caused by differences in the supply of nutrients in the medium, the quality of the compost used, and the cultivation environment rather than the variety.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.2
• /
• pp.73-81
• /
• 2024

Recently, mobile manipulators have been utilized in agriculture industry for weed removal and harvest automation. This paper proposes a domain adaptive fruit detection method for harvest automation, by utilizing OWL-ViT model which is an open-vocabulary object detection model. The vision-language model can detect objects based on text prompt, and therefore, it can be extended to detect objects of undefined categories. In the development of deep learning models for real-world problems, constructing a large-scale labeled dataset is a time-consuming task and heavily relies on human effort. To reduce the labor-intensive workload, we utilized a large-scale public dataset as a source domain data and employed a domain adaptation method. Adversarial learning was conducted between a domain discriminator and feature extractor to reduce the gap between the distribution of feature vectors from the source domain and our target domain data. We collected a target domain dataset in a real-like environment and conducted experiments to demonstrate the effectiveness of the proposed method. In experiments, the domain adaptation method improved the AP50 metric from 38.88% to 78.59% for detecting objects within the range of 2m, and we achieved 81.7% of manipulation success rate.

• Journal of Bio-Environment Control
• /
• v.12 no.2
• /
• pp.57-62
• /
• 2003

In this study, a robotic manipulator for harvesting cucumber was developed. The objective of this research was to design and to construct a robotic manipulator specifically tailored to harvest cucumber in the greenhouse. The system was consisted of an integrated end-efffctor, an image processing system and a controlling system. Especially, the image processing system detected the quality of cucumber within each plant in order for the computer to furnish harvest instructions to the manipulator. In all tests of cucumber, the success rate for cucumber harvest was 84％ in the greenhouse. End-effector, image processing system and controlling system showed good performance. Based on the results of this research the following recommendations are made for further study. Besides harvesting cucumbers, the oldest leaves, creepers and the youngest small side leaves need to be removed.

• Korean Journal of Agricultural Science
• /
• v.46 no.2
• /
• pp.381-393
• /
• 2019

A smart farm is a system that combines information and communication technology (ICT), internet of things (IoT), and agricultural technology that enable a farm to operate with minimal labor and to automatically control of a greenhouse environment. Machine learning based on recently data-driven techniques has emerged with big data technologies and high-performance computing to create opportunities to quantify data intensive processes in agricultural operational environments. This paper presents research on the application of machine learning technology to diagnose the growth status of crops and predicting the harvest time of strawberries in a greenhouse according to image processing techniques. To classify the growth stages of the strawberries, we used object inference and detection with machine learning model based on deep learning neural networks and TensorFlow. The classification accuracy was compared based on the training data volume and training epoch. As a result, it was able to classify with an accuracy of over 90% with 200 training images and 8,000 training steps. The detection and classification of the strawberry maturities could be identified with an accuracy of over 90% at the mature and over mature stages of the strawberries. Concurrently, the experimental results are promising, and they show that this approach can be applied to develop a machine learning model for predicting the strawberry harvesting time and can be used to provide key decision support information to both farmers and policy makers about optimal harvest times and harvest planning.

• Journal of Bio-Environment Control
• /
• v.25 no.2
• /
• pp.106-110
• /
• 2016

In this study, a planting density-growth-harvest (PGH) chart was developed to easily read the growth and harvest factors such as crop growth rate, relative growth rate, shoot fresh weight, shoot dry weight, harvesting time, marketable rate, and marketable yield of common ice plant (Mesembryanthemum crystallinum L.). The plants were grown in a nutrient film technique (NFT) system in a closed-type plant factory using fluorescent lamps with three-band radiation under a light intensity of $140{\mu}mol{\cdot}m^{-2}{\cdot}s^{-1}$ and a photoperiod of 12 h. Growth and yield were analyzed under four planting densities ($15{\times}10cm$, $15{\times}15cm$, $15{\times}20cm$, and $15{\times}25cm$). Shoot fresh and dry weights per plant increased at a higher planting density until reached an upper limit and yield per area was also same tendency. Crop growth rate, relative growth rate and lost time were described using quadratic equation. A linear relationship between shoot dry weight and fresh weights was observed. PGH chart was constructed based on the growth data and making equations. For instance, with within row spacing (= 20 cm) and fresh weight per plant at harvest (= 100 g), we can estimate all the growth and harvest factors of common ice plant. The planting density, crop growth rate, relative growth rate, lost time, shoot dry weight per plant, harvesting time, and yield were $33plants/m^2$, $20g{\cdot}m^{-2}{\cdot}d^{-1}$, $0.27g{\cdot}g^{-1}{\cdot}d^{-1}$, 22 days, 2.5 g/plant, 26 days after transplanting, and $3.2kg{\cdot}m^{-2}$, respectively. With this chart, we could easily obtain the growth factors such as planting density, crop growth rate, relative growth rate, lost time and the harvest factors such as shoot fresh and dry weights, harvesting time, marketable rate, and marketable yield with at least two parameters, for instance, planting distance and one of harvest factors of plant. PGH charts will be useful tools to estimate the growth and yield of crops and to practical design of a closed-type plant production system.

