• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.105-113
• /
• 2021

Due to the recent coronavirus outbreak, many universities in Korea have started to implement remote education. Accordingly, the Ministry of Education has stated its plans to continuously encourage and maintain remote learning as the future innovation model for education and suggested the need for a diverse range of remote learning models. However, studies on the development of practical learning models have not been carried out actively until now. Particularly, there are not many case studies in the field of design, especially regarding mobile website development. As means to improve the newly designed practice environment, this study therefore proposes the "modoo" project that offers domain creation and online marketing services. As a result of this study, the researcher suggests the use of a mixed(blending) teaching method and realized that the effectiveness of education multiplies when project-based learning and flipped learning is combined appropriately. The research methodology was divided into two big sections, education content and operations, and the effect was evaluated using the course evaluations. The study results confirmed that the applicability will increase given that learning satisfaction levels increased by more than 5% compared to face-to-face learning.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3981-4004
• /
• 2019

This paper proposes a novel method for locating objects in real space from a single remote image and measuring actual distances between them by automatic detection and perspective transformation. The dimensions of the real space are known in advance. First, the corner points of the interested region are detected from an image using deep learning. Then, based on the corner points, the region of interest (ROI) is extracted and made proportional to real space by applying warp-perspective transformation. Finally, the objects are detected and mapped to the real-world location. Removing distortion from the image using camera calibration improves the accuracy in most of the cases. The deep learning framework Darknet is used for detection, and necessary modifications are made to integrate perspective transformation, camera calibration, un-distortion, etc. Experiments are performed with two types of cameras, one with barrel and the other with pincushion distortions. The results show that the difference between calculated distances and measured on real space with measurement tapes are very small; approximately 1 cm on an average. Furthermore, automatic corner detection allows the system to be used with any type of camera that has a fixed pose or in motion; using more points significantly enhances the accuracy of real-world mapping even without camera calibration. Perspective transformation also increases the object detection efficiency by making unified sizes of all objects.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.51-57
• /
• 2022

The purpose of this study is to explore the future direction of university liberal arts classes at a time when many educational institutions have returned to face-to-face instruction as social distancing related to COVID-19 has been eliminated. A survey was conducted with 187 college students who took a liberal arts class that included a combination of online and in-person classes. The results found that learners were generally satisfied with remote learning (87.8%). The reasons for this high level of satisfaction included sufficient comprehension of class content, systematic class progress, and the efficiency and convenience of learning in a remote environment. Satisfaction levels for in-person classes (66%) were relatively lower than those for remote classes, and this is reflected in the preference for class type. Among wholly in-person, wholly remote, and a combination of both, it was found that learners preferred remote classes the most (54.4%). When conducting in-person classes, instructors must devise a class plan that incorporates the advantages of online remote classes.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.502-504
• /
• 2004

With rapidly growing of computer and internet technology, Internet-based tote-operation of robotic systems has created new opportunities in resource sharing, long-distance learning, and remote experimentation. In this paper, remote control system of a mobile robot through the internet has been designed. The internet users can access and command a mobile robot in the real time, receiving the robot's sensor data. The overall system has been tested and its usefulness shown through the experimental results.

• Journal of information and communication convergence engineering
• /
• v.20 no.1
• /
• pp.16-21
• /
• 2022

In this research, we create a network infrastructure based on a service-oriented infrastructure (SOI) for the virtualization technology and integrate it with a cloud technology that applies the cloud integration management platform (CIMP) concept. In CIMP, the server and storage will be separated. The server will be adopted for virtualization while the storage will be used by students and teachers to store data. As long they save their data in the storage module, every time, everywhere, and on every device, they can access their data. This research will implement the design of the network infrastructure and be applied to the remote practical learning system in the laboratory. Students and teachers will ultimately adopt this network infrastructure for remote practice using their respective devices without physically meeting in the laboratory. In the future, if the implementation phase is successful, then in addition to laboratory environments, it can be implemented in all learning activities at our campus.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.645-646
• /
• 2023

본 연구에서는 원격강좌(콘텐츠 기반)를 이용하여 학습하는 학습자들의 학습 형태를 분석하여 효율적인 원격강좌 운영을 위한 제도 마련에 대한 필요성을 제시하고자 하였다. 학습자들이 원격강좌를 학습한 정규교과 1년의 데이터를 가지고 분석한 결과 학습자들은 오후8시부터 자정까지 학습하는 빈도가 가장 높았다. 이는 교과 구분 형태인 전공/교양 모두에서 나타나는 분석결과였다. 또한 요일별로 분석해 보면 특정 요일에 학습의 빈도가 높았는데 이 요일은 한 주간의 강의가 종료되는 요일이었다. 이러한 분석 결과를 기반으로 효율적인 원격강좌가 운영되기 위한 제도적 보완 - 원격강좌별로 종료되는 요일을 달리한다든지 -을 생각해 볼 필요가 있다 하겠다.

