• Journal of Broadcast Engineering
• /
• v.15 no.4
• /
• pp.527-539
• /
• 2010

Most video coding systems use YCbCr color space for their inputs, but RGB space is more preferred in the field of high fidelity video because the compression gain from YCbCr becomes disappeared in the high quality operation region. In order to improve the coding performance of RGB video signal, this paper presents an adaptive frequency-selective weighted prediction algorithm. Based on the sign agreement and the strength of frequency-domain correlation of residual color planes, the proposed scheme adaptively selects the frequency elements as well as the corresponding prediction weights for better utilization of inter-plane correlation of RGB signal. Experimental results showed that the proposed algorithm improves the coding gain of around 13% bitrate reduction, on average, compared to the common mode of 4:4:4 video coding in the state-of-the-art video compression standard, H.264/AVC.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.252-260
• /
• 2016

The performance of human detection system is affected by camera location and view angle. In 2D image acquired from such camera settings, humans are displayed in different sizes. Detecting all the humans with diverse sizes poses a difficulty in realizing a real-time system. However, if the size of a human in an image can be predicted, the processing time of human detection would be greatly reduced. In this paper, we propose a method that estimates human size by constructing an indoor scene in 3D space. Since the human has constant size everywhere in 3D space, it is possible to estimate accurate human size in 2D image by projecting 3D human into the image space. Experimental results validate that a human size can be predicted from the proposed method and that machine-learning based detection methods can yield the reduction of the processing time.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.2
• /
• pp.69-75
• /
• 2012

This paper presents a novel de-interlacing algorithm that can make up motion compensation errors by using maximum a posteriori (MAP) estimator. First, a proper registration is performed between a current field and its adjacent fields, and the progressive frame corresponding to the current field is found via MAP estimator based on the computed registration information. Here, in order to obtain a stable solution, well-known bilateral total variation (BTV)-based regularization is employed. Next, so-called feathering artifacts are detected on a block basis effectively. So, edge-directional interpolation is applied to the pixels where feathering artifact may happen, instead of the above-mentioned temporal de-interlacing. Experimental results show that the PSNR of the proposed algorithm is on average 4dB higher than that of previous studies and provides the better subjective quality than the previous works.

• Journal of Broadcast Engineering
• /
• v.9 no.4 s.25
• /
• pp.434-445
• /
• 2004

Motion Estimation is an essential module in video encoders based on international standards such as H.263 and MPEG. Many fast motion estimation algorithms have been proposed in order to reduce the computational complexity of a well-known full search algorithms(FS). However, these fast algorithms can not work efficiently in DSP processors recently developed for video processing. To solve for this. we propose an efficient motion estimation scheme optimized in the DSP processor like Philips TM1300. A motion vector predictor is pre-estimated and a small search range is chosen in the proposed scheme using strong motion vector correlation between a current macro block (MB) and its neighboring MB's to reduce computation time. An MPEG-4 SP@L3(Simple Profile at Level 3) encoding system is implemented in Philips TM1300 to verify the effectiveness of the proposed method. In that processor, we can achieve better performance using our method than other conventional ones while keeping visual quality as good as that of the FS.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.33-41
• /
• 2022

In this article, we proposed to predict natural gas (NG) leakage levels through feature selection based on a factor analysis (FA) of the integrating the Korean Meteorological Agency data and natural gas leakage data for considering complex factors. The paper has been divided into three modules. First, we filled missing data based on the linear interpolation method on the integrated data set, and selected essential features using FA with OrdinalEncoder (OE)-based normalization. The dataset is labeled by K-means clustering. The final module uses four algorithms, K-nearest neighbors (KNN), decision tree (DT), random forest (RF), Naive Bayes (NB), to predict gas leakage levels. The proposed method is evaluated by the accuracy, area under the ROC curve (AUC), and mean standard error (MSE). The test results indicate that the OrdinalEncoder-Factor analysis (OE-F)-based classification method has improved successfully. Moreover, OE-F-based KNN (OE-F-KNN) showed the best performance by giving 95.20% accuracy, an AUC of 96.13%, and an MSE of 0.031.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.27-36
• /
• 2022

