• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.898-910
• /
• 2020

Single image-based super-resolution has been studied for a long time in computer vision because of various applications. Various deep learning-based super-resolution algorithms are introduced recently to improve the performance by reducing side effects like blurring and staircase effects. Most deep learning-based approaches have focused on how to implement the network architecture, loss function, and training strategy to improve performance. Meanwhile, Several approaches using Attention Module, which emphasizes the extracted features, are introduced to enhance the performance of the network without any additional layer. Attention module emphasizes or scales the feature map for the purpose of the network from various perspectives. In this paper, we propose the various channel attention and spatial attention in single image-based super-resolution and analyze the results and performance according to the architecture of the attention module. Also, we explore that designing multi-attention module to emphasize features efficiently from various perspectives.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.33-43
• /
• 2022

In this paper, we propose an ensemble model facilitated by multi-channel palm images with attention U-Net models and pretrained convolutional neural networks (CNNs) for establishing a contactless palm-based user identification system using conventional inexpensive camera sensors. Attention U-Net models are used to extract the areas of interest including hands (i.e., with fingers), palms (i.e., without fingers) and palm lines, which are combined to generate three channels being ped into the ensemble classifier. Then, the proposed palm information-based user identification system predicts the class using the classifier ensemble with three outperforming pre-trained CNN models. The proposed model demonstrates that the proposed model could achieve the classification accuracy, precision, recall, F1-score of 98.60%, 98.61%, 98.61%, 98.61% respectively, which indicate that the proposed model is effective even though we are using very cheap and inexpensive image sensors. We believe that in this COVID-19 pandemic circumstances, the proposed palm-based contactless user identification system can be an alternative, with high safety and reliability, compared with currently overwhelming contact-based systems.

• Investigative Magnetic Resonance Imaging
• /
• v.7 no.1
• /
• pp.12-21
• /
• 2003

Purpose : In order to overcome limitations in the existing conventional spectrometer, a new spectrometer with advanced functionalities is designed and implemented. Materials and Methods : We designed a spectrometer using the TMS320C6701 DSP capable of 1 giga floating point operations per second (GFLOPS). The spectrometer can generate continuously varying complicate gradient waveforms by real-time calculation, and select image plane interactively. The designed spectrometer is composed of two parts: one is DSP-based digital control part, and the other is analog part generating gradient and RF waveforms, and performing demodulation of the received RF signal. Each recover board can measure 4 channel FID signals simultaneously for parallel imaging, and provides fast reconstruction using the high speed DSP. Results : The developed spectrometer was installed on a 1.5 Tesla whole body MRI system, and performance was tested by various methods. The accurate phase control required in digital modulation and demodulation was tested, and multi-channel acquisition was examined with phase-array coil imaging. Superior image quality is obtained by the developed spectrometer compared to existing commercial spectrometer especially in the fast spin echo images. Conclusion : Interactive control of the selection planes and real-time generation of gradient waveforms are important functions required for advanced imaging such as spiral scan cardiac imaging. Multi-channel acquisition is also highly demanding for parallel imaging. In this paper a spectrometer having such functionalities is designed and developed using the TMS320C6701 DSP having 1 GFLOPS computational power. Accurate phase control was achieved by the digital modulation and demodulation techniques. Superior image qualities are obtained by the developed spectrometer for various imaging techniques including FSE, GE, and angiography compared to those obtained by the existing commercial spectrometer.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.959-962
• /
• 2005

Efficient video data storage and search techniques are essential for DVR-based security systems. We have designed appropriate data structures and search techniques for efficient image storage and search, in this study. The date and time can be saved and searched as a folder form. The overall system is designed for MPEG4 CODEC. It can handle variable sizes of frames (100bytes $^{\sim}$ 6Kbytes) produced by MPEG4 CODEC without errors. We also have developed image transmission techniques through inter-net networking.

• Economic and Environmental Geology
• /
• v.32 no.1
• /
• pp.33-41
• /
• 1999

A new sedimentary basin is reported from the marine multi-channel seismic data which were acquired for the hydrocarbon exploration on the southwestern Korean continental shelf in 1970. Along the southeastern part of Line 1192, the about 60-km-long basin with the thickness of 0.55~1.1 s is observed on the near-trace gather. However, both new and previous 24-fold stack sections fail to show the basin image probably due to its rugged top beneath the shallow water. The boundary contact between the basement with the velocity of about 5200m/s and the basin filling with the velocities of 4300~4700 m/s is unclear. These velocites are calculated from the corresponding shot gathers. Compared with the Haenam Basin, a neighbouring onshore Cretaceous sedimentary basin, we interpret that the new basin includes the volcanics and volcaniclastic sequences deposited in the lacustrine environment. This nonmarine basin was possibly formed as the result of the tectonic movement during the Cretaceous, implying the wide occurrence of the Cretaceous basins over the southern Korean Peninsula as well as its southwestern continental shelf.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2882-2903
• /
• 2022

