• Proceedings of the KIEE Conference
• /
• 2005.05a
• /
• pp.182-184
• /
• 2005

An embedded system has been applied to many fields including households and industrial sites. The embedded system is implemented fur image tracking in security area. This system supports a fixed IP far the reliable server operation on TCP/IP networks. A real time video image on the is analyzed to detect a certain invader who jumped into the observed area. The digital camera is connected at the USB host port of the target board. The video images from the video camera is continuously analyzed and displayed at the Linux web-server. The moving vector of the invaders on the continuous image frames is calculated and then it sends the calculated pan/tilt movement. That used Block matching algorithm and edge detection algorithm for past speed. And the displacement vector is used at pan/tilt motor control through RS232 serial cable. The experiment result showed tracking performance by the moving part speed of 10 to 150 pixels/sec.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.11 no.2
• /
• pp.302-312
• /
• 2000

Digital TV tuner for 8-VSB modulation was developed with satisfying the requirements of ATSC. Double frequency conversion and active tracking filter was used in order to suppress IF beat and image band, which results in reducing the interference between adjacent channels and multi-channels. The implemented digital TV tuner has excellent performance such as the wide dynamic range, good flatness in passing band, and low phase noise. The developed tuner is available to handle the digital and analogue television signal at the same time.

• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.297-302
• /
• 2012

In this paper, we present a object detection and tracking method based on image context analysis. It is robust from the image variations such as complicated background, dynamic movement of the object. Image context analysis is carried out using the hybrid network of k-means and RBF. The proposed object detection employs context-driven adaptive Bayesian framework to relive the effect due to uneven object images. The proposed method used feature vector generator using 2D Haar wavelet transform and the Bayesian discriminant method in order to enhance the speed of learning. The system took less time to learn, and learning in a wide variety of data showed consistent results. After we developed the proposed method was applied to real-world environment. As a result, in the case of the object to detect pass outside expected area or other changes in the uncertain reaction showed that stable. The experimental results show that the proposed approach can achieve superior performance using various data sets to previously methods.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.139-147
• /
• 2022

The goal of this study is to develop a mobile application so that a person who is new to chemistry can easily acquire the knowledge necessary for chemical structure learning using image tracking technology. The point of this study is to provide a new chemical structure learning experience by recognizing a two-dimensional picture, augmenting the chemical structure into a three-dimensional object, showing it on the user's screen, and using a service that simultaneously provides related information in multiple fields. characteristic. Login API and real-time database technology were used for safe and real-time data management, and an application was developed using image tracking technology for image recognition and 3D object augmentation service. In the future, we plan to use the chemical structure data library to efficiently load and output data.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.43 no.4
• /
• pp.87-97
• /
• 2015

There's a trend towards vitalization of nightscape planning businesses nationally and locally as well for city image making and activation of regional economy, but there is still no systematic nightscape planning going on for lack of relevant researches and objective evaluations. This study aims to suggest the guideline for nightscape planning by conducting an eye tracking experiment and survey for recognizing the characteristics of a nightscape. Furthermore, the authors intended to verify the eye-tracking method as a tool for landscape evaluation. The research site was restricted in the campus of Virginia Tech, VA, and those were selected by experts' survey among various types of nightscape images. The variables for analyzing the characteristics of nightscape images selected were 'preference', 'safety(fear)' and 'clearness'. 'Fixation duration', 'saccade duration', 'scan path length', and 'pupil size' were selected as the eye movement measurements. The results of this study are as follows: The first outcome found was that there were significant differences among the characteristics(preference, safety and clearness) of a nightscape by MANOVA, and these variables were correlated positively by Pearson's correlation. Secondly, there were differences on fixation duration, saccade duration and scan path depending on the nightscape setting statistically. Also, the eye tracking measurement in an open setting was recorded lower than enclosed settings. In the result of a heat map, we found the meaning of the fixated areas on both viewing without intention and viewing intentionally. It turned out that the fixated areas were consistent with the areas the subjects felt preferred and clarity in all of the nightscape images, which means people usually focus on what they prefer and see clearly in a certain nightscape. Based on this result and previous studies, the authors could make a conclusion that eye tracking method can apply to evaluate nightscape settings in terms of analyzing the whole characteristics and finding specific points for the detailed analysis as well. Therefore, these results can contribute by suggesting nightscape planning, implication of the landscape evaluation, and implication of the eye tracking study.

