• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.68-73
• /
• 2005

Various techniques have been proposed for detection and tracking of targets in order to develop a real-world computer vision system, e.g., visual surveillance systems, intelligent transport systems (ITSs), and so forth. Especially, the idea of distributed vision system is required to realize these techniques in a wide-spread area. In this paper, we develop a ubiquitous vision system for location-awareness of multiple targets. Here, each vision sensor that the system is composed of can perform exact segmentation for a target by color and motion information, and visual tracking for multiple targets in real-time. We construct the ubiquitous vision system as the multiagent system by regarding each vision sensor as the agent (the vision agent). Therefore, we solve matching problem for the identity of a target as handover by protocol-based approach. We propose the identified contract net (ICN) protocol for the approach. The ICN protocol not only is independent of the number of vision agents but also doesn't need calibration between vision agents. Therefore, the ICN protocol raises speed, scalability, and modularity of the system. We adapt the ICN protocol in our ubiquitous vision system that we construct in order to make an experiment. Our ubiquitous vision system shows us reliable results and the ICN protocol is successfully operated through several experiments.

• 한국생산제조학회지
• /
• 제26권2호
• /
• pp.251-256
• /
• 2017

This study developed an image processing system for detecting damages on underground spiral PVC pipes. The detection method is simple-identifying damaged areas by measuring circularity along the pipeline. This uses the assumption that damage parts will not make a circular shape. Conventional devices check the circular shape of the pipe along the pipeline by measuring the angles between 6 spring-connected legs on the device. The conventional device, however, requires the insertion of 3 different wires (electrical, communication, and camera lines) along with a guide wire for pulling the device. The developed system presented here has simplified this system, requiring only a camera line while maintaining reasonable accuracy in damage detection.

• International Journal of Advanced Culture Technology
• /
• 제8권4호
• /
• pp.119-128
• /
• 2020

Object detection is an important field of computer vision and is applied to applications such as security, autonomous driving, and face recognition. Recently, as the application of artificial intelligence technology including deep learning has been applied in various fields, it has become a more powerful tool that can learn meaningful high-level, deeper features, solving difficult problems that have not been solved. Therefore, deep learning techniques are also being studied in the field of object detection, and algorithms with excellent performance are being introduced. In this paper, a deep learning-based object detection algorithm used to detect multiple objects in an image is investigated, and future development directions are presented.

• 반도체디스플레이기술학회지
• /
• 제21권3호
• /
• pp.7-11
• /
• 2022

Object detection technology is one of the main research topics in the field of computer vision and has established itself as an essential base technology for implementing various vision systems. Recent DNN (Deep Neural Networks)-based algorithms achieve much higher recognition accuracy than traditional algorithms. However, it is well-known that the DNN model inference operation requires a relatively high computational power. In this paper, we analyze the inference time complexity of the state-of-the-art object detection architecture Yolov7 in various environments. Specifically, we compare and analyze the time complexity of four types of the Yolov7 model, YOLOv7-tiny, YOLOv7, YOLOv7-X, and YOLOv7-E6 when performing inference operations using CPU and GPU. Furthermore, we analyze the time complexity variation when inferring the same models using the Pytorch framework and the Onnxruntime engine.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.516-519
• /
• 1999

Gaze detection is to find out the position on a monitor screen where a user is looking at, using the image processing and computer vision technology, We developed a computer interface system using the gaze detection technology, This system enables a user to control the computer system without using their hands. So this system will help the handicapped to use a computer and is also useful for the man whose hands are busy doing another job, especially in tasks in factory. For the practical use, command signal like mouse clicking is necessary and we used eye winking to give this command signal to the system.

• 방송공학회논문지
• /
• 제26권6호
• /
• pp.738-747
• /
• 2021

오늘날 딥러닝 기술의 향상으로 영상 분류, 객체 탐지, 객체 분할, 객체 추적 등 컴퓨터 비전 분야 또한 큰 발전을 이루고 있다. 지능적 감시, 로봇, 사물 인터넷, 자율주행 자동차 등 딥러닝 기술이 결합된 다양한 응용 기술들은 실제 산업에 적용되고 있으며, 이에 따라 사람의 소비를 위한 영상 데이터 뿐만 아니라 머신 비전을 위한 영상 데이터의 효율적인 압축 방식에 대한 필요성이 대두되고 있다. 본 논문에서는 머신 비전을 위한 열 적외선 영상의 객체 기반 압축 기법을 제안한다. 효율적인 영상 압축과 신경망의 좋은 성능을 유지하기 위해 본 논문에서는 신경망의 객체 탐지 결과와 객체 크기에 따라 입력 영상을 객체 부분과 배경 부분으로 나누어 서로 다른 압축률로 부호화를 수행하는 방법을 제안한다. 제안하는 방법은 VVC로 영상 전체를 압축하는 방식보다 BD-rate 값이 최대 -19.83%로 압축 효율이 뛰어나다는 것을 확인할 수 있다.

