• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.76-85
• /
• 2019

We introduce a vision-based object detection method for real-time video surveillance system in low-end edge computing environments. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as Region Convolutional Neural Network(R-CNN) which has two stage for inferencing. On the other hand, one stage detection algorithms such as single-shot detection (SSD) and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as General-Purpose computing on Graphics Processing Unit(GPGPU) is required to still achieve excellent object detection performance and speed. To address hardware requirement that is burdensome to low-end edge computing environments, We propose sub-frame analysis method for the object detection. In specific, We divide a whole image frame into smaller ones then inference them on Convolutional Neural Network (CNN) based image detection network, which is much faster than conventional network designed forfull frame image. We reduced its computationalrequirementsignificantly without losing throughput and object detection accuracy with the proposed method.

• 한국학교보건학회지
• /
• 제31권3호
• /
• pp.167-177
• /
• 2018

Purpose: This study examined the factors that affect suicidal ideation among Korean adolescents according to their family type. Methods: The data of the 2017 Korea Youth Risk Behavior Web-based Survey was used in this study. Out of 62,276, a total of 60,077 adolescents (51,367 adolescents from two-parent families and 8,710 adolescents from single-parent families) were included in the analysis. Results: This study demonstrated that the level of suicidal ideation of the adolescents in single-parent families was significantly higher than that of the adolescents in two-parent families. The factors that affect suicidal ideation among the two-parent family adolescents were gender, grade, economic status, academic performance, smoking, drinking, physical activity, subjective health status, subjective body image, subjective happiness, stress, and depression. The factors that affect suicidal ideation among the single-parent family adolescents included gender, grade, smoking, subjective health status, subjective happiness, stress and depression. Conclusion: Single-parent family adolescents are likely to have a higher level of suicidal ideation along with higher levels of depression and stress and lower levels of subjective health and happiness, compared to single-parent family adolescents. For this higher-risk group of suicidal ideation, more thoughtful attentions and proactive policies are needed to manage their mental health and stress in school and family situations.

• 천문학회지
• /
• 제34권1호
• /
• pp.1-8
• /
• 2001

We present a fast reduction method of survey data obtained using a single-dish radio telescope. Along with a brief review of classical method, a new method of identification and elimination of negative and positive bad channels are introduced using cloud identification code and several IRAF (Image Reduction and Analysis Facility) tasks relating statistics. Removing of several ripple patterns using Fourier Transform is also discussed. It is found that BACKGROUND task within IRAF is very efficient for fitting and subtraction of base-line with varying functions. Cloud identification method along with the possibility of its application for analysis of cloud structure is described, and future data reduction method is discussed.

• 한국가시화정보학회:학술대회논문집
• /
• 한국가시화정보학회 2004년도 Proceedings of 2004 Korea-Japan Joint Seminar on Particle Image Velocimetry
• /
• pp.25-32
• /
• 2004

The new algorithm for higher performance of dynamic PIV has been proposed. Present study considered mathematical basis of PIV analysis for multiple-time-step images and it enables us to analyze the high time-resolution PIV, which is obtained by dynamic PIV system. Conventional single pair image PIV analysis gives us the velocity field data in each time step but it sometimes contains unnecessary information of target flow. Present technique utilize multi-time step correlation information, and it is analyzed.

• 통상정보연구
• /
• 제19권1호
• /
• pp.67-98
• /
• 2017

본 연구의 목적은 미국의 국가이미지와 방문경험이 해외직접구매의도에 미치는 영향을 분석하는 것이다. 국가이미지의 구성요소로써 경제기술이미지, 사회문화이미지 그리고 국민이미지를 사용하였으며, 총 155명의 국내소비자를 대상으로 설문조사를 실시하였다. 데이터분석에는 단순회귀분석, 다중회귀분석 그리고 t검증이 사용되었다. 국가이미지는 해외직구의도를 예측함에 있어 매우 중요한 요인으로 결과가 도출되었으며 다중회귀분석 결과는 국가이미지의 구성요소 중 사회문화이미지가 해외직구의도에 가장 중요한 영향을 미치며, 경제기술이미지 또한 통계적으로 유의한 영향을 미치는 것으로 나타났다. 그러나, 국민이미지는 국내 소비자가 해외직구를 할 때 고려하지 않는 것으로 분석되었다. 미국 방문경험 여부에 따른 해외직구의도에 차이가 있는지 살펴본 결과 이전에 미국을 방문을 경험해 본 소비자는 방문경험이 없는 소비자 보다 해외직구를 할 의향이 높은 것으로 나타났다. 본 연구의 결과는 해외직구 소비자 이해의 폭을 넓히고 해외직판을 계획하고 있는 기업들의 향후 판매전략과 마케팅전략을 수립함에 있어서 유용한 정보를 제공하는데 있다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
• /
• pp.69-72
• /
• 2000

