• Proceedings of the Korean Society of Crop Science Conference
• /
• 2021.10a
• /
• pp.115-115
• /
• 2021

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.621-630
• /
• 2017

In this paper, a study on classification targeting a main production area of garlic and onion was carried out in order to figure out the applicability of multi-temporal high-resolution satellite imagery for field crop classification. After collecting satellite imagery in accordance with the growth cycle of garlic and onion, classifications using each sing date imagery and various combinations of multi-temporal dataset were conducted. In the case of single date imagery, high classification accuracy was obtained in December when the planting was completed and March when garlic and onion started to grow vigorously. Meanwhile, higher classification accuracy was obtained when using multi-temporal dataset rather than single date imagery. However, more images did not guarantee higher classification accuracy. Rather, the imagery at the planting season or right after planting reduced classification accuracy. The highest classification accuracy was obtained when using the combination of March, April and May data corresponding the growth season of garlic and onion. Therefore, it is recommended to secure imagery at main growth season in order to classify garlic and onion field using multi-temporal satellite imagery.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.5 no.2
• /
• pp.24-33
• /
• 1987

This study aims at obtaining more effective image processing techniques and more accurately classified image in the sphere which uses remotely sensed data. For this practice, the result of land use classification compounding summer scene with winter scene and the classified result of summer scene were compared, analyzed. From the upper analysed results, we found that Bitemporal Classification technique and $tan^{-1}$transformation were effective. Particularly, dividing crop class into two classes of farmland and field was more possible by appling Bitemporal Classification technique.

• Journal of the Korea Society for Simulation
• /
• v.29 no.4
• /
• pp.1-7
• /
• 2020

Early detection and classification of crop diseases play significant role to help farmers to reduce disease spread and to increase agricultural productivity. Recently, many researchers have used deep learning techniques like convolutional neural network (CNN) classifier for crop disease inspection with dataset of crop leaf images (e.g., PlantVillage dataset). These researches present over 90% of classification accuracy for crop diseases, but they have ability to detect only the pre-trained diseases. This paper proposes an efficient disease inspection CNN model for new crops not used in the pre-trained model. First, we present a benchmark crop disease classifier (CDC) for the crops in PlantVillage dataset using VGG16. Then we build a modified crop disease classifier (mCDC) to inspect diseases for untrained crops. The performance evaluation results show that the proposed model outperforms the benchmark classifier.

• The Korean Journal of Pesticide Science
• /
• v.18 no.1
• /
• pp.48-51
• /
• 2014

Since the year of 2006 when the extended revision of the Codex Classification of Foods and Animal Feeds was undertaken, considerable progresses have been made in revising the Classification. This paper aimed to summarize the present status on revision of the Codex Classification of Foods and Animal Feeds, focusing remarkable achievements such as 1) the draft revision of the Codex Classification for the fruit commodity group and 2) the draft Principles and Guidance on the Selection of Representative Commodities for the Extrapolation of Maximum Residue Limits for Pesticides to Commodity Groups, adopted by the Codex Alimentarius Commission in 2012. Additionally, it included information on lists of crop group or subgroup which are holding at Step 7 and were adopted at Step 5, and further have not been yet discussed by the Codex Committee on Pesticide Residues. These information will be very helpful for a pesticide regulatory regime.

• Journal of Biosystems Engineering
• /
• v.39 no.2
• /
• pp.96-100
• /
• 2014

Purpose: The objective of this study was to develop a classification index and the grade levels for a five-grade energy efficiency classification of agricultural dryers in Korea. Methods: The classification index and the grade levels were determined by using the performance test data published by the FACT over the last eight years to reflect a state of the art technology for agricultural dryers in Korea. The five grades were designed to have the classified dryers distributed normally over the grades with 15% for the $1^{st}$ grade, 20% for the $2^{nd}$ grade, 30% for the $3^{rd}$ grade, 20% for the $4^{th}$ grade and 15% for the $5^{th}$ grade. Results: The classification index was defined as the total amount of fuel and electrical energy consumed per 1% of the wet basis moisture content evaporated from a unit mass of grain or agricultural crops during the drying process: 1 MT of paddy rice for grain dryers and 1 kg of red pepper for agricultural crop dryers as the standard mass. Conclusions: The grade levels for the five-grade energy efficiency classification of grain dryers, kerosene dryers, and electric dryers were proposed in terms of the classification index value.

