• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3823-3840
• /
• 2020

Recently, auto-encoder has emerged as the most popular method in convolutional neural network (CNN) based image compression and has achieved impressive performance. In the traditional auto-encoder based image compression model, the encoder simply sends the features of last layer to the decoder, which cannot allocate bits over different spatial regions in an efficient way. Besides, these methods do not fully exploit the contextual information under different receptive fields for better reconstruction performance. In this paper, to solve these issues, a novel auto-encoder model is designed for image compression, which can effectively transmit the hierarchical features of the encoder to the decoder. Specifically, we first propose an adaptive bit-allocation strategy, which can adaptively select an importance channel. Then, we conduct the multiply operation on the generated importance mask and the features of the last layer in our proposed encoder to achieve efficient bit allocation. Moreover, we present an additional novel perceptual loss function for more accurate image details. Extensive experiments demonstrated that the proposed model can achieve significant superiority compared with JPEG and JPEG2000 both in both subjective and objective quality. Besides, our model shows better performance than the state-of-the-art convolutional neural network (CNN)-based image compression methods in terms of PSNR.

• Journal of Korea Water Resources Association
• /
• v.45 no.2
• /
• pp.127-136
• /
• 2012

River is able to change by various environmental factors. In order to conduct river restoration design, it is necessary to evaluate the stable channel through the analysis of past and present river channels. River evaluation requires various data, such as geometry, hydraulic and hydrology, but there is a lot of difficulty to understand topographical information of river change on time and space due to a lack of past data by domestic conditions. This study was analyzed abandoned channel formation, changes in the vertical-section and cross-section length of rivers, and micro-landform changes etc using an image analysis technique. Purpose of this research is to evaluates the stable channel through a river channel morphology change from past and present river channels image. Mangyoung river was conducted artificial river maintenance through straight channel consolidation form 1920 to 1930 year. In the result river maintenance, mangyoung river length was decreased by 15 km and abandoned channels of six points were made. Since then, weir was continuously increased to control bed slope and use water. Install of weir was to be the reason of changes on channel width, thalweg, vegetated bar, sand bar, water area. Present Mangyoung river show that water area was temporary increased in upper and middle reach because of weir installation. Total sand bar was only decreased in upper channel. The change of vegetated bar and sand bar was slight recently. In this result, Mangyoung river is inferred to reach stabilized channel although there is some difference to the lower reach.

• ETRI Journal
• /
• v.34 no.1
• /
• pp.17-23
• /
• 2012

This paper analyzes the feasibility of a new 3DTV broadcasting service scenario via Advanced Television Systems Committee Mobile/Handheld (ATSC-M/H). We suggest a dual-channel system in which a left-view image is encoded by MPEG-2 with HD quality and a small-sized right-view image is encoded by AVC. Also, the left view is transmitted through ATSC main channel and the right view is transmitted through ATSC-M/H channel. Although the transport stream formats of two channels are different from each other, we demonstrate that it is possible for the ATSC 2.0 decoder to synchronize the display of the left and right views when both encoders use a common wall clock and time stamp. We also propose a program specific information descriptor which guarantees full compatibility with the conventional 2D HDTV and emerging mobile TV services. Finally, we provide the results of subjective visual quality assessment of the proposed system in support of its 3DTV service quality.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.12
• /
• pp.1730-1736
• /
• 2015

This paper presents a 16-channel transimpedance amplifier (TIA) array implemented in a standard $0.18-{\mu}m$ CMOS technology for the applications of panoramic scan LADAR (PSL) systems. Since this array is the front-end circuits of the PSL systems to recover three dimensional image for unmanned vehicles, low-noise and high-gain characteristics are necessary. Thus, we propose a voltage-mode inverter TIA (I-TIA) array in this paper, of which measured results demonstrate that each channel of the array achieves $82-dB{\Omega}$ transimpedance gain, 565-MHz bandwidth for 0.5-pF photodiode capacitance, 6.7-pA/sqrt(Hz) noise current spectral density, and 33.8-mW power dissipation from a single 1.8-V supply. The measured eye-diagrams of the array confirm wide and clear eye-openings up to 1.3-Gb/s operations. Also, the optical pulse measurements estimate that the proposed 16-channel TIA array chip can detect signals within 20 meters away from the laser source. The whole chip occupies the area of $5.0{\times}1.1mm^2$ including I/O pads. For comparison, a current-mode 16-channel TIA array is also realized in the same $0.18-{\mu}m$ CMOS technology, which exploits regulated-cascode (RGC) input configuration. Measurements reveal that the I-TIA array achieves superior performance in optical pulse measurements.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.12
• /
• pp.2355-2362
• /
• 2016

