• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.2
• /
• pp.91-108
• /
• 2022

In most cases, optical images have been used as training data of DL (Deep Learning) models for object detection, recognition, identification, classification, semantic segmentation, and instance segmentation. However, properties of 3D objects in the real-world could not be fully explored with 2D images. One of the major sources of the 3D geospatial information is DSM (Digital Surface Model). In this matter, characteristic information derived from DSM would be effective to analyze 3D terrain features. Especially, man-made objects such as buildings having geometrically unique shape could be described by geometric elements that are obtained from 3D geospatial data. The background and motivation of this paper were drawn from concept of the intrinsic image that is involved in high-level visual information processing. This paper aims to extract buildings after classifying terrain features by training DL model with DSM-derived information including slope, aspect, and SRI (Shaded Relief Image). The experiments were carried out using DSM and label dataset provided by ISPRS (International Society for Photogrammetry and Remote Sensing) for CNN-based SegNet model. In particular, experiments focus on combining multi-source information to improve training performance and synergistic effect of the DL model. The results demonstrate that buildings were effectively classified and extracted by the proposed approach.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1451-1466
• /
• 2023

In the context of maritime emergencies, the utilization of drones has rapidly increased, with a particular focus on their application in search and rescue operations. Deep learning models utilizing drone images for the rapid detection of distressed vessels and other maritime drift objects are gaining attention. However, effective training of such models necessitates a substantial amount of diverse training data that considers various weather conditions and vessel states. The lack of such data can lead to a degradation in the performance of trained models. This study aims to enhance the performance of deep learning models for distress ship detection by developing a maritime environment simulator to augment the dataset. The simulator allows for the configuration of various weather conditions, vessel states such as sinking or capsizing, and specifications and characteristics of drones and sensors. Training the deep learning model with the dataset generated through simulation resulted in improved detection performance, including accuracy and recall, when compared to models trained solely on actual drone image datasets. In particular, the accuracy of distress ship detection in adverse weather conditions, such as rain or fog, increased by approximately 2-5%, with a significant reduction in the rate of undetected instances. These results demonstrate the practical and effective contribution of the developed simulator in simulating diverse scenarios for model training. Furthermore, the distress ship detection deep learning model based on this approach is expected to be efficiently applied in maritime search and rescue operations.

• Korean Journal of Remote Sensing
• /
• v.33 no.4
• /
• pp.359-375
• /
• 2017

We developed fog detection algorithm (KNU_FDA) based on the optical and textural properties of fog using satellite (COMS) and ground observation data. The optical properties are dual channel difference (DCD: BT3.7 - BT11) and albedo, and the textural properties are normalized local standard deviation of IR1 and visible channels. Temperature difference between air temperature and BT11 is applied to discriminate the fog from other clouds. Fog detection is performed according to the solar zenith angle of pixel because of the different availability of satellite data: day, night and dawn/dusk. Post-processing is also performed to increase the probability of detection (POD), in particular, at the edge of main fog area. The fog probability is calculated by the weighted sum of threshold tests. The initial threshold and weighting values are optimized using sensitivity tests for the varying threshold values using receiver operating characteristic analysis. The validation results with ground visibility data for the validation cases showed that the performance of KNU_FDA show relatively consistent detection skills but it clearly depends on the fog types and time of day. The average POD and FAR (False Alarm Ratio) for the training and validation cases are ranged from 0.76 to 0.90 and from 0.41 to 0.63, respectively. In general, the performance is relatively good for the fog without high cloud and strong fog but that is significantly decreased for the weak fog. In order to improve the detection skills and stability, optimization of threshold and weighting values are needed through the various training cases.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.1
• /
• pp.101-106
• /
• 2010

Due to significant advances in Internet technology, there have been many e-learning courses offered by universities and academic institutes nowadays through the Internet. And these courses have benefited many students who might be constrained by distance and time. Nevertheless, most web-based courses are lecturing courses that cannot fulfill the needs for engineering technology education. In this paper, we propose the design and implementation of web-based programmable logic controller(PLC) laboratory to support learning and training for industrial automation. The proposed web-based PLC laboratory system consists of virtual labs and remote labs. This web-based PLC laboratory can be accessed by registered students to practice PLC experiments at their own home, enhancing the quality of education without much increasing in the overall cost. With the help of web cameras, the students can even have experience the live PLC experiments through the Internet.

• The KIPS Transactions:PartA
• /
• v.9A no.1
• /
• pp.121-128
• /
• 2002

Web-based teaching-learning systems through the internet has continuously pursued the learner-centered educational environment by promoting the interaction between leachers and students. As a result, learners haute become free of the limit of time and space and have more ways to have access to education information more easily. Consequently, the development of the internet has resulted in the changes of the educational environment. Web-based distance education through the internet is now expected to be applied widely in various fields of education. In fact, distance education through the internet has taken place in a new education paradigm. The purpose of this paper is to promote the economical and educational efficiency of all the procedures from developing the system to operating in a remote training cyber system. Therefore in developing the system, we designed it to raise the efficiency by making main modulo into components and by reducing the terms and cost by reuse. Also lute meant to raise the efficiency of education by applying constructivism as an educational basic.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3917-3941
• /
• 2019