• Korean Journal of Medicinal Crop Science
• /
• v.9 no.4
• /
• pp.301-309
• /
• 2001

This study was conducted to provide the basic information on safflower collections and to identify the variations which could be utilized in safflower breeding programs. The agronomic characteristics was used to clarify the genetic relationships among safflower collections and to classify them into distint genetic groups. There were 21 early maturing collections with less than 80 days in number of days from planting to flowering. The number of primary and secondary branches ranged ${3.8{\sim}14.8\;and\;0{\sim}26.9}$, respectively, and two collections, IT201434 and IT202723, were found to be high branch types. The 101 safflower collections were classified into 11 groups based on the complete linkage cluster analysis using agronomic characteristics. The I, II, III, IV, IX, X and ? groups included the 25%, 33%, 14%, 8%, 2%, 1% and 1% of the collections, respectively. All the collections in the group III were Korean landraces. The collections in group X could be characterized as early emergence, late flowering and high yield components such as the number of capitula per plant, number of seeds per capitula and seed weight per plant. The number of capitula per plant and seed weight per plant, i.e., the two main yield components, had the highly significant positive correlations with stem diameter, number of the primary branches, number of the secondary branches, number of leaves and leaf length.

• The Plant Pathology Journal
• /
• v.39 no.4
• /
• pp.319-334
• /
• 2023

Plant disease is an important factor affecting crop yield. With various types and complex conditions, plant diseases cause serious economic losses, as well as modern agriculture constraints. Hence, rapid, accurate, and early identification of crop diseases is of great significance. Recent developments in deep learning, especially convolutional neural network (CNN), have shown impressive performance in plant disease classification. However, most of the existing datasets for plant disease classification are a single background environment rather than a real field environment. In addition, the classification can only obtain the category of a single disease and fail to obtain the location of multiple different diseases, which limits the practical application. Therefore, the object detection method based on CNN can overcome these shortcomings and has broad application prospects. In this study, an annotated apple leaf disease dataset in a real field environment was first constructed to compensate for the lack of existing datasets. Moreover, the Faster R-CNN and YOLOv3 architectures were trained to detect apple leaf diseases in our dataset. Finally, comparative experiments were conducted and a variety of evaluation indicators were analyzed. The experimental results demonstrate that deep learning algorithms represented by YOLOv3 and Faster R-CNN are feasible for plant disease detection and have their own strong points and weaknesses.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.4
• /
• pp.337-345
• /
• 2023

Estimating the rice heading date is one of the most crucial agricultural tasks related to productivity. However, due to abnormal climates around the world, it is becoming increasingly challenging to estimate the rice heading date. Therefore, a more objective classification method for estimating the rice heading date is needed than the existing methods. This study, we aimed to classify the rice heading stage from various images using a CNN classification model. We collected top-view images taken from a drone and a phenotyping tower, as well as slanted-view images captured with a RGB camera. The collected images underwent preprocessing to prepare them as input data for the CNN model. The CNN architectures employed were ResNet50, InceptionV3, and VGG19, which are commonly used in image classification models. The accuracy of the models all showed an accuracy of 0.98 or higher regardless of each architecture and type of image. We also used Grad-CAM to visually check which features of the image the model looked at and classified. Then verified our model accurately measure the rice heading date in paddy fields. The rice heading date was estimated to be approximately one day apart on average in the four paddy fields. This method suggests that the water head can be estimated automatically and quantitatively when estimating the rice heading date from various paddy field monitoring images.

• 한국약용작물학회:학술대회논문집
• /
• 2010.10a
• /
• pp.553-554
• /
• 2010