In this paper, to improve the conditions of the fish processing site, we propose a method to predict the cutting point of fish according to the target weight using AI machine vision. The proposed method performs image-based preprocessing by first photographing the top and front views of the input fish. Then, RANSAC(RANdom SAmple Consensus) is used to extract the fish contour line, and then 3D external information of the fish is obtained using 3D modeling. Next, machine learning is performed on the extracted three-dimensional feature information and measured weight information to generate a neural network model. Subsequently, the fish is cut at the cutting point predicted by the proposed technique, and then the weight of the cut piece is measured. We compared the measured weight with the target weight and evaluated the performance using evaluation methods such as MAE(Mean Absolute Error) and MRE(Mean Relative Error). The obtained results indicate that an average error rate of less than 3% was achieved in comparison to the target weight. The proposed technique is expected to contribute greatly to the development of the fishery industry in the future by being linked to the automation system.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.667-671
• /
• 2024

Professional job training for government officers emphasizes establishing desirable values as public officials and improving professionalism in public service. To provide customized education, some studies are analyzed factors affecting education satisfaction. However, there is a lack of research predicting education satisfaction with educational contents. Therefore, we propose a deep learning-based regression model that predicts government officer education satisfaction with educational contents. We use education information data for government officer. We use one-hot encoding to categorize variables collected in text format, such as education targets, education classifications, and education types. We quantify the education contents stored in text format as TF-IDF. We train our deep learning-based regression model and validate model performance with 10-Fold Cross Validation. Our proposed model showed 99.87% accuracy on test sets. We expect that customized education recommendations based on our model will help provide and improve optimized education content.

• Proceedings of The KACE
• /
• 2017.08a
• /
• pp.209-211
• /
• 2017

기계학습은 인공지능(AI, Artificial Intelligence)의 일종으로 다른 인공지능 알고리즘이 정해진 규칙을 기반으로 주어진 임무(Task)를 해결하는 것과는 달리, 기계학습은 수집된 Data를 기반으로 최적의 솔루션을 학습한 후 미래의 값들을 예측하거나 해석하는 방법을 사용하고 있다. 더욱이 인터넷을 통한 연결성의 확대와 컴퓨터의 연산능력 발전으로 가능하게 된 Big-Data를 기반으로 하고 있어 이전의 인공지능 알고리즘에 비해 월등한 성능을 보여주고 있다. 그러나 기계학습 알고리즘이 Data를 학습할 때 학습 결과를 사람이 해석하기에 너무 복잡하여 사람이 그 내부 구조를 이해하는 것은 사실상 불가능하고, 이에 따라 학습된 기계학습 모델의 단점 또는 한계 등을 알지 못하는 문제가 있다. 본 연구에서는 이러한 블랙박스화된 기계학습 알고리즘의 특성을 이해하기 위해, 기계학습 알고리즘이 특정 입력에 대한 결과를 예측할 때 어떤 입력들로 부터 영향을 많이 받는지 그리고 어떤 입력으로부터 영향을 적게 받는지를 알아보는 방법을 소개하고 기존 연구의 단점을 개선하기 위한 방법을 제시한다.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.620-628
• /
• 2020

Automatically predicting video highlight is an important task for media industry and streaming platform providers to save time and cost of manual video editing process. We propose a new ensemble model that combines multiple highlight detectors with each focusing on different parts of highlight events. Therefore, our model can capture more information-rich sections of events. Furthermore, the proposed model can extract improved features for highlight detection particularly when the train video set is small. We evaluate our model on e-sports and baseball videos.

• Explosives and Blasting
• /
• v.22 no.3
• /
• pp.43-55
• /
• 2004

Use term of tower style construction exceeds recently. Accordingly, according to construction safety diagnosis result, achieve removal or Improvement construction. But when work removal, must shorten shut down time. Therefore, removal method of construction to use blasting demolition of construction is very profitable. Influence construction and equipment by blasting vibration and occurrence vibration caused by felling impact. Is using disadvantageous machine removal method of construction by and economic performance by effect of such vibartion. Therefore, this research studied techniques to forecast vibartion level happened at blasting demolition and vibration reduction techniques by use a scaled model test.