• Journal of Broadcast Engineering
• /
• v.13 no.1
• /
• pp.137-151
• /
• 2008

H.264/AVC is showed high coding efficiency more than previous video coding standard by using new coding tools. Specially, Variable block-based motion estimation and Rate-Distortion Optimization are very important coding tools in H.264/AVC. These coding tools have high coding efficiency, however the encoder complexity greatly increase due to these coding tools. In this paper, we propose early SKIP mode decision and selective inter/intra mode decision to reduce the computational complexity. Simulation results show that the proposed method could reduce encoding time of the overall sequences by 30% on average than JM 10.2 without noticeable degradation of coding efficiency. Besides, the proposed method runs over twice as fast as the previous proposed Fast Coding Mode Selection method (FCMS)[5].

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.2
• /
• pp.355-363
• /
• 2011

Recently, as one of several methods to improve the performance of DVC(Distributed Video Coding) system, many research works are focusing on the iterative refinement of side information. Most of the conventional techniques are mainly based on the relationship between the reconstruction level and side information, or the vector median filtering of motion vectors, but, their performance improvements are restricted. In order to overcome the performance limit of the conventional schemes, in this paper, a side information generation scheme is designed by measuring the block-cost estimation. Then, by adaptively selecting the compensation mode using the received bit-plane information, we propose a block-adaptive iterative refinement which is efficient for non-symmetric moving objects. Computer simulations show that, by using the proposed refinement method, the performance can be improved up to 0.2 dB in rate-distortion.

• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.6
• /
• pp.29-38
• /
• 2018

In this paper, we developed a virtual cloth try-on (VTON) technology that segement the cloth image worn on the mannequin and applies it to the user 's photograph. The two-dimensional image-based virtual wear study which does not require three-dimensional information of cloth and model is of practical value, but the research result shows that there are limitations of of the current technology for the problem of occlusion or distortion. In this study, we proposed an algorithm to apply the results obtained from the DNN- based segmentation and posture estimation to the user 's photograph, assuming that the mannequin cloth reduces the difficulties in this part. In order to improve the performance compared with the existing one, we used the validity check of the pre-attitude information, the improvement of the deformation using the outline, and the improvement of the divided area. As a result, a significantly improved result image of more than 50% was obtained.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.4
• /
• pp.434-439
• /
• 2019

This paper proposed a control algorithm to compensate the delay time to improve the signal to noise, and the proposed control algorithm estimate the target information to apply the continuous wave radar equation. The proposed control algorithm improves the output signal of each array element bv multiplying the weight of the receive signal to the signal to noise ratio. Radar radiate a signal in spatial and the target information is estimated by the echoed signal from the target. But the signal in the wireless communication environment occurs the delay time due to the multipath which appear human and natural structures. It is difficult to accurately estimate the desired information because of the degradation for the system performance due to the interference signal and the signal distortion. The target information can be improved by compensating the delay signal to apply the weight to the received signal by using the uniform linear array antenna. As a simulation result, we show that the performance of the proposed control algorithm and the non-compensated delay time are compared. The proposed control algorithm proved that the target distance estimation information is improved.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.1
• /
• pp.19-26
• /
• 2022

This paper presents a pre-processing method to facilitate the container's BIC-code recognition. We propose a network that can find ROI(Region Of Interests) containing a BIC-code region and estimate a homography matrix for warping. Taking the structure of STN(Spatial Transformer Networks), the proposed network consists of next 3 steps, ROI detection, homography matrix estimation, and warping using the homography estimated in the previous step. It contributes to improving the accuracy of BIC-code recognition by estimating ROI and matrix using the proposed network and correcting perspective distortion of ROI using the estimated matrix. For performance evaluation, five evaluators evaluated the output image as a perfect score of 5 and received an average of 4.25 points, and when visually checked, 224 out of 312 photos are accurately and perfectly corrected, containing ROI.

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.172-178
• /
• 2023

In this paper, performance of autoencoder based OFDM communication systems is compared with IEEE 802.11a Wireless Lan System (Wi-Fi). The proposed autoencoder based OFDM system is composed of the following steps. First, one sub-carrier's transmitter - channel - receiver system is created by autoencoder. Then learning process of the one sub-carrier autoencoder generates constellation map. Secondly, using the plural sub-carrier autoencoder systems, parallel bundle is configured with inserting IFFT and FFT before and after the channel to configure OFDM system. Finally, the receiver part of the OFDM communication system was updated by re-learning process for adapting channel condition such as multipath channel. For performance comparison, IEEE802.11a and the proposed autoencoder based OFDM system are compared. For channel estimation, Wi-Fi uses initial long preamble to measure channel condition. but Autoencoder needs re-learning process to create an equalizer which compensate a distortion caused by the transmission channel. Therefore, this autoencoder based system has basic advantage to the Wi-Fi system. For the comparison of the system, additive random noise and 2-wave and 4-wave multipaths are assumed in the transmission path with no inter-symbol interference. A simulation was performed to compare the conventional type and the autoencoder. As a result of the simulation, the autoencoder properly generated automatic constellations with QPSK, 16QAM, and 64QAM. In the previous simulation, the received data was relearned, thus the performance was poor, but the performance improved by making the initial value of reception a random number. A function equivalent to an equalizer for multipath channels has been realized in OFDM systems. As a future task, there is not include error correction at this time, we plan to make further improvements by incorporating error correction in the future.