The recent interest in artificial intelligence and machine learning has partly contributed to an interest in the use of such approaches for hyperspectral remote sensing (HRS) imagery classification, as evidenced by the increasing number of deep framework with deep convolutional neural networks (CNN) structures proposed in the literature. In these approaches, the assumption of obtaining high quality deep features by using CNN is not always easy and efficient because of the complex data distribution and the limited sample size. In this paper, conventional handcrafted learning-based multi features based on expert knowledge are introduced as the input of a special designed CNN to improve the pixel description and classification performance of HRS imagery. The introduction of these handcrafted features can reduce the complexity of the original HRS data and reduce the sample requirements by eliminating redundant information and improving the starting point of deep feature training. It also provides some concise and effective features that are not readily available from direct training with CNN. Evaluations using three public HRS datasets demonstrate the utility of our proposed method in HRS classification.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1567-1577
• /
• 2020

Urban land cover classification is role in urban planning and management. So, it's important to improve classification accuracy on urban location. In this paper, machine learning model, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are proposed for urban land cover classification based on high resolution satellite imagery (KOMPSAT-3A). Satellite image was trained based on 25 m rectangle grid to create training data, and training models used for classifying test area. During the validation process, we presented confusion matrix for each result with 250 Ground Truth Points (GTP). Of the four SVM kernels and the two activation functions ANN, the SVM Polynomial kernel model had the highest accuracy of 86%. In the process of comparing the SVM and ANN using GTP, the SVM model was more effective than the ANN model for KOMPSAT-3A classification. Among the four classes (building, road, vegetation, and bare-soil), building class showed the lowest classification accuracy due to the shadow caused by the high rise building.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1589-1605
• /
• 2022

Phase unwrapping is an essential procedure for interferometric synthetic aperture radar techniques. Accordingly, a lot of phase unwrapping methods have been developed. Deep-learning-based unwrapping methods have recently been proposed. In this paper, we reviewed state-of-the-art deep-learning-based unwrapping approaches in terms of 1) the approaches to predicting unwrapped phases, 2) deep learning model structures for phase unwrapping, and 3) training data generation. The research trend of the approaches to predicting unwrapped phases was introduced by categorizing wrap count segmentation, phase jump classification, phase regression, and deep-learning-assisted method. We introduced the case studies of deep learning model structure for phase unwrapping, and model structure optimization to relate the overall phase information. In addition, we summarized the research trend of the training data generation approaches in the views of phase gradient and noise in the main. And the future direction in deep-learning-based phase unwrapping was presented. It is expected that this paper is used as guideline for exploring future direction of deep-learning-based phase unwrapping research in Korea.

• Journal of Korean Home Economics Education Association
• /
• v.30 no.1
• /
• pp.15-28
• /
• 2018

Teachers are not completed by appointment, but gradually made through self-development and training for a long time. In order to improve a sense of responsibility of home economics teachers, and also to suggest the purpose and direction of program through job training, the needs of training subjects should be preferentially understood. Thus, this study aims to provide basic data for establishing the developmental operation measures of training for home economics teachers, by researching the needs for training performed after the qualification training for first-grade teachers, targeting the teachers participating in the qualification training program for first-grade teachers of home economics in 2017. About the half of the research subjects received the home economics training one time or less for last three years. Through the training for first-grade teachers, the technical improvement of lesson instruction was demanded the most. As professional qualifications that should be cultivated through training, the ability to develop teaching methods and teaching/learning materials was the highest. Regarding the theme of training, the development of teaching/learning materials for home economics was desired the most. They wanted the training method including direct participation with high utilization for lesson, sublation of competition-centered evaluation, preference of instructors with field experience, continuous opportunity of home economics training, and communicative training. Regarding the needs for the 2015 revised curriculum, the demand for the training of 'human development and family' area was the highest. Therefore, in order to improve the professionalism of teachers through home economics training, it would be necessary to improve the educational environment such as temporal room for training and administrative support, and also to provide diverse types of training like group training, remote training, and smartphone app training suitable for changes in the generation of teachers. Also, on top of forming communities of home economics teachers, and sharing great contents of training, there should be individually-customized training for practice and sharing lesson cases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.671-686
• /
• 2020

Due to the long training time and high training cost of traditional surgical training methods, the emerging virtual surgical training method has gradually replaced it as the mainstream. However, the virtual surgical system suffers from poor authenticity and high computational cost problems. For overcoming the deficiency of these problems, we propose an optimized model for the local compression deformation of soft tissue. This model uses a simulated annealing algorithm to optimize the parameters of the soft tissue model to improve the authenticity of the simulation. Meanwhile, although the soft tissue deformation is divided into local deformation region and non-deformation region, our proposed model only needs to calculate and update the deformation region, which can improve the simulation real-time performance. Besides, we define a compensation strategy for the "superelastic" effect which often occurs with the mass-spring model. To verify the validity of the model, we carry out a compression simulation experiment of abdomen and human foot and compare it with other models. The experimental results indicate the proposed model is realistic and effective in soft tissue compression simulation, and it outperforms other models in accuracy and real-time performance.