• Transactions of the Korean Society of Automotive Engineers
• /
• 제14권1호
• /
• pp.129-137
• /
• 2006

This paper studies the effects of the swirl for the variation of intake port configuration that is key parameters in the flow field of direct injection diesel engines. In-cylinder flow characteristics is known to have significant effects on air-fuel mixing, combustion, and emissions. To investigate the effects of the swirl flow, various rpm(250, 500, 750) and two different intake port were used. And to evaluate the swirl motion in the flow field visualization engine, steady state flow test was conducted. Helical port intake port and SCV(Swirl Control Valve) were selected as the design parameters to increase the swirl flow and parametric study was performed. In the case of non-SCV, intake flow rate and non-dimensional swirl ratio were higher than those of SCV for the swirl head type. So, we could strengthen the swirl in the flow field with the swirl head type and don't using SCV. From the results of steady state flow test, non-swirl head type has the most good advantage for intake flow rate, and also the flow rate could be increased by using the SCV slightly. The effects of the type of engine head on intake air flow capability are dominant with respect to the existence of the SCV. We could measure the qualitative grade of swirl by capturing the scattering signal of microballoon from ICCD camera in the visualization diesel engine.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권4호
• /
• pp.1904-1926
• /
• 2016

Iris recognition for biometric personnel identification has gained much interest owing to the increasing concern with security today. The image quality plays a major role in the performance of iris recognition systems. When capturing an iris image under uncontrolled conditions and dealing with non-cooperative people, the chance of getting non-ideal images is very high owing to poor focus, off-angle, noise, motion blur, occlusion of eyelashes and eyelids, and wearing glasses. In order to improve the accuracy of iris recognition while dealing with non-ideal iris images, we propose a novel algorithm that improves the quality of degraded iris images. First, the iris image is localized properly to obtain accurate iris boundary detection, and then the iris image is normalized to obtain a fixed size. Second, the valid region (iris region) is extracted from the segmented iris image to obtain only the iris region. Third, to get a well-distributed texture image, bilinear interpolation is used on the segmented valid iris gray image. Using contrast-limited adaptive histogram equalization (CLAHE) enhances the low contrast of the resulting interpolated image. The results of CLAHE are further improved by stretching the maximum and minimum values to 0-255 by using histogram-stretching technique. The gray texture information is extracted by 1D Gabor filters while the Hamming distance technique is chosen as a metric for recognition. The NICE-II training dataset taken from UBRIS.v2 was used for the experiment. Results of the proposed method outperformed other methods in terms of equal error rate (EER).

• The Journal of the Korea Contents Association
• /
• 제12권9호
• /
• pp.93-105
• /
• 2012

Dardenne brothers' films deals with minorities' issues who are shoved out to periphery of society, and especially takes interest in value-deprived human life in labor market of today. This study examines such social awareness of Dardenne brothers targeting their latest works awarded in Cannes Film Festival, , , , , . And analysis is attempted about Dardenne brothers' unique formal aesthetical style that exactly captures such social awareness. In Dardenne brothers' films a person shows up who faces abject matter of living. Their agony is closely connected to unemployment, and shows images of irresistible anxiety and alienation. Dardenne brothers' images are not only simple platform with contents embodied, but designed form showing essential thematic consciousness. Location and gaze, motion of camera capturing a character makes us to reflect the situation a character is facing in the world. There are almost no regard about plots, no dramatic devices, superficial and even straightforward, but Dardenne brothers' films have such independent formal aesthetic, which makes able to give endless tension.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• 제44권6호
• /
• pp.84-92
• /
• 2007

The gait recognition is presented for human identification from a sequence of noisy silhouettes segmented from video by capturing at a distance. The proposed gait recognition algorithm gives better performance than the baseline algorithm because of segmentation of the object by using multiple modules; i) motion detection, ii) object region detection, iii) head detection, and iv) active shape models, which solve the baseline algorithm#s problems to make background, to remove shadow, and to be better recognition rates. For the experiment, we used the HumanID Gait Challenge data set, which is the largest gait benchmarking data set with 122 objects, For realistic simulation we use various values for the following parameters; i) viewpoint, ii) shoe, iii) surface, iv) carrying condition, and v) time.

• Steel and Composite Structures
• /
• 제25권6호
• /
• pp.717-726
• /
• 2017

In this paper, a new simple shear deformation theory for bending analysis of functionally graded plates is developed. The present theory involves only three unknown and three governing equation as in the classical plate theory, but it is capable of accurately capturing shear deformation effects, instead of five as in the well-known first shear deformation theory and higher-order shear deformation theory. A shear correction factor is, therefore, not required. The material properties of the functionally graded plates are assumed to vary continuously through the thickness, according to a simple power law distribution of the volume fraction of the constituents. Equations of motion are obtained by utilizing the principle of virtual displacements and solved via Navier's procedure. The elastic foundation is modeled as two parameter elastic foundation. The results are verified with the known results in the literature. The influences played by transversal shear deformation, plate aspect ratio, side-to-thickness ratio, elastic foundation, and volume fraction distributions are studied. Verification studies show that the proposed theory is not only accurate and simple in solving the bending behaviour of functionally graded plates, but also comparable with the other higher-order shear deformation theories which contain more number of unknowns.