• Wind and Structures
• /
• v.34 no.2
• /
• pp.231-257
• /
• 2022

Transmission lines systems are important components of the electrical power infrastructure. However, these systems are vulnerable to damage from high wind events such as hurricanes. This study presents the results from a 1:50 scale aeroelastic model of a multi-span transmission lines system subjected to simulated hurricane winds. The transmission lines system considered in this study consists of three lattice towers, four spans of conductors and two end-frames. The aeroelastic tests were conducted at the NSF NHERI Wall of Wind Experimental Facility (WOW EF) at the Florida International University (FIU). A horizontal distortion scaling technique was used in order to fit the entire model on the WOW turntable. The system was tested at various wind speeds ranging from 35 m/s to 78 m/s (equivalent full-scale speeds) for varying wind directions. A system identification (SID) technique was used to evaluate experimental-based along-wind aerodynamic damping coefficients and compare with their theoretical counterparts. Comparisons were done for two aeroelastic models: (i) a self-supported lattice tower, and (ii) a multi-span transmission lines system. A buffeting analysis was conducted to estimate the response of the conductors and compare it to measured experimental values. The responses of the single lattice tower and the multi-span transmission lines system were compared. The coupling effects seem to drastically change the aerodynamic damping of the system, compared to the single lattice tower case. The estimation of the drag forces on the conductors are in good agreement with their experimental counterparts. The incorporation of the change in turbulence intensity along the height of the towers appears to better estimate the response of the transmission tower, in comparison with previous methods which assumed constant turbulence intensity. Dynamic amplification factors and gust effect factors were computed, and comparisons were made with code specific values. The resonance contribution is shown to reach a maximum of 18% and 30% of the peak response of the stand-alone tower and entire system, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.7
• /
• pp.468-474
• /
• 2010

The major factor that disturbs practical use of speech recognition is distortion by the ambient and channel noises. Generally, the ambient noise drops the performance and restricts places to use. DSR (Distributed Speech Recognition) based speech recognition also has this problem. Various noise cancelling algorithms are applied to solve this problem, but loss of spectrum and remaining noise by incorrect noise estimation at low SNR environments cause drop of recognition rate. This paper proposes methods for speech enhancement. This method uses MMSE-STSA for noise cancelling and ideal binary mask to compensate damaged spectrum. According to experiments at noisy environment (SNR 15 dB ~ 0 dB), the proposed methods showed better spectral results and recognition performance.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.11-20
• /
• 2024

Among the generative models in Artificial Intelligence (AI), especially Generative Adversarial Network (GAN) has been successful in various applications such as image processing, density estimation, and style transfer. While the GAN models including Conditional GAN (CGAN), CycleGAN, BigGAN, have been extended and improved, researchers face challenges in real-world applications in specific domains such as disaster simulation, healthcare, and urban planning due to data scarcity and unstable learning causing Image distortion. This paper proposes a new progressive learning methodology called Progressive Step Training (PST) based on the Auxiliary Classifier GAN (ACGAN) that discriminates class labels, leveraging the progressive learning approach of the Progressive Growing of GAN (PGGAN). The PST model achieves 70.82% faster stabilization, 51.3% lower standard deviation, stable convergence of loss values in the later high resolution stages, and a 94.6% faster loss reduction compared to conventional methods.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.5
• /
• pp.635-643
• /
• 2018

This paper propose a method to identify the motor parameters and improve input voltage error which affect the low speed position error of the back-emf(back electromotive force) based sensorless algorithm and to secure the operation reliability and stability even in the case where the load fluctuation is severe and the start and low speed operation frequently occurs. In the model-based observer used in this paper, stator resistance, inductance, and input voltage are particularly influential factors on low speed performance. Stator resistance can cause resistance value fluctuation which may occur in mass production process, and fluctuation of resistance value due to heat generated during operation. The inductance is influenced by the fluctuation due to the manufacturing dispersion and at a low speed where the change of the current is severe. In order to find stator resistance and inductance which have different initial values and fluctuate during operation and have a large influence on sensorless performance at low speed, they are commonly measured through 2-point calculation method by 2-step align current injection. The effect of voltage error is minimized by offsetting the voltage error. In addition, when the command voltage is used, it is difficult to estimate the back-emf due to the relatively large distortion voltage due to the dead time and the voltage drop of the power device. In this paper, we propose a simple circuit and method to detect the voltage by measuring the PWM(Pulse Width Modulation) pulse width and compensate the voltage drop of the power device with the table, thereby minimizing the position error due to the exact estimation of the back-emf at low speed. The suitability of the proposed algorithm is verified through experiment.