• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.448-449
• /
• 2022

In the image upscaling field, the method using deep learning is showing better results than using the interpolation method. And for hologram upscaling, using deep learning is showing better results than general interpolation. In this paper, the network structure and learning results are analyzed. The learning results are compared by adjusting the depth of the network and the number of channels at the same weight.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.1-10
• /
• 2024

The research on predicting the routes of ships, which constitute the majority of maritime transportation, can detect potential hazards at sea in advance and prevent accidents. Unlike roads, there is no distinct signal system at sea, and traffic management is challenging, making ship route prediction essential for maritime safety. However, the time intervals of the ship route datasets are irregular due to communication disruptions. This study presents a method to adjust the time intervals of data using appropriate interpolation techniques for ship route prediction. Additionally, a deep learning model for predicting ship routes has been developed. This model is an LSTM model that predicts the future GPS coordinates of ships by understanding their movement patterns through real-time route information contained in AIS data. This paper presents a data preprocessing method using linear interpolation and a suitable deep learning model for ship route prediction. The experimental results demonstrate the effectiveness of the proposed method with an MSE of 0.0131 and an Accuracy of 0.9467.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.1
• /
• pp.8-14
• /
• 2022

With the development of deep learning, super-resolution (SR) methods have tried to use deep learning mechanism, instead of using simple interpolation. SR methods using deep learning is generally based on convolutional neural networks (CNN), but recently, SR researches using attention mechanism have been actively conducted. In this paper, we propose an approach of improving SR performance using one of the attention mechanisms, non-local sparse attention (NLSA). Through experiments, we confirmed that the performance of the existing SR models, IMDN, CARN, and OISR-LF-s can be improved by using NLSA.

• Korean Journal of Remote Sensing
• /
• v.38 no.2
• /
• pp.167-177
• /
• 2022

In order to obtain satellite image products using the image transmitted to the ground station after capturing the satellite images, many image pre/post-processing steps are involved. During the pre/post-processing, when converting from level 1R images to level 1G images, geometric correction is essential. An interpolation method necessary for geometric correction is inevitably used, and the quality of the level 1G images is determined according to the accuracy of the interpolation method. Also, it is crucial to speed up the interpolation algorithm by the level processor. In this paper, we proposed a lightweight CNN-based interpolation method required for geometric correction when converting from level 1R to level 1G. The proposed method doubles the resolution of satellite images and constructs a deep learning network with a lightweight deep convolutional neural network for fast processing speed. In addition, a feature map fusion method capable of improving the image quality of multispectral (MS) bands using panchromatic (PAN) band information was proposed. The images obtained through the proposed interpolation method improved by about 0.4 dB for the PAN image and about 4.9 dB for the MS image in the quantitative peak signal-to-noise ratio (PSNR) index compared to the existing deep learning-based interpolation methods. In addition, it was confirmed that the time required to acquire an image that is twice the resolution of the 36,500×36,500 input image based on the PAN image size is improved by about 1.6 times compared to the existing deep learning-based interpolation method.

• Geophysics and Geophysical Exploration
• /
• v.26 no.4
• /
• pp.185-198
• /
• 2023

In marine seismic surveys, the inevitable occurrence of trace gaps in the near offset resulting from geometrical differences between sources and receivers adversely affects subsequent seismic data processing and imaging. The absence of data in the near-offset region hinders accurate seismic imaging. Therefore, reconstructing the missing near-offset information is crucial for mitigating the influence of seismic multiples, particularly in the case of offshore surveys where the impact of multiple reflections is relatively more pronounced. Conventionally, various interpolation methods based on the Radon transform have been proposed to address the issue of the nearoffset data gap. However, these methods have several limitations, leading to the recent emergence of deep-learning (DL)-based approaches as alternatives. In this study, we conducted an in-depth analysis of two representative DL-based studies to scrutinize the challenges that future studies on near-offset interpolation must address. Furthermore, through field data experiments, we precisely analyze the limitations encountered when applying previous DL-based trace interpolation techniques to near-offset situations. Consequently, we suggest that near-offset data gaps must be approached by extrapolation rather than interpolation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.650-652
• /
• 2022

Frame rate up-conversion (FRUC) algorithm is an image interpolation technology that improves the frame rate of moving pictures. This solves problems such as screen shake or blurry motion caused by low frame rate video in high-definition digital video systems, and provides viewers with a more free and smooth visual experience. In this paper, we propose a video compression technique using deep learning-based FRUC algorithm. The proposed method compresses and transmits after excluding some images from the original video, and uses a deep learning-based interpolation method in the decoding process to restore the excluded images, thereby compressing them with high efficiency. In the experiment, the compression performance was evaluated using the decoded image and the image restored by the FRUC algorithm after encoding the video by skipping 1 or 3 pages. When 1 and 3 sheets were excluded, the average BD-rate decreased by 81.22% and 27.80%. The reason that excluding three images has lower encoding efficiency than excluding one is because the PSNR of the image reconstructed by the FRUC method is low.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2473-2489
• /
• 2022

