• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.406-409
• /
• 1993

Integration of intelligent robot workcell is now a hot issue in CIM and robotics area. This paper dealt with relatively low level essential topics. i. e., multi-robot coordination and real-time communication for the integration of intelligent robot workcell. For the coordination of multi-robot system, the tightly-coupled coordination is proposed using the various sensors. In order to handle the numerous communication data, time-critical communication network (field-bus) is introduced and investigated. Finally, intelligent robot workcell is suggested using the mini-MAP and field-bus.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.3
• /
• pp.87-93
• /
• 2019

In this paper, we propose a real-time drone-based violent protest detection system. Our proposed system uses drones to detect scenes of violent protest in real-time. The important problem is that the victims and violent actions have to be manually searched in videos when the evidence has been collected. Firstly, we focused to solve the limitations of existing collecting evidence devices by using drone to collect evidence live and upload in AWS(Amazon Web Service)[1]. Secondly, we built a Deep Learning based violence detection model from the videos using Yolov3 Feature Pyramid Network for human activity recognition, in order to detect three types of violent action. The built model classifies people with possession of gun, swinging pipe, and violent activity with the accuracy of 92, 91 and 80.5% respectively. This system is expected to significantly save time and human resource of the existing collecting evidence.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.619-624
• /
• 2021

Vehicle orientation detection is a challenging task because the orientations of vehicles can vary in a wide range in captured images. The existing methods for oriented vehicle detection require too much computation time to be applied to a real-time system. We propose Rotate YOLO, which has a set of anchor boxes with multiple scales, ratios, and angles to predict bounding boxes. For estimating the orientation angle, we applied angle-related IoU with CIoU loss to solve the underivable problem from the calculation of SkewIoU. Evaluation results on three public datasets DLR Munich, VEDAI and UCAS-AOD demonstrate the efficiency of our approach.

• Educational Technology International
• /
• v.14 no.2
• /
• pp.215-228
• /
• 2013

In engineering education practical experiments is very important for each student, but due to the limitation of time and available resources such as laboratory equipment, space and instructors enough hands-on real experiments could not be provided to all students enrolled in the program throughout the academic year. In this sense web-based remote experiments through internet become a solution for engineering education and an emerging new paradigm for students and teachers. This paper presents the development of the web-based remote vibration experiment system for mechatronics education. Students can access this experimental equipment through an internet and conduct vibration experiment remotely without any restriction on time and place. IP address for data communication and web-service are assigned in local computer and then students receive experimental results and the captured pictures using network. The developed system provides real-time feedback of the tested results. Ubiquitous access to the system gained popularity from students.

• ETRI Journal
• /
• v.9 no.1
• /
• pp.125-137
• /
• 1987

반도체 산업에서는 반도체 소자의 고집적도와 고기능화로 인하여 전반적으로 생산설비의 자동화가 급격히 발달함에 따라 생산라인의 관리자동화가 필연적으로 요구되고 있다. 이것은 컴퓨터 network에 의한 콘트롤과 자동운반 시스팀에 의한 공정제어를 실시하기 때문이다. 이러한 시스팀들의 특징은 feed forward, feed back 에 의한 정확한 공정제어와 on line, real time의 데이터 수집, 해석을 한다. 그러나 전반적인 자동화를 실현하려면 웨이퍼의 자동 handling 기술, 고성능 센서의 개발 등이 문제점으로 남아있다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.10a
• /
• pp.287-287
• /
• 2003

• Proceedings of the KWS Conference
• /
• 2007.11a
• /
• pp.60-62
• /
• 2007

• 한국ITS학회:학술대회논문집
• /
• 2004.11a
• /
• pp.106-110
• /
• 2004

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.2033-2036
• /
• 2004

A novel approach to estimate the real time moving trajectory of an object is proposed in this paper. The object position is obtained from the image data of a CCD camera, while a state estimator predicts the linear and angular velocities of the moving object. To overcome the uncertainties and noises residing in the input data, a Kalman filter and neural networks are utilized. Since the Kalman filter needs to approximate a non-linear system into a linear model to estimate the states, there always exist errors as well as uncertainties again. To resolve this problem, the neural networks are adopted in this approach, which have high adaptability with the memory of the input-output relationship. Kohonen Network(Self-Organized Map) is selected to learn the motion trajectory since it is spatially oriented. The superiority of the proposed algorithm is demonstrated through the real experiments.

• Journal of Industrial Technology
• /
• v.22 no.A
• /
• pp.73-82
• /
• 2002

It is difficult to find the shortest paths using existing algorithms (Dijkstra, Floyd-Warshall algorithm, and etc) in high complex and large size real traffic networks The objective of this paper is to develop an evolution program to find the multiple shortest paths within reasonable time in these networks including turn-restrictions, U-turns, and etc.