• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.43 no.2 s.344
• /
• pp.42-50
• /
• 2006

Owing to the development of semiconductor processing technology, high density complex circuits can be integrated in a System-on-Chip (SoC). However, increasing energy consumption becomes one of the most important limiting factors. Power estimation at the early stage of design is essential, since design changes at lower levels may significantly lengthen the design period and increase the cost. In this paper, logic level circuits ire levelized and several levels are selected to build power model tables for efficient power estimation. The proposed techniques are applied to a set of ISCAS'85 benchmark circuits to illustrate their effectiveness. Experimental results show that significant improvement in estimation accuracy and slight improvement in efficiency are achieved when compared to those of a well-known existing method. The average estimation error has been reduced from $9.49\%\;to\;3.84\%$.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.12
• /
• pp.103-112
• /
• 2011

Motion estimation (ME) is regarded as an important component in a video encoding process, because it consumes a large computation complexity. H.264/AVC requires additional computation overheads for fractional search and interpolation. This causes a problem that computational complexity is increased. In Motion estimation, SATD(Sum of Transform Difference) has the characteristics of a parabolic based on the minimum point. In this paper, we propose new prediction algorithm to reduce search point in motion estimation by sub-pixel interpolation characteristics. The proposed algorithm reduces the time of encoding process by decreasing computational complexity. Experimental results show that the proposed method reduces 20% of the computation complexity of motion estimation, while the degradation in video quality is negligible.

• Computers and Concrete
• /
• v.33 no.5
• /
• pp.535-544
• /
• 2024

In the rapidly advancing landscape of computer vision (CV) technology, there is a burgeoning interest in its integration with the construction industry. Camera calibration is the process of deriving intrinsic and extrinsic parameters that affect when the coordinates of the 3D real world are projected onto the 2D plane, where the intrinsic parameters are internal factors of the camera, and extrinsic parameters are external factors such as the position and rotation of the camera. Camera pose estimation or extrinsic calibration, which estimates extrinsic parameters, is essential information for CV application at construction since it can be used for indoor navigation of construction robots and field monitoring by restoring depth information. Traditionally, camera pose estimation methods for cameras relied on target objects such as markers or patterns. However, these methods, which are marker- or pattern-based, are often time-consuming due to the requirement of installing a target object for estimation. As a solution to this challenge, this study introduces a novel framework that facilitates camera pose estimation using standardized materials found commonly in construction sites, such as concrete forms. The proposed framework obtains 3D real-world coordinates by referring to construction materials with certain specifications, extracts the 2D coordinates of the corresponding image plane through keypoint detection, and derives the camera's coordinate through the perspective-n-point (PnP) method which derives the extrinsic parameters by matching 3D and 2D coordinate pairs. This framework presents a substantial advancement as it streamlines the extrinsic calibration process, thereby potentially enhancing the efficiency of CV technology application and data collection at construction sites. This approach holds promise for expediting and optimizing various construction-related tasks by automating and simplifying the calibration procedure.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.39-47
• /
• 2023

In this paper, we propose a method to measure the similarity between golf swings in videos. As it is known that deep learning-based artificial intelligence technology is effective in the field of computer vision, attempts to utilize artificial intelligence in video-based sports data analysis are increasing. In this study, the joint coordinates of a person in a golf swing video were obtained using a deep learning-based pose estimation model, and based on this, the similarity of each swing segment was measured. For the evaluation of the proposed method, driver swing videos from the GolfDB dataset were used. As a result of measuring swing similarity by pairing swing videos of a total of 36 players, 26 players evaluated that their other swing sequence was the most similar, and the average ranking of similarity was confirmed to be about 5th. This ensured that the similarity could be measured in detail even when the motion was performed similarly.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.35-43
• /
• 2021

Recently, there has been a growing interest in zero-shot cross-lingual transfer, which leverages cross-lingual language models (CLLMs) to perform downstream tasks that are not trained in a specific language. In this paper, we point out the limitations of the data-centric aspect of quality estimation (QE), and perform zero-shot cross-lingual transfer even in environments where it is difficult to construct QE data. Few studies have dealt with zero-shots in QE, and after fine-tuning the English-German QE dataset, we perform zero-shot transfer leveraging CLLMs. We conduct comparative analysis between various CLLMs. We also perform zero-shot transfer on language pairs with different sized resources and analyze results based on the linguistic characteristics of each language. Experimental results showed the highest performance in multilingual BART and multillingual BERT, and we induced QE to be performed even when QE learning for a specific language pair was not performed at all.