Image super-resolution (SR) processing is of great value in the fields of digital image processing, intelligent security, film and television production and so on. This paper proposed a densely connected deep learning network based on cascade architecture, which can be used to solve the problem of super-resolution in the field of image quality enhancement. We proposed a more efficient residual scaling dense block (RSDB) and the multi-channel cascade architecture to realize more efficient feature reuse. Also we proposed a hybrid loss function based on L₁ error and L_∞ error to achieve better L_∞ error performance. The experimental results show that the overall performance of the network is effectively improved on cascade architecture and residual scaling. Compared with the residual dense net (RDN), the PSNR / SSIM of the new method is improved by 2.24% / 1.44% respectively, and the L_∞ performance is improved by 3.64%. It shows that the cascade connection and residual scaling method can effectively realize feature reuse, improving the residual convergence speed and learning efficiency of our network. The L_∞ performance is improved by 11.09% with only a minimal loses of 1.14% / 0.60% on PSNR / SSIM performance after adopting the new loss function. That is to say, the L_∞ performance can be improved greatly on the new loss function with a minor loss of PSNR / SSIM performance, which is of great value in L_∞ error sensitive tasks.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.2
• /
• pp.313-320
• /
• 2018

The importance of sensors on a self-driving vehicle has rising since it act as eyes for the vehicle. Lidar sensors based on laser technology tend to yield better image quality with more laser channels, thus, it has higher detection accuracy for obstacles, pedistrians, terrain, and other vechicles. However, incorporating more laser channels results higher unit price more than ten times, and this is a major drawback for using high channel lidar sensors on a vehicle for actual consumer market. To come up with this drawback, we propose a method of integrating multiple low channel, low cost lidar sensors acting as one high channel sensor. The result uses four 16 channels lidar sensors with small form factor acting as one bulky 64 channels sensor, which in turn, improves vehicles cosmetic aspects and helps widespread of using the lidar technology for the market.

• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.361-368
• /
• 2022

The purpose of this study was to develop a hand rehabilitation training system for hemiplegic patients. We also tried to find out five hand postures (WF: Wrist Flexion, WE: Wrist Extension, BG: Ball Grip, HG: Hook Grip, RE: Rest) in real-time using multi-channel EMG-based deep learning. We performed a pre-processing method that converts to Spider Chart image data for the classification of hand movement from five test subjects (total 1,500 data sets) using Convolution Neural Networks (CNN) deep learning with an 8-channel armband. As a result of this study, the recognition accuracy was 92% for WF, 94% for WE, 76% for BG, 82% for HG, and 88% for RE. Also, ten physical therapists participated for the usability evaluation. The questionnaire consisted of 7 items of acceptance, interest, and satisfaction, and the mean and standard deviation were calculated by dividing each into a 5-point scale. As a result, high scores were obtained in immersion and interest in game (4.6±0.43), convenience of the device (4.9±0.30), and satisfaction after treatment (4.1±0.48). On the other hand, Conformity of intention for treatment (3.90±0.49) was relatively low. This is thought to be because the game play may be difficult depending on the degree of spasticity of the hemiplegic patient, and compensation may occur in patient with weakened target muscles. Therefore, it is necessary to develop a rehabilitation program suitable for the degree of disability of the patient.

• Korean Journal of Remote Sensing
• /
• v.9 no.1
• /
• pp.79-93
• /
• 1993

The relative geostrophic velocity is estimated by using the MCSST(Multi-Channel Sea Surface Temperature) from a NOAA/AVHRR image and applied to the Korea Strait. Remote sensing technique can play a useful role to research for oceanic phenomena because of its synoptic, simultaneous and repetitive viewing. The high resolution data of AVHRR can determine the geostrophic flow more precisely than the hydrographic data on shipboard. As a result of research, the relative geostrophic velocity in the weatern channel of the Korea Strait is the strongest in the trough area and its maximum speed is about 23.8cm/sec in April, 1992. But this results include the error due to neglecting the effect of salinity in estimation the geopotential anomaly. The geostrophic volume transport through the western channel of the Korea Strait is the largest between trough area and the Tsushima Island.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.1
• /
• pp.179-189
• /
• 2000

Recently, due to the increasing interests in deep sea development, all possible efforts to the development of underwater unmanned working vehicles such as AUV(Autonomous Underwater Vehicle) or underwater robot are exerted. This paper proposes a new efficient acoustic-based underwater image data communication system, which ensures a certain level of maximum throughput regardless of the propagation delay of ultrasonic and allowsfast data transmission through the multiple ultrasonic communication channel. Proposed system consists of an acoustic transducer which operates at 136kHz center frequency and it's 10kHz bandwidth, pre-amplifier, $\pi/4 QPSK$(Quadrature Phase Shift Keying) modulation/demodu-lation method, image compressing method using JPEG technique and modified Stop & Wait protocol. The experimental result of the system make it possible to transfer the underwater image as a high throughput at the basin test. The results of test are also verified which allows to desirable transmission performance compared with the existing developed system and the possibility to put the practical use of survey and investigation in the water.