Seg fog removal is an important issue concerned by both computer vision and image processing. Sea fog or haze removal is widely used in lots of fields, such as automatic control system, CCTV, and image recognition. Color image dehazing techniques have been extensively studied, and expecially the dark channel prior(DCP) technique has been widely used. This paper propose a fast and efficient image prior - dark channel prior to remove seg-fog from a single digital image based on the GPU. We implement the basic parallel program and then optimize it to obtain performance acceleration with more than 250 times. While paralleling and the optimizing the algorithm, we improve some parts of the original serial program or basic parallel program according to the characteristics of several steps. The proposed GPU programming algorithm and implementation results may be used with advantages as pre-processing in many systems, such as safe navigation for ship, topographical survey, intelligent vehicles, etc.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.10
• /
• pp.59-70
• /
• 2010

Each pixels become got pixel value for color of only one from among colors because of bayer pattern that light receiving device of image sensor which is used in HHP and digital camera writes only one color. Information of the missing pixels could infer perfect color image from using information of neighbor pixels by using CFA(Color Filter Array). In this paper, we derive relation between the average of the data from the light receiving device of image sensor and each color channel data. And by using this relation, a new efficient edge color fuzzy method for color interpolation is proposed. Also, missing luminance signal channel interpolation was fuzzy interpolation along any edges direction for reducing color noise and interpolating efficiently it. And in this paper, the proposed method has been proved improving average 2.4dB than the conventional method by using PSNR. Also, resolution of the image of the proposed method was similar to the original image by visual images, we has been verified to be decreased a chromatic aberration than image of conventional algorithms with simulation result.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.2
• /
• pp.206-212
• /
• 2006

Many image and video compression algorithms work by splitting the input image into blocks and producing variable-length coded bits for each block data. If variable-length coded data are transmitted consecutively, then the resulting coder is highly sensitive to channel errors. Therefore, most image and video techniques for providing some protection to the stream against channel errors usually involve adding a controlled amount of redundancy back into the stream. Such redundancy might take the form of resynchronization markers, which enable the decoder to restart the decoding process from the known state, in the event of transmission errors. The Error Resilient Entropy Code (EREC) is a well known method which can regain synchronization without any redundant information to convert from variable-length code to fixed-length code. This paper proposes an enhancement to EREC, which greatly improves its transmission ability for the compressed image quality without any redundant bits in the event of errors. The simulation result shows that the both objective and subjective quality of transmitted image is enhanced compared with the existing EREC at the same BER(Bit Error Rate).

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.1-9
• /
• 2019

The image obtained from systems such as autonomous driving cars or fire-fighting robots often suffer from several degradation such as noise, motion blur, and compression artifact due to multiple factor. It is difficult to apply image recognition to these degraded images, then the image restoration is essential. However, these systems cannot recognize what kind of degradation and thus there are difficulty restoring the images. In this paper, we propose the deep neural network, which restore natural images from images degraded in several ways such as noise, blur and JPEG compression in situations where the distortion applied to images is not recognized. We adopt the channel attention modules and skip connections in the proposed method, which makes the network focus on valuable information to image restoration. The proposed method is simpler to train than other methods, and experimental results show that the proposed method outperforms existing state-of-the-art methods.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.3
• /
• pp.203-213
• /
• 2023

In medical ultrasound imaging systems, Side lobes may appear if signals outside the imaging point are not completely removed during receive focusing. If the time signal of the side lobe overlaps with the time signal (main lobe) from the image point, it is difficult to completely remove it using filter processing in the time domain. However, In the receive focusing process, when time-channel signals are Fourier-transformed, the main lobe and side lobe signals are spatially separated in the spectral domain. Therefore, the side lobes can be suppressed by multiplying the image with magnitude weights, which are determined by the magnitudes of the main and side lobes calculated in the spectral domain. In addition, when the main lobe and the side lobe spectrum are adjacent, the distance weight was applied based on the distance between them. In a 5 MHz ultrasound imaging system using a 64-channel linear transducer, point reflector and speckle images with cysts of various brightness were synthesized and weights were applied to the ultrasound image. Using computer simulations, we confirmed that the side lobes were greatly reduced without affecting the spatial resolution in the point reflector image, and the contrast was significantly improved in the cyst image with computer simulations.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.4
• /
• pp.362-370
• /
• 2001

In this paper, we proposed multispectral image compression method using CIP (classified inter-channel prediction) and SVQ (selective vector quantization) in wavelet domain. First, multispectral image is wavelet transformed and classified into one of three classes considering reflection characteristics of the subband with the lowest resolution. Then, for a reference channel which has the highest correlation and the same resolution with other channels, the variable VQ is performed in the classified intra-channel to remove spatial redundancy. For other channels, the CIP is performed to remove spectral redundancy. Finally, the prediction error is reduced by performing SVQ. Experiments are carried out on a multispectral image. The results show that the proposed method reduce the bit rate at higher reconstructed image quality and improve the compression efficiency compared to conventional methods. Index Terms-Multispectral image compression, wavelet transform, classfied inter-channel prediction, selective vetor quantization, subband with lowest resolution.