• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.265-271
• /
• 2015

This study proposes an algorithm for recognizing apple trees in images and detecting apples to measure the number of apples on the trees. The proposed algorithm explores whether there are apple trees or not based on the number of image block-unit edges, and then it detects apple areas. In order to extract colors appropriate for apple areas, the CIE $L^*a^*b^*$ color space is used. In order to extract apple characteristics strong against illumination changes, modified census transform (MCT) is used. Then, using the AdaBoost learning algorithm, characteristics data on the apples are learned and generated. With the generated data, the detection of apple areas is made. The proposed algorithm has a higher detection rate than existing pixel-based image processing algorithms and minimizes false detection.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.818-821
• /
• 2020

The artificial intelligence software market is developing in various fields world widely. In particular, there is a wide variety of applications for image recognition technology using deep learning. This study intends to apply image recognition technology to the 'Home Gardening' market growing rapidly due to COVID-19, and aims to build a small-scale smart farm in the house using artificial intelligence and IoT technology for convenient crop cultivation for busy people living in cities. This intelligent farm system includes an automatic image recognition function and recommendation function based on temperature and humidity sensor-based indoor environment analysis.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.583-589
• /
• 2020

Recently, the utility of UAS (Unmanned Aerial System) for a smart farm using various sensors and ICT (Information & Communications Technology) is expected. In particular, it has proven its effectiveness as an outdoor crop monitoring method through various indices and is being studied in various fields. This study analyzes damage to crops caused by natural disasters and measures the damage area of rice plants. To this end, data is acquired using BG-NIR (Blue Green_Near Infrared Red) and RGB sensors, and image analysis and NDWI (Normalized Difference Water Index) index performed to review crop damage caused by in the rainy season. Also, point cloud data based on image analysis is generated, and damage is measured by comparing data before and after the typhoon through an inspection map. As a result of the study, the growth and rainy season damage of rice was examined through NDWI index analysis, and the damage area caused by typhoon was measured by analysis of the inspection map.

• Journal of Aerospace System Engineering
• /
• v.17 no.2
• /
• pp.38-44
• /
• 2023

This study aims to determine how agricultural drones are operated for flight tests using a 5G communication in order to carry out a mission such as sensing agricultural crop healthy status with special cameras. Drones were installed with a multi-spectral and IR camera to capture images of crop status in separate altitudes with different speeds. A multi-spectral camera can capture crop image data using five different particular wavelengths with a built-in GPS so that captured images with synchronized time could provide better accuracy of position and altitude during the flight time. Captured thermal videos are then sent to a ground server to be analyzed via 5G communication. Thus, combining two cameras can result in better visualization of vegetation areas. The flight test verified how agricultural drones equipped with special cameras could collect image data in vegetation areas.

• Journal of Forest and Environmental Science
• /
• v.40 no.1
• /
• pp.1-8
• /
• 2024

Recently, intensive research has been conducted to develop innovative methods for diagnosing plant diseases based on hyperspectral technologies. Hyperspectral analysis is a new subject that combines optical spectroscopy and image analysis methods, which makes it possible to simultaneously evaluate both physiological and morphological parameters. Among the physiological and morphological parameters are classifying healthy and diseased plants, assessing the severity of the disease, differentiating the types of pathogens, and identifying the symptoms of biotic stresses at early stages, including during the incubation period, when the symptoms are not visible to the human eye. Plant diseases cause significant economic losses in agriculture around the world as the symptoms of diseases usually appear when the plants are infected severely. Early detection, quantification, and identification of plant diseases are crucial for the targeted application of plant protection measures in crop production. Hence, this can be done by possible applications of hyperspectral sensors and platforms on different scales for disease diagnosis. Further, the main areas of application of hyperspectral sensors in the diagnosis of plant diseases are considered, such as detection, differentiation, and identification of diseases, estimation of disease severity, and phenotyping of disease resistance of genotypes. This review provides a deeper understanding, of basic principles and implementation of hyperspectral sensors that can measure pathogen-induced changes in plant physiology. Hence, it brings together critically assessed reports and evaluations of researchers who have adopted the use of this application. This review concluded with an overview that hyperspectral sensors, as a non-invasive system of measurement can be adopted in early detection, identification, and possible solutions to farmers as it would empower prior intervention to help moderate against decrease in yield and/or total crop loss.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.131-131
• /
• 2017

Though the Platycodon grandiflorum, has a broad range of pharmacologic properties, but the mechanisms underlying these effects remain unclear. In order to profile proteins from the nodal segment, callus, root and shoot, high throughput proteome approach was executed in the present study. Two-dimensional gels stained with CBB, a total of 84 differential expressed proteins were confirmed out of 839 protein spots using image analysis by Progenesis SameSpot software. Out of total differential expressed spots, 58 differential expressed protein spots (${\geq}2-fold$) were analyzed using MASCOT search engine according to the similarity of sequences with previously characterized proteins along with the UniProt database. Out of 58 differential expressed protein, 32 protein spots were up-regulated such as ribulose-1,5-bisphosphate carboxylase, endoplasmic oxidoreductin-1, heat stress transcription factor A3, RNA pseudourine synthase 4, cysteine proteinase, GntR family transcriptional regulator, E3 xyloglucan 6-xylosyltransferase, while 26 differential protein spots were down-regulated such as L-ascorbate oxidase precursor, late embryogenesis abundant protein D-34, putative SCO1 protein, oxygen-evolving enhancer protein 3. However, the frequency distribution of identified proteins using iProClass databases, and assignment by function based on gene ontology revealed that the identified proteins from the explants were mainly associated with the nucleic acid binding (17%), transferase activity (14%) and ion binding (12%). Taken together, the protein profile may provide insight clues for better understanding the characteristics of proteins and its metabolic activities in various explants of this essential medicinal plant P. grandiflorum.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2017.06a
• /
• pp.132-132
• /
• 2017