• Korean Journal of Remote Sensing
• /
• v.33 no.4
• /
• pp.423-436
• /
• 2017

This paper presents a deep learning-based road segmentation framework from very high-resolution orthophotos. The proposed method uses Deep Convolutional Autoencoders for end-to-end mapping of orthophotos to road segmentations. In addition, a set of post-processing steps were applied to make the model outputs GIS-ready data that could be useful for various applications. The optimization of the model's parameters is explained which was conducted via grid search method. The model was trained and implemented in Keras, a high-level deep learning framework run on top of Tensorflow. The results show that the proposed model with the best-obtained hyperparameters could segment road objects from orthophotos at an average accuracy of 88.5%. The results of optimization revealed that the best optimization algorithm and activation function for the studied task are Stochastic Gradient Descent (SGD) and Exponential Linear Unit (ELU), respectively. In addition, the best numbers of convolutional filters were found to be 8 for the first and second layers and 128 for the third and fourth layers of the proposed network architecture. Moreover, the analysis on the time complexity of the model showed that the model could be trained in 4 hours and 50 minutes on 1024 high-resolution images of size $106{\times}106pixels$, and segment road objects from similar size and resolution images in around 14 minutes. The results show that the deep learning models such as Convolutional Autoencoders could be a best alternative to traditional machine learning models for road segmentation from aerial photographs.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1707-1720
• /
• 2023

With the increase in satellite time series data, the utility of remote sensing data is growing. In the analysis of time series data, the relative positional accuracy between images has a significant impact on the results, making image registration essential for correction. In recent years, research on image registration has been increasing by applying deep learning, which outperforms existing image registration algorithms. To train deep learning-based registration models, a large number of image pairs are required. Additionally, creating a correlation map between the data of existing deep learning models and applying additional computations to extract registration points is inefficient. To overcome these drawbacks, this study developed a data augmentation technique for training image registration models and applied it to OffsetNet, a registration model that predicts the offset amount itself, to perform image registration for KOMSAT-2, -3, and -3A. The results of the model training showed that OffsetNet accurately predicted the offset amount for the test data, enabling effective registration of the master and slave images.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.459-466
• /
• 2023

In the last decade, artificial intelligence's dramatic advancement with the development of various deep learning techniques has significantly contributed to remote sensing fields and satellite image applications. Among many prominent areas, super-resolution research has seen substantial growth with the release of several benchmark datasets and the rise of generative adversarial network-based studies. However, most previously published remote sensing benchmark datasets represent spatial resolution within approximately 10 meters, imposing limitations when directly applying for super-resolution of small objects with cm unit spatial resolution. Furthermore, if the dataset lacks a global spatial distribution and is specialized in particular land covers, the consequent lack of feature diversity can directly impact the quantitative performance and prevent the formation of robust foundation models. To overcome these issues, this paper proposes a method to generate benchmark datasets by simulating the modulation transfer functions of the sensor. The proposed approach leverages the simulation method with a solid theoretical foundation, notably recognized in image fusion. Additionally, the generated benchmark dataset is applied to state-of-the-art super-resolution base models for quantitative and visual analysis and discusses the shortcomings of the existing datasets. Through these efforts, we anticipate that the proposed benchmark dataset will facilitate various super-resolution research shortly in Korea.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_4
• /
• pp.1111-1123
• /
• 2023

In recent times, semantic image segmentation methods using deep learning models have been widely used for monitoring changes in surface attributes using remote sensing imagery. To enhance the performance of various UNet-based deep learning models, including the prominent UNet model, it is imperative to have a sufficiently large training dataset. However, enlarging the training dataset not only escalates the hardware requirements for processing but also significantly increases the time required for training. To address these issues, transfer learning is used as an effective approach, enabling performance improvement of models even in the absence of massive training datasets. In this paper we present three transfer learning models, UNet-ResNet50, UNet-VGG19, and CBAM-DRUNet-VGG19, which are combined with the representative pretrained models of VGG19 model and ResNet50 model. We applied these models to building extraction tasks and analyzed the accuracy improvements resulting from the application of transfer learning. Considering the substantial impact of learning rate on the performance of deep learning models, we also analyzed performance variations of each model based on different learning rate settings. We employed three datasets, namely Kompsat-3A dataset, WHU dataset, and INRIA dataset for evaluating the performance of building extraction results. The average accuracy improvements for the three dataset types, in comparison to the UNet model, were 5.1% for the UNet-ResNet50 model, while both UNet-VGG19 and CBAM-DRUNet-VGG19 models achieved a 7.2% improvement.