• Journal of IKEEE
• /
• v.17 no.4
• /
• pp.469-477
• /
• 2013

This paper enhances the speed of a pedestrian detection using an estimation of feature information based on integral image. Pedestrian model or input image should be resized to the size of various pedestrians. In case that the size of pedestrian model would be changed, pedestrian models with respect to the size of pedestrians should be required. Reducing the size of pedestrian model, however, deteriorates the quality of the model information. Since various features according to the size of pedestrian models should be extracted, repetitive feature extractions spend the most time in overall process of pedestrian detection. In order to enhance the processing time of feature extraction, this paper proposes the fast extraction of pedestrian features based on the estimate of integral image. The efficiency of the proposed method is evaluated by comparative experiments with the Channel Feature and Adaboost training using INRIA person dataset.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.178-203
• /
• 2018

In this paper, authors have been evaluated the Frame Error Rate (FER) performance of IEEE 802.11 a/g/p standard 5 GHz frequency band WLAN over Rayleigh and Rician distributed fading channels in presence of Additive White Gaussian Noise (AWGN). Orthogonal Frequency Division Multiplexing (OFDM) based transceiver is implemented by using real-time signal processing frameworks (IEEE 802.11 Blocks) in GNU Radio Companion (GRC) and Ettus USRP N200 is used to process the symbol over the wireless radio channel. The FER is calculated for each sub-carrier conventional modulation schemes used by OFDM such as BPSK, QPSK, 16, 64-QAM with different punctuated coding rates. More precise SNR is computed by modifying the SNR calculation process of YANS and NIST error rate model to estimate more accurate FER. Here, real-time signal constellations, OFDM signal spectrums etc. are also observed to find the effect of multipath propagation of signals through flat and frequency selective fading channels. To reduce the error rate due to the multipath fading effect and Doppler shifting, channel estimation (CE) and equalization techniques such as Least Square (LS) and training based adaptive Least Mean Square (LMS) algorithm are applied in the receiver. The simulation work is practically verified at GRC by turning into a pair of Software Define Radio (SDR) as a simultaneous transceiver.

• Journal of Convergence for Information Technology
• /
• v.10 no.7
• /
• pp.33-40
• /
• 2020

This work tackles the problem of conventional reinforcement learning scheme which has a relatively long training time to reduce energy consumption in underwater network. The enhanced scheme adjusts the learning range of reinforcement learning based on distance estimation. It can be reduce the scope of learning. To take account the fact that the distance estimation may not be accurate due to the underwater wireless network characteristics. this research added noise in consideration of the underwater environment. In simulation result, the proposed AQ-NAV scheme has completed learning much faster than existing method. AQ-NAV can finish the training process within less than 40 episodes. But the existing method requires more than 120 episodes. The result show that learning is possible with fewer attempts than the previous one. If AQ-NAV will be applied in Underwater Networks, It will affect energy efficiency. and It will be expected to relieved existing problem and increase network efficiency.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.6
• /
• pp.110-121
• /
• 2016

The primary aim of the color constancy algorithm is to estimate illuminant chromaticity. There are various statistical-based, learning-based and combinational-based color constancy algorithms already exist. However, the statistical-based algorithms can only perform well on images that satisfy certain assumptions, learning-based methods are complex methods that require proper preprocessing and training data, and combinational-based methods depend on either pre-determined or dynamically varying weights, which are difficult to determine and prone to error. Therefore, this paper presents a new optimization based illuminant estimation method which is free from complex preprocessing and can estimate the illuminant under different environmental conditions. A strong color cast always has an odd standard deviation value in one of the RGB channels. Based on this observation, a cost function called the degree of illuminant tinge(DIT) is proposed to determine the quality of illuminant color-calibrated images. This DIT is formulated in such a way that the image scene under standard illuminant (d65) has lower DIT value compared to the same scene under different illuminant. Here, a swarm intelligence based particle swarm optimizer(PSO) is used to find the optimum illuminant of the given image that minimizes the degree of illuminant tinge. The proposed method is evaluated using real-world datasets and the experimental results validate the effectiveness of the proposed method.

• Nuclear Engineering and Technology
• /
• v.44 no.4
• /
• pp.355-362
• /
• 2012

The aim of this study was to develop a bundle position-wise linear model (BPLM) to predict Pressure Tube (PT) diametral creep employing the previously measured PT diameters and operating conditions. There are twelve bundles in a fuel channel, and for each bundle a linear model was developed by using the dependent variables, such as the fast neutron fluences and the bundle coolant temperatures. The training data set was selected using the subtractive clustering method. The data of 39 channels that consist of 80 percent of a total of 49 measured channels from Units 2, 3, and 4 of the Wolsung nuclear plant in Korea were used to develop the BPLM. The data from the remaining 10 channels were used to test the developed BPLM. The BPLM was optimized by the maximum likelihood estimation method. The developed BPLM to predict PT diametral creep was verified using the operating data gathered from Units 2, 3, and 4. Two error components for the BPLM, which are the epistemic error and the aleatory error, were generated. The diametral creep prediction and two error components will be used for the generation of the regional overpower trip setpoint at the corresponding effective full power days. The root mean square (RMS) errors were also generated and compared to those from the current prediction method. The RMS errors were found to be less than the previous errors.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.205-208
• /
• 2022

Multi-exposure high dynamic range (HDR) image reconstruction, the task of reconstructing an HDR image from multiple low dynamic range (LDR) images in a dynamic scene, often produces ghosting artifacts caused by camera motion and moving objects and also cannot deal with washed-out regions due to over or under-exposures. While there has been many deep-learning-based methods with motion estimation to alleviate these problems, they still have limitations for severely moving scenes. They also require large parameter counts, especially in the case of state-of-the-art methods that employ attention modules. To address these issues, we propose a frequency domain approach based on the idea that the transform domain coefficients inherently involve the global information from whole image pixels to cope with large motions. Specifically we adopt Residual Fast Fourier Transform (RFFT) blocks, which allows for global interactions of pixels. Moreover, we also employ Depthwise Overparametrized convolution (DO-conv) blocks, a convolution in which each input channel is convolved with its own 2D kernel, for faster convergence and performance gains. We call this LFFNet (Lightweight Frequency Fusion Network), and experiments on the benchmarks show reduced ghosting artifacts and improved performance up to 0.6dB tonemapped PSNR compared to recent state-of-the-art methods. Our architecture also requires fewer parameters and converges faster in training.