• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.40 no.9
• /
• pp.807-813
• /
• 2016

Recently, a spherical pendulum attached to an end-effector of a robot manipulator has been frequently used for a test bed of residual vibration suppression control in a multi-dimensional motion. However, there was no automatic tracking system to detect the current bob position on-line, and there was inconvenience to not be able to store the bob position in real time and plot the trajectory. In this study, we developed a two-dimensional, real-time bob-detecting system using a digital USB camera, of which the key is hardware component design and software C programming for fast image processing and interfacing. The developed system was applied to residual vibration suppression control of a two-dimensional spherical pendulum that is attached at the end-effector of a two degree-of-freedom SCARA robot, and the effectiveness of the developed system has been demonstrated.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.1
• /
• pp.1-8
• /
• 2022

In this paper, we propose a fire detection system based on CCTV images using an object tracking technology with YOLOv4 model capable of real-time object detection and a DeepSORT algorithm. The fire detection model was learned from 10800 pieces of learning data and verified through 1,000 separate test sets. Subsequently, the fire detection rate in a single image and fire detection maintenance performance in the image were increased by tracking the detected fire area through the DeepSORT algorithm. It is verified that a fire detection rate for one frame in video data or single image could be detected in real time within 0.1 second. In this paper, our AI fire detection system is more stable and faster than the existing fire accident detection system.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.6
• /
• pp.108-116
• /
• 2008

In this paper, we propose the algorithm for making panoramic background and object tacking using pan-tilt-zoom camera. We draw an analogy relation between images for cylinder projection, rearrange of images, stitching, and blending. We can then make the panoramic background, and can track the object use the panoramic background. After generated the background, the proposed algorithm tracks the moving object. Therefore it can detect the wide area, and it tracks the object continuously. So the proposed algorithm is able to use at wide area to detect and track the object.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.1
• /
• pp.100-107
• /
• 2008

This paper proposes a real-time processing method to simplify the image input procedure while extracting and tracing a specified object among multiple ones. In order to extract an object in a specified area among multiple objects of indoor environment and tracing the extracted object continuously, it is verified through experiments that the information interchanged between cameras upwards and in front of it have effect on tracing a specified object continuously. The camera located upward transfers its x-axis data of the input image to the front camera so that the front camera can catch the area of object soon without computing the information of x-axis. The front camera can't resolve the problem of objects overlapping till they share information with the upward camera. The result of the experiment shows that the computation for tracing an object is simplified and the accuracy for extracting and tracing is upgraded.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.437-441
• /
• 2006

본 논문에서는 Active Appearance Model과 EFM을 기반으로 하는 실시간 표정인식 시스템을 설명한다. AAM은 얼굴추적, 얼굴인식 그리고 물체인식과 같은 시스템에 널리 사용되어 지고 있다. 시스템에 사용된 AAM은 Inverse Compositional Image Alignment를 적용한Independent AAM으로서 fitting 속도가 빨라 실시간 시스템에 매우 효과 적이다. 시스템의 성능 평가는 Cohn-Kanade Image DB의 표정영상과 연속영상을 사용하여 실시 하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.319-320
• /
• 2022

교통량이 증가됨에 따라 높아지는 사고율을 줄이기 위해 효율적이며, 다양한 교통 위반 단속이 요구되고 있다. 기존의 유무인 교통법규 위반 단속 시스템의 도입으로 단속 구역 확대를 시도하고 있으나 높은 비용의 문제로 한정된 지역에서만 실시되고 있다. 해당 문제 해결을 위해 본 논문에서는 딥러닝 실시간 객체인식기술을 적용하여 차량의 교통법규 위반을 인식하며 이에 대한 정보를 제공하는 시스템을 개발하였다. 실시간 객체인식 알고리즘인 YOLOv4와 실시간 객체추적기술인 deepSORT 알고리즘을 데스크톱 PC에 적용하여 구현하였다. 개발한 시스템은 과속, 버스 전용 차로, 주정차, 급속 다차선 변경에 대한 인식 결과를 제공한다. 기존 설치된 CCTV 영상을 대상으로 시스템 적용이 가능하여 저비용으로 넓은 지역에 대한 교통법규 위반 상황 인식을 기대할 수 있다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.49-57
• /
• 2022

The government is making great efforts to prevent crimes such as missing children by using public CCTVs. However, there is a shortage of operating manpower, weakening of concentration due to long-term concentration, and difficulty in tracking. In addition, applying real-time object search, re-identification, and tracking through a deep learning algorithm showed a phenomenon of increased parameters and insufficient memory for speed reduction due to complex network analysis. In this paper, we designed the network to improve speed and save memory through the application of Yolo v4, which can recognize real-time objects, and the application of Batch and TensorRT technology. In this thesis, based on the research on these advanced algorithms, OSNet re-ranking and K-reciprocal nearest neighbor for re-identification, Jaccard distance dissimilarity measurement algorithm for correlation, etc. are developed and used in the solution of CCTV national safety identification and tracking system. As a result, we propose a solution that can track objects by recognizing and re-identification objects in real-time within situation of a Korean public multi-CCTV environment through a set of algorithm combinations.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.3C
• /
• pp.271-277
• /
• 2010

In this paper we proposed an object tracking system using PTZ camera. Once the target object is detected, the CAMshift tracking algorithm focuses it in realtime mode as the camera is moving accordingly. Since the CAMShift algorithm takes into account the object size, zoom related tracking is possible. We used the spherical coordinate to gain pan and tilt position. The position information is used to set the center of target object in the middle of the image by using the PTZ protocol and RS-485 interface. Our system showed excellent experimental results in various environments.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.2 no.4
• /
• pp.227-232
• /
• 2007

인간과 상호작용하는 로봇의 경우, 자연스러운 움직임과 행동은 사람에게 친근감을 제공한다. 그러한 자연스러운 움직임과 행동의 기반이 되는 요소기술들 중 하나로 음원추적을 꼽을 수 있다. 본 논문에서는 3개의 마이크를 장착한 로봇에서의 시간지연기반 음원추적 시스템에 대해 소개한다. 개발된 음원추적 시스템을 지능형 서비스 로봇 WEVER-R2에 적용한 결과, 에러율 ${\pm}15$도 이내에서 93% 이상의 성공률을 보였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.1
• /
• pp.151-157
• /
• 2009

This project would discuss how to improve the limit and enhance the accuracy and confidence and the improved algorithm path searching engine module shelter's interference limit on spot searching and analysing by using real time path finding technology and USB memo교 RF which is fused to a Tag(u-Card).