• 한국공작기계학회논문집
• /
• 제16권6호
• /
• pp.110-116
• /
• 2007

This paper presents a new technique to implement the real-time recognition for shapes and model number of parts based on an active vision approach. The main focus of this paper is to apply a technique of 3D object recognition for non-contacting inspection of the shape and the external form state of precision parts based on the pattern recognition. In the field of computer vision, there have been many kinds of object recognition approaches. And most of these approaches focus on a method of recognition using a given input image (passive vision). It is, however, hard to recognize an object from model objects that have similar aspects each other. Recently, it has been perceived that an active vision is one of hopeful approaches to realize a robust object recognition system. The performance is illustrated by experiment for several parts and models.

• Journal of Information Processing Systems
• /
• 제17권1호
• /
• pp.151-162
• /
• 2021

Quantum information has passed the theoretical research period and has entered the realization step for its application to the information and communications technology (ICT) sector. Currently, quantum information has the advantage of being safer and faster than conventional digital computers. Thus, a lot of research is being done. The amount of big data that one needs to deal with is expected to grow exponentially. It is also a new business model that can change the landscape of the existing computing. Just as the IT sector has faced many challenges in the past, we need to be prepared for change brought about by Quantum. We would like to look at studies on quantum communication, quantum sensing, and quantum computing based on quantum information and see the technology levels of each country and company. Based on this, we present the vision and challenge for quantum information in the future. Our work is significant since the time for first-time study challengers is reduced by discussing the fundamentals of quantum information and summarizing the current situation.

• 대한원격탐사학회지
• /
• 제4권1호
• /
• pp.31-40
• /
• 1988

Low-cost microcomputer systems can be assembled which possess computing power, color display, memory, and storage capacity approximately equal to graphic workstactions. A low-cost, flexible, and user-friendly IBM/PC/XT/AT based image processing system has been developed and named as KMIPS(KAIST (Korea Advanced Institute of Science & Technology) Map and Image Processing Station). It can be easily utilized by the resource managers who are not computer specialists. This system can: * directly access Landsat MSS and TM, SPOT, NOAA AVHRR, MOS-1 satellite imagery and other imagery from different sources via magnetic tape drive connected with IBM/PC; * extract image up to 1024 line by 1024 column and display it up to 480 line by 672 column with 512 colors simultaneously available; * digitize photographs using a frame grabber subsystem(512 by 512 picture elements); * perform a variety of image analyses, GIS and terrain analyses, and display functions; and * generate map and hard copies to the various scales. All raster data input to the microcomputer system is geographically referenced to the topographic map series in any rater cell size selected by the user. This map oriented, georeferenced approach of this system enables user to create a very accurately registered(.+-.1 picture element), multivariable, multitemporal data sets which can be subsequently subsequently subjected to various analyses and display functions.

• 한국정보통신학회논문지
• /
• 제23권2호
• /
• pp.127-132
• /
• 2019

본 논문에서는 사출성형 자동차부품의 외관 품질과 생산성을 높이기 위하여 사출성형 자동차부품의 외관 비전검사 방법을 제안한다. 일반적으로 기존 사출성형 자동차부품의 외관검사는 사람에 의한 매뉴얼 샘플링 검사로 진행된다. 먼저 전자부품(TFT-LCD 및 PCB 등) 비전검사에 활용되는 Edge-Tolerance 비전검사 알고리즘([1]-[4])을 사출성형 부품 외관검사에 적용하고, 그 문제점을 파악하였다. 그리고 그 문제점을 극복하는 새로운 외관 비전검사 방법을 제안한다. 제안된 외관비전검사는 양품 기준영상을 기준으로 검사하고자 하는 부품의 검사영상을 정렬한 후, 부분적인 적응적 이진화 후, 이진블록매칭 알고리즘을 이용하여 양품 이진영상과 검사이진영상을 블록단위로 비교함으로써 불량부분을 검출한다. Edge-Tolerance 비전검사 알고리즘과 제안된 외관비전검사 방법을 실제 개발된 장비를 이용하여 다양한 비교 실험을 통하여 그 효용성을 검증하였다.