• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.196-204
• /
• 2017

Behavior of intelligent video surveillance system is recognized by analyzing the pattern of the object of interest by using the frame information of video inputted from the camera and analyzes the behavior. Detection of object's certain behaviors in the crowd has become a critical problem because in the event of terror strikes. Recognition of object's certain behaviors is an important but difficult problem in the area of computer vision. As the realization of big data utilizing machine learning, data mining techniques, the amount of video through the CCTV, Smart-phone and Drone's video has increased dramatically. In this paper, we propose a multiple-sliding window method to recognize the cumulative change as one piece in order to improve the accuracy of the recognition. The experimental results demonstrated the method was robust and efficient learning units in the classification of certain behaviors.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.44-48
• /
• 2006

디지털 카메라 기술의 발전과 보급으로 공공건물의 보안 카메라부터 개인 휴대 단말기의 카메라까지 동영상 데이터를 수집할 수 있는 수단이 크게 늘었으며, 그 활용 또한 매우 일반화되었다. 동영상 데이터는 문서나 음성 등의 다른 데이터보다 훨씬 구체적이고 사실적인 정보를 포함하므로 과거의 기억을 정리하고 복원하기 위한 유용한 방법이 될 수 있다. 동영상 데이터의 증가와 함께 동영상 요약에 대한 연구가 최근에 활발히 진행되고 있는데, 이들 연구의 대부분은 하나의 동영상을 요약하고 분석하기 위한 것이다. 본 논문에서는 사무실에 여러 대의 카메라를 설치하여 데이터를 저장하며, 이렇게 수집된 동영상 데이터를 효과적으로 요약하고 검색하는 시스템을 구축한다. 동일한 이벤트를 여러 방향에서 바라보고, 그 상황을 가장 잘 설명한 카메라를 선택 할 수 있다는 점에서 멀티 카메라의 사용은 장점을 갖는다. 사전에 정의된 이벤트에 따라 전문가가 어노테이션을 부여하도록 하였으며, 전문가가 설정한 유틸리티에 따라 카메라 선택 및 요약이 이루어진다. 다양한 옵션에 따라 요약된 결과로 사용자 평가를 수행하였다.

• Journal of Institute of Convergence Technology
• /
• v.8 no.1
• /
• pp.9-13
• /
• 2018

The purpose of this study is to investigate the liquid- and vapor-phase spray characteristics, such as spray tip penetration and spray angle using gasoline direct injection (GDI) injector with multi-hole. The vapor-phase spray was captured by the Schlieren visualization system, which consists of high-speed camera, LED lamp, concave mirrors, and knife-edge. The liquid-phase spray was visualized by Mie-scattering techniques. Both spray images of vapor- and liquid-phase were visualized under 373 K of ambient temperature, 1 bar of ambient pressure, and 100/200 bar of injection pressure. The energizing duration was fixed at 1.5 ms. From the analysis of experimental results, it revealed that the increased injection pressure induced an early vaporization due to the improvement of droplet atomization. The spray tip penetration and spray angle in vapor-phase were higher than those in liquid-phase. The difference in the spray tip penetration between vapor- and liquid-spray gradually increased with the time elapsed after the injection. Even with the spray angle characteristics, it was found that the difference between the spray angle of liquid and vapor spray gradually grew after they entered steady-state conditions.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.1
• /
• pp.137-151
• /
• 2023

Stationary 3D whole-body scanners generally require 5 to 20 seconds of scanning time and cannot effectively detect armpit and crotch areas. Therefore, this study aimed to analyze the accuracy of a photogrammetric technique using a multi-camera system. First, dimensional accuracy was analyzed using a mannequin scan, comparing the differences between the scan-derived measurements and the direct measurements, with an allowable tolerance of ISO 20685-1:2018. Only 2 of 59 measurement items (ankle height and upper arm circumference, specifically) exceeded the ISO 20685-1:2018 criteria. When compared with the results of the eight stationary whole-body scanners assessed by the literature, the photogrammetric technique was found to have the advantage of scanning the top of the head, armpit, and crotch areas clearly. Second, this study found the photogrammetric technique is suitable for obtaining the body scans because it can minimize the perform scanning, resulting in a reduction of measurement errors due to breathing and uncontrolled movements. The error rate of the photogrammetry method was much lower than that of stationary 3D whole-body scanners.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.481-483
• /
• 2023

본 논문에서는 다중 카메라환경에서의 안면인식 기반 영유아 활동 사진 자동 생성 시스템을 개발했다. 개발한 시스템은 어린이집에서 알림장 작성을 위한 촬영하는 동안 보육에 부주의하여 안전사고가 발생하는 것을 방지 할 수 있다. 시스템은 이동식 수집기와 분류 서버로 나뉘어 작동하게 된다. 이동식 수집기는 Raspberry Pi를 이용하였고 초당 1장 내외의 사진을 촬영하여 SAMBA를 사용 공유폴더에 저장한다. 분류 서버에서는 YOLOv5를 사용해 안면을 인식해 분류한다. OpenCV와 TensorFlow-Keras를 통해 분류된 사진에서의 표정을 파악하여 부모에게 전송할 웃는사진만을 분류하여 남겨둔다. 이외의 사진은 /dev/null로 이동하여 삭제된다.