Plants, including Platycodon grandiflorum have been used globally across varied cultures as a safe natural source of medicines. From time immemorial, humans have relied on plants that could meet their basic necessities such as food, shelter, fuel and health. This study was executed to profile proteins from the hormone induced diploid and tetraploid roots using high throughput proteome approach. Two dimensional gels stained with CBB, a total of 64 differential expressed proteins were identified from the diploid root using image analysis by Progenesis SameSpot software. Out of total differential expressed spots, 20 differential expressed protein spots ( ${\geq}1.5-fold$) were analyzed using LTQ-FTICR MS whereas a total of 13 protein spots were up regulated and 7 protein spots were down-regulated. However, in the case of tetraploid root, a total of 78 differential expressed proteins were identified from tetraploid root of which a total of 28 differential expressed protein spots (${\geq}1.5-fold$) were analyzed by mass spectrometry whereas a total of 16 protein spots were up regulated and a total of 12 protein spots were down-regulated. However, proteins identified using iProClass databases revealed that the identified proteins from the explants were mainly associated with the nucleic acid binding, oxidoreductase activity, transporter activity and isomers activity. The exclusive protein profile may provide insight clues for better understanding the characteristics of protein function and its metabolic activity that can help for the development of the nutritional and breeding aspects of this economically important medicinal plant.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.60 no.1
• /
• pp.97-106
• /
• 2015

Platycodon grandiflorum, commonly known as Doraji in Korea, has a wide range of pharmacologic properties, such as reducing adiposity and hyperlipidemia, and antiatherosclerotic effects. However, the mechanisms underlying these effects remain unclear. In order to profile proteins from the nodal segment, callus, root and shoot, high throughput proteome approach was executed in the present study. Two dimensional gels stained with CBB, a total of 84 differential expressed proteins were confirmed out of 839 protein spots using image analysis by Progenesis SameSpot software. Out of total differential expressed spots, 58 differential expressed protein spots (${\geq}$ 2-fold) were analyzed using MASCOT search engine according to the similarity of sequences with previously characterized proteins along with the UniProt database. Out of 58 differential expressed protein, 32 protein spots were up-regulated such as ribulose-1,5-bisphosphate carboxylase, endoplasmic oxidoreductin-1, heat stress transcription factor A3, RNA pseudourine synthase 4, cysteine proteinase, GntR family transcriptional regulator, E3 xyloglucan 6-xylosyltransferase, while 26 differential protein spots were down-regulated such as L-ascorbate oxidase precursor, late embryogenesis abundant protein D-34, putative SCO1 protein, oxygen-evolving enhancer protein 3. However, frequency distribution of identified proteins using iProClass databases, and assignment by function based on gene ontology revealed that the identified proteins from the explants were mainly associated with the nucleic acid binding (17%), transferase activity (14%) and ion binding (12%). In that way, the exclusive protein profile may provide insight clues for better understanding the characteristics of proteins and metabolic activity in various explants of the economically important medicinal plant Platycodon grandiflorum.

• Korean Journal of Remote Sensing
• /
• v.36 no.4
• /
• pp.515-525
• /
• 2020

This study investigates the potential of bidirectional long short-term memory (Bi-LSTM) for efficient modeling of temporal information in crop classification using multitemporal remote sensing images. Unlike unidirectional LSTM models that consider only either forward or backward states, Bi-LSTM could account for temporal dependency of time-series images in both forward and backward directions. This property of Bi-LSTM can be effectively applied to crop classification when it is difficult to obtain full time-series images covering the entire growth cycle of crops. The classification performance of the Bi-LSTM is compared with that of two unidirectional LSTM architectures (forward and backward) with respect to different input image combinations via a case study of crop classification in Anbadegi, Korea. When full time-series images were used as inputs for classification, the Bi-LSTM outperformed the other unidirectional LSTM architectures; however, the difference in classification accuracy from unidirectional LSTM was not substantial. On the contrary, when using multitemporal images that did not include useful information for the discrimination of crops, the Bi-LSTM could compensate for the information deficiency by including temporal information from both forward and backward states, thereby achieving the best classification accuracy, compared with the unidirectional LSTM. These case study results indicate the efficiency of the Bi-LSTM for crop classification, particularly when limited input images are available.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.1
• /
• pp.15-26
• /
• 2022

3D open-field farm model developed from UAV (Unmanned Aerial Vehicle) data could make crop monitoring easier, also could be an important dataset for various fields like remote sensing or precision agriculture. It is essential to separate crops from the non-crop area because labeling in a manual way is extremely laborious and not appropriate for continuous monitoring. We, therefore, made a 3D open-field farm model based on UAV images and developed a crop segmentation model using a supervised machine learning algorithm. We compared performances from various models using different data features like color or geographic coordinates, and two supervised learning algorithms which are SVM (Support Vector Machine) and KNN (K-Nearest Neighbors). The best approach was trained with 2-dimensional data, ExGR (Excess of Green minus Excess of Red) and z coordinate value, using KNN algorithm, whose accuracy, precision, recall, F1 score was 97.85, 96.51, 88.54, 92.35% respectively. Also, we compared our model performance with similar previous work. Our approach showed slightly better accuracy, and it detected the actual crop better than the previous approach, while it also classified actual non-crop points (e.g. weeds) as crops.