• Korean Journal of Construction Engineering and Management
• /
• v.18 no.2
• /
• pp.21-29
• /
• 2017

Recently, with having a great interest of the general public for the AR (Augmented Reality) technology, there have been lots of study to improve efficiency of a construction equipment with applying the AR technology to a construction equipment. The clear extrinsic calibration is essential to applying AR technology at the construction site without any error which came from superimposition between 'Real world' and 'Virtual world'. However, on the construction site, the clear extrinsic calibration is not possible, because of lack of time and budget for the specific survey, also, the huge error of the outdoor tracking system such as gyro, GPS system and so on. In this study, we do research about seamless superposition with unclear extrinsic calibration and the image process method for making AR navigator operating in the excavator. Based on this study, we figure that we can fully develop the AR navigator for the excavator. Furthermore, thereby operating AR navigator at many construction sites, we expect that the efficiency of the excavator will be improved. In addition, we can develop AR navigator for not only a excavator but all about construction equipment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1563-1566
• /
• 2015

보안과 관련된 기술이 발전하여 대규모의 장소에 적합한 보안시스템들이 많이 개발되었다. 특히 CCTV를 이용한 감시카메라의 형태도 다양화되었다. 스마트폰의 어플리케이션이나 웹을 통해서 어디서든 감시할 수도 있어, 이를 통해 보안사고 시에 빠른 대처가 가능하다. 하지만 대규모 시스템이 아닌 경우에는 침입자 발견이 늦고, 뒤늦은 대처로 인해 큰 피해가 발생할 수 있다. 라즈베리파이, 실드 보드 등 기타 하드웨어들을 통하여 침입자를 스스로 감지하여 사용자에게 즉시 알림을 전송함으로써 보안사고에 대한 대처를 빠르고 효율적으로 할 수 있는 보안카메라를 구현하였다. 본 보안 시스템은 소리의 방향을 계산하고 정확한 방향으로의 보정을 통하여 최초 침입자를 인식한다. 이후 이미지트래킹을 통하여 침입자를 추적한다. 무선 네트워크를 이용하기 때문에 네트워크가 지원되는 어느 장소에서든지 사용이 가능하다. 대규모 보안시스템을 설치할 여건이 되기 어려운 작은 공장, 상가, 사무실 등에서 보안시스템으로 사용되면 유용할 것이다. 자세한 개발 내용은 본문에 기술한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.11
• /
• pp.724-731
• /
• 2016

The purpose of this study was to determine what rules or patterns exist when people gaze at a villa savoye, which is probably Le Corbusier's best known building, using eye-movement tracking techniques. Villa savoye was designed, addressing his emblematic "Five Points", such as pilotis, functional roofs, free floor plans, long horizontal windows, and freely-designed facades. This study examined how the villa savoye's facade image is formed in an objective manner. This study selected a total of 56 test subjects, and showed them an image of a villa savoye. Using eye-movement tracking tools, this study recorded where they mostly gazed at when seeing the building. In addition, an experiment was carried out to test the different points of view, relating to visual attention, between the two groups with different levels of knowledge in architecture. To analyze the data, the Gaze Frequency was used as the key indicator. The results showed that the subjects have a higher degree of attention to either the door or window in general than in former studies. The architecture major group showed that they gazed the experiment image more evenly.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.45-55
• /
• 2021

This paper has proposed an algorithm that detecting for dense small vehicle in large image efficiently. It is consisted of two Ensemble Deep-Learning Network algorithms based on Coarse to Fine method. The system can detect vehicle exactly on selected sub image. In the Coarse step, it can make Voting Space using the result of various Deep-Learning Network individually. To select sub-region, it makes Voting Map by to combine each Voting Space. In the Fine step, the sub-region selected in the Coarse step is transferred to final Deep-Learning Network. The sub-region can be defined by using dynamic windows. In this paper, pre-defined mapping table has used to define dynamic windows for perspective road image. Identity judgment of vehicle moving on each sub-region is determined by closest center point of bottom of the detected vehicle's box information. And it is tracked by vehicle's box information on the continuous images. The proposed algorithm has evaluated for performance of detection and cost in real time using day and night images captured by CCTV on the road.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.2
• /
• pp.235-240
• /
• 2015

Active Safety system is requested on the market of the medium and heavy duty commercial vehicle over 4.5ton beside the market of passenger car with advancement of the digital equipment proportionally. Unlike the passenger car, the mounting position of camera in case of the medium and heavy duty commercial vehicle is relatively high, it is disadvantaged conditions for lane recognition in contradiction to passenger car. In this work, we show the method of lane recognition through the Sobel edge, based on the spatial domain processing, Hough transform and color conversion correction. Also we suggest the low error method of front vehicles recognition in order to reduce the detection error through Haar-like, Adaboost, SVM and Template matching, etc., which are the object recognition methods by frontal camera vision. It is verified that the reliability over 98% on lane recognition is obtained through the vehicle test.