• Journal of Convergence for Information Technology
• /
• v.10 no.9
• /
• pp.15-21
• /
• 2020

This paper presents the outlier detection algorithm in the estimation method of a source location and velocity based on two-step weighted least-squares method using time difference of arrival(TDOA) and frequency difference of arrival(FDOA) data. Since the accuracy of the estimated location and velocity of a moving source can be reduced by the outliers of TDOA and FDOA data, it is important to detect and remove the outliers. In this paper, the method to find the minimum inlier data and the method to determine whether TDOA and FDOA data are included in inliers or outliers are presented. The results of numerical simulations show that the accuracy of the estimated location and velocity is improved by removing the outliers of TDOA and FDOA data.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.3 s.303
• /
• pp.15-22
• /
• 2005

This paper proposed a object tracking algorithm which can track contour of fast moving object through motion estimation. Since the proposed tracking algorithm is based on the radial representation, the motion estimation of object can be accomplished at the center of object with the low computation complexity. The motion estimation of object makes it possible to track object which move fast more than distance from center point to contour point for each frame. In addition, by introducing both gradient image and difference image into energy functions in the process of energy convergence, object tracking is more robust to the complex background. The results of experiment show that the proposed algorithm can track fast moving object in real-time and is robust under the complex background.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.3
• /
• pp.1454-1466
• /
• 2016

This paper implements an estimated ranking algorithm of closeness centrality measures in large-scale workflow-supported social networks. The traditional ranking algorithms for large-scale networks have suffered from the time complexity problem. The larger the network size is, the bigger dramatically the computation time becomes. To solve the problem on calculating ranks of closeness centrality measures in a large-scale workflow-supported social network, this paper takes an estimation-driven ranking approach, in which the ranking algorithm calculates the estimated closeness centrality measures by applying the approximation method, and then pick out a candidate set of top k actors based on their ranks of the estimated closeness centrality measures. Ultimately, the exact ranking result of the candidate set is obtained by the pure closeness centrality algorithm [1] computing the exact closeness centrality measures. The ranking algorithm of the estimation-driven ranking approach especially developed for workflow-supported social networks is named as RankCCWSSN (Rank Closeness Centrality Workflow-supported Social Network) algorithm. Based upon the algorithm, we conduct the performance evaluations, and compare the outcomes with the results from the pure algorithm. Additionally we extend the algorithm so as to be applied into weighted workflow-supported social networks that are represented by weighted matrices. After all, we confirmed that the time efficiency of the estimation-driven approach with our ranking algorithm is much higher (about 50% improvement) than the traditional approach.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.1-7
• /
• 2023

The advent of deep learning technologies has led to the development of various medical applications, making healthcare services more convenient and effective. Among these applications, heart rate estimation is considered a vital method for assessing an individual's health. Traditional methods, such as photoplethysmography through smart watches, have been widely used but are invasive and require additional hardware. Recent advancements allow for contactless heart rate estimation through facial image analysis, providing a more hygienic and convenient approach. In this paper, we propose a lightweight methodology capable of accurately estimating heart rate in mobile environments, using a specialized 2-channel network structure based on 2D convolution. Our method considers both subtle facial movements and color changes resulting from blood flow and muscle contractions. The approach comprises two major components: an Encoder for analyzing image features and a regression layer for evaluating Blood Volume Pulse. By incorporating both features simultaneously our methodology delivers more accurate results even in computing environments with limited resources. The proposed approach is expected to offer a more efficient way to monitor heart rate without invasive technology, particularly well-suited for mobile devices.

• Journal of the Korea Computer Graphics Society
• /
• v.18 no.1
• /
• pp.1-9
• /
• 2012

Video-based modeling / rendering developed to produce photo-realistic video contents have been one of the important research topics in computer graphics and computer visions. To smoothly combine original input video clips and 3D graphic models, geometrical information of light sources and cameras used to capture a scene in the real world is essentially required. In this paper, we present a simple technique to estimate the position and orientation of an optimal light source from the topology of objects and the silhouettes of shadows appeared in the original video clips. The technique supports functions to generate well matched shadows as well as to render the inserted models by applying the estimated light sources. Shadows are known as an important visual cue that empirically indicates the relative location of objects in the 3D space. Thus our method can enhance realism in the final composed videos through the proposed shadow generation and rendering algorithms in real-time.