• Smart Media Journal
• /
• 제12권7호
• /
• pp.59-67
• /
• 2023

Recently, research on behavior analysis tracking human posture and movement has been actively conducted. In particular, OpenPose, an open-source software developed by CMU in 2017, is a representative method for estimating human appearance and behavior. OpenPose can detect and estimate various body parts of a person, such as height, face, and hands in real-time, making it applicable to various fields such as smart healthcare, exercise training, security systems, and medical fields. In this paper, we propose a method for classifying four exercise movements - Squat, Walk, Wave, and Fall-down - which are most commonly performed by users in the gym, using OpenPose-based deep learning models, DNN and CNN. The training data is collected by capturing the user's movements through recorded videos and real-time camera captures. The collected dataset undergoes preprocessing using OpenPose. The preprocessed dataset is then used to train the proposed DNN and CNN models for exercise movement classification. The performance errors of the proposed models are evaluated using MSE, RMSE, and MAE. The performance evaluation results showed that the proposed DNN model outperformed the proposed CNN model.

• Journal of Biomedical Engineering Research
• /
• 제44권4호
• /
• pp.255-263
• /
• 2023

Clinical ultrasound (US) is a widely used imaging modality with various clinical applications. However, capturing a large field of view often requires specialized transducers which have limitations for specific clinical scenarios. Panoramic imaging offers an alternative approach by sequentially aligning image sections acquired from freehand sweeps using a standard transducer. To reconstruct a 3D volume from these 2D sections, an external device can be employed to track the transducer's motion accurately. However, the presence of optical or electrical interferences in a clinical setting often leads to incorrect measurements from such sensors. In this paper, we propose a deep learning (DL) framework that enables the prediction of scan trajectories using only US data, eliminating the need for an external tracking device. Our approach incorporates diverse data types, including correlation volume, optical flow, B-mode images, and rawer data (IQ data). We develop a DL network capable of effectively handling these data types and introduce an attention technique to emphasize crucial local areas for precise trajectory prediction. Through extensive experimentation, we demonstrate the superiority of our proposed method over other DL-based approaches in terms of long trajectory prediction performance. Our findings highlight the potential of employing DL techniques for trajectory estimation in clinical ultrasound, offering a promising alternative for panoramic imaging.

• KIPS Transactions on Software and Data Engineering
• /
• 제13권1호
• /
• pp.17-27
• /
• 2024

Video frame interpolation is an important technique used in the field of video and media, as it increases the continuity of motion and enables smooth playback of videos. In the study of video frame interpolation using deep learning, Kernel Based Method captures local changes well, but has limitations in handling global changes. In this paper, we propose a new U-Net structure that applies feature map differentiation and two directions to focus on capturing major changes to generate intermediate frames more accurately while reducing the number of parameters. Experimental results show that the proposed structure outperforms the existing model by up to 0.3 in PSNR with about 61% fewer parameters on common datasets such as Vimeo, Middle-burry, and a new YouTube dataset. Code is available at https://github.com/Go-MinSeong/SF-AdaCoF.

• Journal of radiological science and technology
• /
• 제35권4호
• /
• pp.309-314
• /
• 2012

Nowadays, digital Radiography (DR) systems are widely used in clinical sites and substitute the analog-film x-ray imaging systems. The resolution of DR images depends on several factors such as characteristic contrast and motion of the object, the focal spot size and the quality of x-ray beam, x-ray scattering, the performance of the DR detector (x-ray conversion efficiency, the intrinsic resolution). The DR detector is composed of an x-ray capturing element, a coupling element and a collecting element, which systematically affect the system resolution. Generally speaking, the resolution of a medical imaging system is the discrimination ability of anatomical structures. Modulation transfer function (MTF) is widely used for the quantification of the resolution performance for an imaging system. MTF is defined as the frequency response of the imaging system to the input of a point spread function and can be obtained by doing Fourier transform of a line spread function, which is extracted from a test image. In clinic, radiologic technologists, who are in charge of system maintenance and quality control, have to evaluate or make routine check on their imaging system. However, it is not an easy task for the radiologic technologists to measure MTF accurately due to lack of their engineering and mathematical backgrounds. The objective of this study is to develop and provide for radiologic technologists a medical system imaging evaluation tool, so that they can measure and quantify system performance easily.

• Science of Emotion and Sensibility
• /
• 제14권1호
• /
• pp.1-6
• /
• 2011

A perceptual reaction to human being's gaits has "regularity" that possibly obtains sympathy among people. This thesis is in the vein of the study that performs the research on the quantificational extraction of the regularity, reconstitute the result, and apply it to controlling behavior. The purpose of this thesis lies in assuring the validity of the future research by demonstrating the following hypothesis: when the physical numerical values of the gait "A" whose perceptual reaction is "a" and those of the gait "B" whose perceptual reaction is "b" are arbitrarily blended, the perceptual reaction to this blended gait also corresponds to the blend of "a" and "b", "a/b". I blended the samples of two types of gaits in the form of Bipeds using the EAM made by 3D Studio Max Script. Blending outcomes were obtained successfully for four times out of the six tries in total. It implies that without utilizing other methods such as Motion Capturing, the basic Bipeds data itself has an enough capability to generate various gaits of Bipeds. Although the present research targets only the Bipeds samples equipped with the 1Cycle moving condition of arms and legs, I acknowledge that a tool that makes blending possible under various moving conditions is necessary for a completed system.