• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.8
• /
• pp.2062-2072
• /
• 1994

This paper presents the development of a fuzzy controller for driving camera pan/tilt device so that the camera's viewing direction can automatically track a moving object. To achieve computational efficiency a non-contact type displacement follower is used as a feedback sensor instead of a vision camera. The displacement follower, however, is extremely sensitive to object's lighting condition and results in unstable response at high speed. To this end, a fuzzy controller is developed in such a way to provide stable tracking performance at high speed where the sensory signal is subjected to intermittant disturbances of large magnitude. The test result shows stable tracking response even for high speed and non-uniform lighting condition. The resulting camera autotracking system can be adopted as an effective tool for visual transfer in the context of teleoperation and autonomous robotics.

• Electronics and Telecommunications Trends
• /
• v.20 no.5 s.95
• /
• pp.1-15
• /
• 2005

음성인터페이스 기술이란 인간의 가장 자연스러운 의사소통 수단 중의 하나인 ‘말’을이용하여 기계와 인간과의 대화를 가능하게 하는 기술이다. 음성인터페이스 기술에 대한 연구는 1960년대부터 이루어져 왔으며 1990년대 후반부터 제한적으로 상용화되기 시작하였다. 아직까지는 기술적 한계에 의해서 간단한 명령어를 알아들을 수 있는 수준이며 응용 분야도 극히 제한되어 있으나 향후 텔레매틱스, 지능형로봇, 홈오토메이션등의 신성장동력 산업이 활성화됨에 따라 기존의 키보드, 마우스 등의 인터페이스 수단들이 충분히 만족스럽지 않은 환경으로 변화하면서, 음성인터페이스 기술은 매우 중요한 대안으로 떠오르고 있다. 본 고에서는 음성인터페이스 기술의 기본 원리 및 요소기술을 설명하고 관련 산업동향 및 응용분야, 그리고 향후 신성장동력 산업을 중심으로 한 발전 전망을 예측해본다.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.264-266
• /
• 2009

A skill is defined as the special ability to do something well, especially as acquired by learning and practice. To learn a skill, a Bayesian network model for representing the skill is first learned. We will regard the Bayesian network for a skill as an affordance. We propose a soft Behavior Motivation(BM) switch as a method for ordering affordances to accomplish a task. Then, a skill is constructed as a combination of an affordance and a soft BM switch. To demonstrate the validity of our proposed method, some experiments were performed with GENIBO(Pet robot) performing a task using skills of Search-a-target-object, Approach-a-target-object, Push-up-in front of -a-target-object.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.811-813
• /
• 2005

무인 자동차 시스템과 같은 실시간 제어 환경에서는 각종 센서의 상황에 대한 주기적인 폴링, 실시간 스케줄링, 병행 메소드의 지원 실시간 병행 접근 제어 등과 같은 환경이 요구된다. 본 논문에서는 micro 내장형 운영체제상의 실시간 객체 엔진으로 개발한 TMO-eCos를 기반으로, TMO를 이용한 무인 자동차 제어프레이워크와 이를 활용한 응용 모델에 대해 기술한다. TMO 모델을 이용한 무인 자동차 제어 프레임워크는 실시간 제어 시스템 개발을 위한 객체 기반의 규격적 환경을 제공하여, 최근 국내외적으로 많은 연구가 진행되고 있는 지능헝 실시간 로봇 제어소프트웨어의 기본 플랫폼으로 활용될 수 있을 것이다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.435-436
• /
• 2009

RFID 시스템의 미들웨어는 태그에서 생성된 방대한 양의 데이터를 리더를 통해 전달받는다. RFID 미들웨어는 이러한 데이터를 정제하여 응용 애플리케이션에 전달하는 기능을 담당한다. 하지만 태그 데이터 정제 과정에서 발생되는 지연 시간은 RFID 미들웨의 응답성을 저하시킨다. 본 논문은 EPCglobal 의 RFID 미들웨어 표준인 ALE 에 의거하여 태그 데이터에 대한 다수의 필터링 조건들이 주어진 RFID 미들웨어 환경에서 실시간으로 수집되는 대용량의 태그에 대한 고속 필터링 엔진을 설계한다. 이를 위하여 Intermediate node 들이 key 값을 저장하는 Binary Search Tree 형태를 구성하여 태그를 필터링하는 방법을 제안한다. 결과로써 기존의 순차적인 RFID 데이터 필터링에 비해 고속의 필터링 성능을 보이며 특히 필터의 수가 증가할수록 필터링의 효율이 높아짐을 보인다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.1308-1310
• /
• 2011

실내용 IR-UWB 레이더를 기반한 침입 탐지, 추적 시스템을 지원하기 위한 미들웨어 설계를 제안한다. 이 미들웨어의 설계는 다수의 측정 구역으로부터 받은 연속적인 데이터의 관리에 초점이 있다. 효율적인 데이터 관리를 위해 레이더 소프트웨어 플랫폼을 기능적으로 구분하여 설계하고 연동하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.493-494
• /
• 2022

The development of livestock faces intensive farming results in a rising need for recognition of individual animals such as cows and pigs is related to high traceability. In this paper, we present a non-invasive biometrics systematic approach based on the deep-learning classification model to pig face identification. Firstly, in our systematic method, we build a ROS data collection system block to collect 10 pig face data images. Secondly, we proposed a preprocessing block in that we utilize the SSIM method to filter some images of collected images that have high similarity. Thirdly, we employ the improved image classification model of CNN (ViT), which uses the finetuning and pretraining technique to recognize the individual pig face. Finally, our proposed method achieves the accuracy about 98.66%.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.139-145
• /
• 2023

The ROK Army is promoting cutting-edge, future-oriented military development such as a mobile, intelligent, and hyper-connected Army TIGER system. The future infantry brigade plans to increase mobility with squad-level tactical vehicles to enable combat in multi-domain operations and to deploy various weapon systems such as surveillance and reconnaissance drones. In addition, it will be developed into an intelligent unit that transmits and receives data collected through the weapon system through a hyper-connected network. Accordingly, the future infantry brigade will transmit and receive more data. However, the Army's tactical information communication system has limitations in operating as a tactical communication system for future units, such as low transmission speed and bandwidth and restrictions on communication support. Therefore, in this paper, the information distribution capability of the future infantry brigade is presented through the offensive operation scenario and M&S.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.11
• /
• pp.449-456
• /
• 2019

This paper is a study on the construction of a wall-climbing mobile robot using vacuum suction and wheel-type movement, and a comparison of the performance of an automatic wall crack detection algorithm based on machine learning that is suitable for such an embedded environment. In the embedded system environment, we compared performance by applying recently developed learning methods such as YOLO for object learning, and compared performance with existing edge detection algorithms. Finally, in this study, we selected the optimal machine learning method suitable for the embedded environment and good for extracting the crack features, and compared performance with the existing methods and presented its superiority. In addition, intelligent problem - solving function that transmits the image and location information of the detected crack to the manager device is constructed.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.4 s.316
• /
• pp.8-14
• /
• 2007

Social participation of the elderly and people with disabilities continuously becomes more active due to improvement of social systems and technological development. Various assistive systems, such as intelligence robots and intelligence home systems, have been developed to support the social participation, and obviously contributed to independent lives of the elderly and people with disabilities. These systems, however, usually require expensive special hardware. To relieve a financial burden software-oriented approaches, which utilizes existing hardware such as laptops, can be an alternative. The software should be developed considering users with physical limitation and without much knowledge of computers. This paper suggests software-oriented approaches to solve these problems and describes an actual development procedure of the software with related theories. We also introduce an unified user interface for a special work chair as a real application.