Urban development has brought about the increasing saturation of urban traffic demand, and traffic congestion has become the primary problem in transportation. Roads are in a state of waiting in line or even congestion, which seriously affects people's enthusiasm and efficiency of travel. This paper mainly studies the discrete domain path planning method based on the flow data. Taking the traffic flow data based on the highway network structure as the research object, this paper uses the deep learning theory technology to complete the path weight determination process, optimizes the path planning algorithm, realizes the vehicle path planning application for the expressway, and carries on the deployment operation in the highway company. The path topology is constructed to transform the actual road information into abstract space that the machine can understand. An appropriate data structure is used for storage, and a path topology based on the modeling background of expressway is constructed to realize the mutual mapping between the two. Experiments show that the proposed method can further reduce the interpolation error, and the interpolation error in the case of random missing is smaller than that in the other two missing modes. In order to improve the real-time performance of vehicle path planning, the association features are selected, the path weights are calculated comprehensively, and the traditional path planning algorithm structure is optimized. It is of great significance for the sustainable development of cities.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.3
• /
• pp.35-42
• /
• 2022

The N-value from the Standard Penetration Test (SPT), which is one of the representative in-situ test, is an important index that provides basic geological information and the depth of the bearing layer for the design of geotechnical structures. In the aspect of time and cost-effectiveness, there is a need to carry out a representative sampling test. However, the various variability and uncertainty are existing in the soil layer, so it is difficult to grasp the characteristics of the entire field from the limited test results. Thus the spatial interpolation techniques such as Kriging and IDW (inverse distance weighted) have been used for predicting unknown point from existing data. Recently, in order to increase the accuracy of interpolation results, studies that combine the geotechnics and deep learning method have been conducted. In this study, based on the SPT results of about 22,000 holes of ground survey, a comparative study was conducted to predict the depth of the bearing layer using deep learning methods and IDW. The average error among the prediction results of the bearing layer of each analysis model was 3.01 m for IDW, 3.22 m and 2.46 m for fully connected network and PointNet, respectively. The standard deviation was 3.99 for IDW, 3.95 and 3.54 for fully connected network and PointNet. As a result, the point net deep learing algorithm showed improved results compared to IDW and other deep learning method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.183-183
• /
• 2021

Deep learning methods and their application have become an essential part of prediction and modeling in water-related research areas, including hydrological processes, climate change, etc. It is known that application of deep learning leads to high availability of data sources in hydrology, which shows its usefulness in analysis of precipitation, runoff, groundwater level, evapotranspiration, and so on. However, there is still a limitation on microclimate analysis and prediction with deep learning methods because of deficiency of gauge-based data and shortcomings of existing technologies. In this study, a real-time rainfall prediction model was developed from a sky image data set with convolutional neural networks (CNNs). These daily image data were collected at Chung-Ang University and Korea University. For high accuracy of the proposed model, it considers data classification, image processing, ratio adjustment of no-rain data. Rainfall prediction data were compared with minutely rainfall data at rain gauge stations close to image sensors. It indicates that the proposed model could offer an interpolation of current rainfall observation system and have large potential to fill an observation gap. Information from small-scaled areas leads to advance in accurate weather forecasting and hydrological modeling at a micro scale.

• Korean Journal of Materials Research
• /
• v.32 no.8
• /
• pp.345-353
• /
• 2022

In this study, using deep learning, super-resolution images of transmission electron microscope (TEM) images were generated for nanomaterial analysis. 1169 paired images with 256 × 256 pixels (high resolution: HR) from TEM measurements and 32 × 32 pixels (low resolution: LR) produced using the python module openCV were trained with deep learning models. The TEM images were related to DyVO₄ nanomaterials synthesized by hydrothermal methods. Mean-absolute-error (MAE), peak-signal-to-noise-ratio (PSNR), and structural similarity (SSIM) were used as metrics to evaluate the performance of the models. First, a super-resolution image (SR) was obtained using the traditional interpolation method used in computer vision. In the SR image at low magnification, the shape of the nanomaterial improved. However, the SR images at medium and high magnification failed to show the characteristics of the lattice of the nanomaterials. Second, to obtain a SR image, the deep learning model includes a residual network which reduces the loss of spatial information in the convolutional process of obtaining a feature map. In the process of optimizing the deep learning model, it was confirmed that the performance of the model improved as the number of data increased. In addition, by optimizing the deep learning model using the loss function, including MAE and SSIM at the same time, improved results of the nanomaterial lattice in SR images were achieved at medium and high magnifications. The final proposed deep learning model used four residual blocks to obtain the characteristic map of the low-resolution image, and the super-resolution image was completed using Upsampling2D and the residual block three times.