• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.4
• /
• pp.53-60
• /
• 2011

This paper proposes fusion methods of license plate detection and super-resolution for improving license plate recognition in low-resolution images. In the proposed method, we apply the license plate detection based on local structure pattern feature and the sequential super-resolution based on Kalman filter. The proposed fusion methods are divided into two according to whether the license plate is detected or not in the input image : (i) performing license plate detection after restoring whole image through super resolution, and (ii) restoring only the detected region through super-resolution after detecting the license plate. We demonstrated effectiveness of the proposed methods in various environments.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.05a
• /
• pp.1047-1051
• /
• 2004

Charge amplifier systems benefit from the very wide dynamic range of PE accelerometers by offering flexibility in adjusting the electrical output characteristics such as sensitivity and range. They are well suited for operation at high temperatures. Modern charge systems feature improved low noise operation, simplified digital controls, and dual mode operation for operation with charge or IEPE voltage mode sensors. high impedance circuitry is not well suited for operation in adverse field or factory environments. The resolution of a PE accelerometer may not be specified or known since noise is a system consideration determined by cable length and amplifier gain. IEPE accelerometrs operate from a constant current power source, provide a high-voltage, low-impedance, fixed mV/g output. They operate through long, ordinary, coaxial cable in adverse environments without degradation of signal quality. They have limited high temperature range. IEPE sensors are simple to operate. Both resolution and operating range are defined specifications. Cost perchannel is lower compared to PE systems since low-noise cable and charge amplifiers are not required.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.363-370
• /
• 1999

Remotely sensed data is regarded as a potentially effective data source for the measurement of water quality and for the environmental change of water bodies. In this study, we measured the spectral reflectance by using multi-spectral image of low resolution camera(LRC) which will be loaded in the OSMI multi-purpose satellite(KOMPSAT) scheduled to be launched on 1999 to use the data in analyzing water pollution. We also investigated the possibility of extraction of water quality factors in water bodies by using remotely sensed low resolution data such as NOAA/AVHRR. In this study, Shiwha-District and Sang-Sam Lake was set up as the subject areas for the study. In this part of the study, we measured the spectral reflectance of the water surface to analyze the radiance of the water bodies in low resolution spectral band and tried to analyze the water quality factors in water bodies by using radiance feature from another remotely sensed data such as NOAA/AVHRR. As the method of this study, first, we measured the spectral reflectance of the water surface by using SFOV( Single Field of View) to measure the reflectance of water quality analysis from every channel in LRC spectral band(0.4~O.9${\mu}{\textrm}{m}$). Second, we investigated the usefulness of ground truth data and the LRC data by measuring every spectral reflectance of water quality factors. Third, we analyzed water quality factors by using the radiance feature from another remotely sensed data such as NOAA/AVHRR. We carried out ratio process of what we selected Chlorophyll-a and suspended sediments as the first factors of the water quality. The results of the analysis are below. First, the amount of pollutants of Shiwha-Lake has been increasing every you since 1987 by factors of eutrophication. Second, as a result of the reflectance, Chlorophyll-a represented high spectral reflectance mainly around 0.52${\mu}{\textrm}{m}$ of green spectral band, and turbidity represented high spectral reflectance at 0.57${\mu}{\textrm}{m}$. But suspended sediments absorbed high at 0.8${\mu}{\textrm}{m}$. Third, Chlorophyll-a and suspended sediments could have a distribution chart as a result of the water quality analysis by using NOAA/AVHRR data.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.446-449
• /
• 2009

In this paper, we present a novel method for reconstructing a super-resolution image using multi-view low-resolution images captured for depth varying scene without requiring complex analysis such as depth estimation and feature matching. The proposed method is based on the iterative back projection technique that is extended to the 3D volume domain (i.e., space + depth), unlike the conventional superresolution methods that handle only 2D translation among captured images.

• Journal of International Society for Simulation Surgery
• /
• v.1 no.2
• /
• pp.57-61
• /
• 2014

We present a robust 3D facial reconstruction method using a single image generated by face-specific super resolution technique. Based on the several consecutive frames with low resolution, we generate a single high resolution image and a three dimensional facial model based on it. To do this, we apply PME method to compute patch similarities for SR after two-phase warping according to facial attributes. Based on the SRI, we extract facial features automatically and reconstruct 3D facial model with basis which selected adaptively according to facial statistical data less than a few seconds. Thereby, we can provide the facial image of various points of view which cannot be given by a single point of view of a camera.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1197-1205
• /
• 2018

In this paper, we perform Single Image Super Resolution(SISR) for acquired images of EOTS or IRST from naval combat system. In order to conduct super resolution, we use Generative Adversarial Networks(GANs), which consists of a generative model to create a super-resolution image from the given low-resolution image and a discriminative model to determine whether the generated super-resolution image is qualified as a high-resolution image by adjusting various learning parameters. The learning parameters consist of a crop size of input image, the depth of sub-pixel layer, and the types of training images. Regarding evaluation method, we apply not only general image quality metrics, but feature descriptor methods. As a result, a larger crop size, a deeper sub-pixel layer, and high-resolution training images yield good performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1141-1162
• /
• 2024

Humidity is an important parameter in meteorology and is closely related to weather, human health, and the environment. Due to the limitations of the number of observation stations and other factors, humidity data are often not as good as expected, so high-resolution humidity fields are of great interest and have been the object of desire in the research field and industry. This study presents a novel super-resolution algorithm for humidity fields based on the Wasserstein generative adversarial network(WGAN) framework, with the objective of enhancing the resolution of low-resolution humidity field information. WGAN is a more stable generative adversarial networks(GANs) with Wasserstein metric, and to make the training more stable and simple, the gradient cropping is replaced with gradient penalty, and the network feature representation is improved by sub-pixel convolution, residual block combined with convolutional block attention module(CBAM) and other techniques. We evaluate the proposed algorithm using ERA5 relative humidity data with an hourly resolution of 0.25°×0.25°. Experimental results demonstrate that our approach outperforms not only conventional interpolation techniques, but also the super-resolution generative adversarial network(SRGAN) algorithm.