This study proposes a new calculation method for generating real nighttime lamp-lit images. In order to improve the color appearance in the prediction of a nighttime lamp-lighted scene, the lamp-lit image is synthesized based on spectral distribution using the estimated local spectral distribution of the headlamps and the surface reflectance of every object. The principal component analysis method is introduced to estimate the surface color of an object, and the local spectral distribution of the headlamps is calculated based on the illuminance data and spectral distribution of the illuminating headlamps. HID and halogen lamps are utilized to create beam patterns and captured road scenes are used as background images to simulate actual headlamp-lit images on a monitor. As a result, the reproduced images presented a color appearance that was very close to a real nighttime road image illuminated by single and multiple headlamps.

• 한국자동차공학회논문집
• /
• 제8권4호
• /
• pp.158-168
• /
• 2000

Vehicle driving simulators can provide engineers with benefits on the development and modification of vehicle models. One of the most important factors to realistic simulations is the fidelity given by a motion system and a real-time visual image generation system. Virtual reality technology has been widely used to achieve high fidelity. In this paper the virtual environment including a visual system like a head-mounted display is developed for a vehicle driving simulator system by employing the virtual reality technique. virtual vehicle and environment models are constructed using the object-oriented analysis and design approach. Accordint to the object model a three dimensional graphic model is developed with CAD tools such as Rhino and Pro/E. For the real-time image generation the optimized IRIS Performer 3D graphics library is embedded with the multi-thread methodology. Compared with the single loop apprach the proposed methodology yields an acceptable image generation speed 20 frames/sec for the simulator.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.107-109
• /
• 2003

Optical sensor-based land cover categories produce spectral signature confusion along with degraded classification accuracy. In the classification tasks, the goal of fusing data from different sensors is to reduce the classification error rate obtained by single source classification. This paper describes the result of land cover/land use classification derived from solely of Landsat TM (TM) and multisensor image fusion between JERS 1 SAR (JERS) and TM data. The best radar data manipulation is fused with TM through various techniques. Classification results are relatively good. The highest Kappa Coefficient is derived from classification using principal component analysis-high pass filtering (PCA+HPF) technique with the Overall Accuracy significantly high.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2002년도 학술대회지
• /
• pp.377-380
• /
• 2002

This paper presents the results of a study investigating methods of interpretation of wave directionality based on wavelet transforms. Two-dimensional discrete wavelet was used for the analysis. The proposed scheme utilizes a single frame of ocean waves to detect their directionality. This fact is striking considering the fact that traditional methods require long time histories of ocean wave elevation measured at various locations. The developed schemes were applied to the data generated from numerical simulations and video images to test the efficiency of the proposed scheme in detecting the directionality of ocean waves.

• 융합신호처리학회논문지
• /
• 제19권2호
• /
• pp.35-41
• /
• 2018

The analysis of plankton species distribution in sea or fresh water is very important in preserving marine ecosystem health. Since manual analysis is infeasible, many automatic approaches were proposed. They usually use images from in situ towed underwater imaging sensor or specially designed, lab mounted microscopic imaging system. Normally they assume that only single plankton is present in an image so that, if there is a clumping among multiple plankton of same species (homogeneous clumping) or if there are multiple plankton of different species scattered in an image (heterogeneous interspersion), they have a difficulty in recognition. In this work, we propose a deep learning based method that can detect and recognize individual plankton in images with homogeneous clumping, heterogeneous interspersion, or combination of both.