• 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.

• 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.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.689-698
• /
• 2017

In this paper, a new classification method based on the combination of semi-supervised learning with spatial similarity of adjacent pixels is presented for crop classification in inaccessible areas. Iterative classification based on semi-supervised learning is applied to extract reliable training data from both the initial classification result with a small number of training data, and classification results of adjacent pixels are also considered to extract new training pixels with less uncertainty. To evaluate the applicability of the proposed method, a case study of the classification of field crops was carried out using multi-temporal Landsat-8 OLI acquired in the Daehongdan region, North Korea. From a case study, the misclassification of crops and forests, and isolated pixels in the initial classification result were greatly reduced by applying the proposed semi-supervised learning method. In addition, the combination of classification results of adjacent pixels for the extraction of new training data led to the great reduction of both misclassification results and isolated pixels, compared to the initial classification and traditional semi-supervised learning results. Therefore, it is expected that the proposed method would be effectively applied to classify areas in which it is difficult to collect sufficient training data.

• Korean Journal of Soil Science and Fertilizer
• /
• v.48 no.5
• /
• pp.351-360
• /
• 2015

Human influence on soil formation has dramatically increased with human civilization and industry development. Increase of anthropogenic soils induced researches on the anthropogenic soils; classification, chemical and physical characteristics of anthropogenic soils and plant growth from anthropogenic soils. However there have been no comprehensive analyses on soil pore or physical properties of anthropogenic soils from 3 dimensional images in Korea. The objectives of this study were to characterize physical properties of anthropogenic paddy field soils by depth and to find differences between natural and anthropogenic paddy field soils. Soil samples were taken from two anthropogenic and natural paddy field soils; anthropogenic (A_c) and natural (N_c) paddy soils with topsoil of coarse texture and anthropogenic (A_f) and natural (N_f) paddy soils with topsoil of fine texture. The anthropogenic paddy fields were reestablished during the Arable Land Remodeling Project from 2011 to 2012 and continued rice farming after the project. Natural paddy fields had no artificial changes or disturbance in soil layers up to 1m depth. Samples were taken at three different depths and analyzed for routine physical properties (texture, bulk density, etc.) and pore properties with computer tomography (CT) scans. The CT scan provided 3 dimensional images at resolution of 0.01 mm to calculate pore radius size, length, and tortuosity of soil pores. Fractal and configuration entropy analyses were applied to quantify pore structure and analyze spatial distribution of pores within soil images. The results of measured physical properties showed no clear trend or significant differences across depths or sites from all samples, except the properties from topsoils. The results of pore morphology and spatial distribution analyses provided detailed information of pores affected by human influences. Pore length and size showed significant decrease in anthropogenic soils. Especially, pores of A_c had great decrease in length compared to N_c. Fractal and entropy analyses showed clear changes of pore distributions across sites. The topsoil layer of A_c showed more degradation of pore structure than that of N_c, while pores of A_f topsoil did not show significant degradation compared with those of N_f. These results concluded that anthropogenic soils with coarse texture may have more effects on pore properties than ones with fine texture. The reestablished paddy fields may need more fundamental remediation to improve physical conditions.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.5
• /
• pp.97-102
• /
• 2017

Recently deep learning techniques such as convolutional neural networks (CNN) have been introduced to classify high-resolution remote sensing data. In this paper, we investigated the possibility of applying CNN to crop classification of farmland images captured by drones. The farming area was divided into seven classes: rice field, sweet potato, red pepper, corn, sesame leaf, fruit tree, and vinyl greenhouse. We performed image pre-processing and normalization to apply CNN, and the accuracy of image classification was more than 98%. With the output of this study, it is expected that the transition from the existing image classification methods to the deep learning based image classification methods will be facilitated in a fast manner, and the possibility of success can be confirmed.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.3
• /
• pp.21-28
• /
• 2017

The main goal of this paper is to assess application of UAV (Unmanned Aerial Vehicle) remote sensing and GIS based images in detection and measuring of rice field drought area in South Korea. Drought is recurring feature of the climatic events, which often hit South Korea, bringing significant water shortages, local economic losses and adverse social consequences. This paper describes the assesment of the near-realtime drought damage monitoring and reporting system for the agricultural drought region. The system is being developed using drought-related vegetation characteristics, which are derived from UAV remote sensing data. The study area is $3.07km^2$ of Wonbuk-myeon, Taean-gun, Chungnam in South Korea. UAV images were acquired three times from July 4 to October 29, 2015. Three images of the same test site have been analysed by object-based image classification technique. Drought damaged paddy rices reached $754,362m^2$, which is 47.1 %. The NongHyeop Agricultural Damage Insurance accepted agricultural land of 4.6 % ($34,932m^2$). For paddy rices by UAV investigation, the drought monitoring and crop productivity was effective in improving drought assessment method.

• 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.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1007-1014
• /
• 2022

Compact Advanced Satellite 500 (CAS500) can be used for various purposes, including vegetation, forestry, and agriculture fields. It is expected that it will be possible to acquire satellite images of various areas quickly. In order to use satellite images acquired through CAS500 in the agricultural field, it is necessary to develop a satellite image-based extraction technique for crop-cultivated areas.In particular, as research in the field of deep learning has become active in recent years, research on developing a deep learning model for extracting crop cultivation areas and generating training data is necessary. This manuscript classified the onion and garlic cultivation areas in Hapcheon-gun using PlanetScope satellite images and farm maps. In particular, for effective model learning, the model performance was analyzed according to the proportion of crop-cultivated areas. For the deep learning model used in the experiment, Fully Convolutional Densely Connected Convolutional Network (FC-DenseNet) was reconstructed to fit the purpose of crop cultivation area classification and utilized. As a result of the experiment, the ratio of crop cultivation areas in the training data affected the performance of the deep learning model.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2002.05a
• /
• pp.53-57
• /
• 2002

Quality evaluation must be more developed in order to offer the sufficient information for producer, distribution centers buyer, consumer. There are many parameters which influence the rice quality and cooked rice. It is difficult to evaluate the quality of rice and cooked rice by only some parameters. In the case of rice quality evaluation in Korea, physicochemical inspection is performed by examining the minimum and maximum limits of brown rice recovery, moisture content, damaged kernel, and colored kernel as inspection standard. Marketing standard of rice defines the limits of perfect, white core and belly, colored, damaged kernels, and broken rice, classifying into special, excellent, and normal grades. As a research direction for the development of rice quality evaluation, establishment as parts of technical field, must be further developed as follows : more detailed measure of characters, search of unknown taste-related components, creation and grade classification of quality evaluation factors at each management stages of treatment after harvesting, evaluation as food material as well as cooking rice, method development for simple evaluation and establishment of equation for palatability. In the side of policy, the following concerns must be conducted: price discrimination in conformity to rice cultivar and grade under the basis of qualify evaluation method developed, fixation of head rice branding, and introduction of low temperature circulation.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.618-620
• /
• 2004

This paper explores the use of IKONOS imagery of 1 m resolution panchromatic (PAN) band and 4 m resolution multi-spectral (MS) band in the development of agriculture­related data inventories. Three images (May 25, 2001, December 25, 2001, October 23, 2003) were used to obtain temporal distributions in crop cover characteristics such as rice, pear, grape, red pepper, corn, barley, garlic and surface water cover of reservoir with field investigations. The availability and cost problems are expected to solve by KOMPSAT-2 that is scheduled to launch in 2005. The capability of KOMPSAT-2 image for crop and rural water resources management will increase by accumulating temporal data inventories as a database.