• Tunnel and Underground Space
• /
• v.15 no.1 s.54
• /
• pp.28-38
• /
• 2005

According to the recent development of measurement system utilizing one or a set of boreholes, visualization of the explored underground became to be a major issue. It induced even the introduction of monitoring apparatuses on the borehole wall with multi-function tool, but the usage of these was often limited by where is unfavorable rock condition and a few of engineers can approach. And so, a portable type of borehole camera with only the essential function has been investigated and a few of commercial models about this is recently being applied into the field condition. This paper was based on the monitoring results obtained using a commercial model by Dr. Nakagawa. Discontinuities in rock mass were the topic for the visualization, and it was studied how can visualize their three dimensional distribution and what a numerical formulation is needed and how to understand the visualization result. The numerical formulation was based on the geometric correlation between the dip direction / dip of discontinuous plane and the trend / plunge of borehole, a set of the equation of a plane was induced. As field application of this into two places, it is found that the above visualization methodology will be especially an useful geotechlical tool for analyzing the local distribution of discontinuities.

• International Journal of Highway Engineering
• /
• v.10 no.3
• /
• pp.19-31
• /
• 2008

Video image processing systems(VIPS) offer numerous benefits to transportation models and applications, due to their ability to monitor traffic in real time. VIPS based on wide-area detection, i.e., multi-lane surveillance algorithm provide traffic parameters with single camera such as flow and velocity, as well as occupancy and density. However, most current commercial VIPS utilize a tripwire detection algorithm that examines image intensity changes in the detection regions to indicate vehicle presence and passage, i.e., they do not identify individual vehicles as unique targets. If VIPS are developed to track individual vehicles and thus trace vehicle trajectories, many existing transportation models will benefit from more detailed information of individual vehicles. Furthermore, additional information obtained from the vehicle trajectories will improve incident detection by identifying lane change maneuvers and acceleration/deceleration patterns. The objective of this research was to relate traffic safety to VIPS tracking and this paper has developed a computer vision system of monitoring individual vehicle trajectories based on image processing, and offer the detailed information, for example, volumes, speed, and occupancy rate as well as traffic information via tripwire image detectors. Also the developed system has been verified by comparing with commercial VIP detectors.

• The Journal of Natural Sciences
• /
• v.5 no.1
• /
• pp.87-93
• /
• 1992

A robotically assisted field material handling system designed for loading and unloading of a planar pallet with a forklift in unstructured field environment is presented. The system uses combined acoustic/visual sensing data to define the position/orientation of the pallet and to determine the specific locations of the two slots of the pallet, so that the forklift can move close to the slot and engage it for transport. In order to reduce the complexity of the material handling operation, we have developed a method based on the integration of 2-D range data of Poraloid ultrasonic sensor along with 2-D visual data of an optical camera. Data obtained from the two separate sources complements each other and is used in an efficient algorithm to control this robotically assisted field material handling system . Range data obtained from two linear scannings is used to determine the pan and tilt angles of a pallet using least mean square method. Then 2-D visual data is used to determine the swing angle and engagement location of a pallet by using edge detection and Hough transform techniques. The limitations of the pan and tilt orientation to be determined arc discussed. The system developed is evaluated through the hardware and software implementation. The experimental results are presented.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.3
• /
• pp.95-103
• /
• 2024

The diversity of smart EV(electric vehicle)-related industries is increasing due to the growth of battery-based eco-friendly electric vehicle component material technology, and labor-intensive industries such as logistics, manufacturing, food, agriculture, and service have invested in and studied automation for a long time. Accordingly, various types of robots such as autonomous mobile robots and collaborative robots are being utilized for each process to improve industrial engineering such as optimization, productivity management, and work management. The technology that should accompany this unmanned automobile industry is unmanned automatic charging technology, and if autonomous mobile robots are manually charged, the utility of autonomous mobile robots will not be maximized. In this paper, we conducted a study on the technology of unmanned charging of autonomous mobile robots using charging terminal docking and undocking technology using an unmanned charging system composed of hardware such as a monocular camera, multi-joint robot, gripper, and server. In an experiment to evaluate the performance of the system, the average charging terminal recognition rate was 98%, and the average charging terminal recognition speed was 0.0099 seconds. In addition, an experiment was conducted to evaluate the docking and undocking success rate of the charging terminal, and the experimental results showed an average success rate of 99%.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.438-456
• /
• 2010

Iris recognition uses a unique iris pattern of user to identify person. In order to enhance the performance of iris recognition, it is reported that the diameter of iris region should be greater than 200 pixels in the captured iris image. So, the previous iris system used zoom lens camera, which can increase the size and cost of system. To overcome these problems, we propose a new method of enhancing the accuracy of iris recognition on low-resolution iris images which are captured without a zoom lens. This research is novel in the following two ways compared to previous works. First, this research is the first one to analyze the performance degradation of iris recognition according to the decrease of the image resolution by excluding other factors such as image blurring and the occlusion of eyelid and eyelash. Second, in order to restore a high-resolution iris image from single low-resolution one, we propose a new method based on multiple multi-layered perceptrons (MLPs) which are trained according to the edge direction of iris patterns. From that, the accuracy of iris recognition with the restored images was much enhanced. Experimental results showed that when the iris images down-sampled by 6% compared to the original image were restored into the high resolution ones by using the proposed method, the EER of iris recognition was reduced as much as 0.133% (1.485% - 1.352%) in comparison with that by using bi-linear interpolation