• Proceedings of the Korean Society for Bio-Environment Control Conference
• /
• 1999.04a
• /
• pp.30-34
• /
• 1999

과채류 수확작업은 어렵고 힘든 지루한 작업이 반복적으로 수행된다. 지상 1m내외에서 결과하는 과채류의 경우 수확 중 많은 노동력을 필요로 한다. 특히 오이의 수확은 연속된 단순 반복 작업으로 작업인의 피로도가 매우 높다. 또한 농산물 수입개방으로 값싼 외국산 농산물이 대량 유입되고 있는 실정으로 농산물의 생산비 절감을 통한 대외 경쟁력을 갖추기 위해서는 과채류 수확에 있어서 로봇을 이용한 수확기 개발이 필요한 실정이다. (중략)

• Proceedings of the Korean Society for Bio-Environment Control Conference
• /
• 2003.04a
• /
• pp.135-139
• /
• 2003

식물생산공장은 작물의 생육에 적합하도록 환경을 최적화시킬 수 있기 때문에 최단기간에 작물을 생산할 수 있는 장점이 있다. 또한 지상부나 지하부 환경을 적절히 조절하거나 인위적인 품질제어기술을 이용하여 기존의 상품보다 품질이 월등히 높은 작물을 생산할 수 있는 여건과 설비가 조성될 수 있다. 이러한 식물공장 생산방식은 부가가치가 높은 화훼류나 분화류에 많이 적용되고 있지만, 생산기간이 길고 난방 등의 에너지가 상대적으로 많이 소요된다. (중략)

• Proceedings of the Korean Society for Bio-Environment Control Conference
• /
• 2007.05a
• /
• pp.182-184
• /
• 2007

• Journal of the Korean housing association
• /
• v.23 no.5
• /
• pp.51-60
• /
• 2012

Large-scale urban developments with increasing population and expansion of industrial facilities have destroyed the ecosystem. Consequently, the importance of vertical farm as a form of urban agriculture is increasing. However, such problems of vertical farms as economy and lack of awareness of residents are being raised. Firstly, this study derived types of vertical farm that are applicable to residential spaces through an examination of vertical farm buildings, and then inferred assessment items for a questionnaire survey for the development of u-services. Secondly, based on the issues deduced from the survey, u-services needed in vertical farm buildings were derived to use them as the basic data when we plan for a ubiquitous vertical farm building in residential space in the future. As result, the following uservices of ubiquitous vertical farm were proposed: u-notification service about the condition of crops from the aspect of growth management based on ubiquitous technology, remote/automatic control u-services, harvest information u-service for harvest management, recipe information u-service, and indoor air quality monitoring u-service, indoor environment adjusting u-service, and farm environment control u-service. Considering that many new buildings in Korea are residential buildings and many high-rise buildings are being planned, studies on vertical farm buildings must be continued.

• Proceedings of the Korean Society of Postharvest Science and Technology of Agricultural Products Conference
• /
• 2003.10a
• /
• pp.51-70
• /
• 2003

In recent years, Korean rice must compete with the rice of advanced countries under Doha Development Agenda(DDA) and free Trade Agreement(FTA). Therefore we should find more active and positive solution in rice industry according to the inncreasing power of international pressure. Increasing rice production was the most important policy during the past food-deficient days, but recently, with overproduction of rice, various circulation system by the brand(price)-differentiation should be settled in a recent market of Korea. Nowadays, some advanced rice farmers and Rice Processing Complex(RPC) managers developed new brands of rice with high-quality, adding healthy materials and environment-friendly farming methods. Therefore, the future strategy of making a new brand rice should be planned including selection of rice variety, cultural and post-harvest techniques, circulation and processing methods to compete against foreign rice. And environment-friendly farming is also recommendable for food safety and differentiate from imported rice. For the purpose of successful brand-rice, the following points might be considered. Firstly, selection of good quality rice and continual development of good variety must be conducted for the differentiation of Korean rice from foreign rice. Secondly, a special contract between producer and consumer with functional-rice, organic filming-rice, specific-rice will be recommendable. Thirdly, improvement of post-harvest management and milling system are necessary for the production of differentiated-rice. Fortunately, standard of inspection, rules of description for brand-rice must be developed by a more scientific examination in order to settlement of trust for consumer. Finally, provincial or regional-representative brand rice must be settled and conducted for the development of agreement market system between producer and consumer.