• 융합신호처리학회논문지
• /
• 제11권2호
• /
• pp.143-150
• /
• 2010

무마커 증강현실 시스템은 실내나 옥외 환경에서 자연 물체를 인식하고 매칭하는 기능이 필수적이다. 본 논문에서는 비주얼 서술자와 코드북을 사용하여 특징을 추출하고 자연 물체를 인식하는 기법을 제안한다. 증강현실 응용은 동작 속도와 실시간 성능에 민감하기 때문에, 본 연구에서는 멀티 클래스의 자연 물체 인식에 초점을 두었으며 분류와 특징 추출 시간을 줄이는 것을 포함한다. 훈련과 테스트 과정에서 자연 물체로부터 특징을 추출하기 위해 SIFT와 SURF을 각각 사용하고 그들의 성능을 비교한다. 또한, 클러스터링 알고리즘을 이용하여 다차원의 특징 벡터들로부터 비주얼 코드북을 생성하고 나이브 베이즈 분류기를 이용해 물체를 인식한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.1061-1062
• /
• 2008

Rodents demonstrate an outstanding capability for tactile perceptions using their whiskers. The mechanoreceptors in the whisker follicles are responsive to the deflections or vibrations of the whisker beams. It is believed that the sensor processing can determine the location of an object in touch, that is, the angular position and direction of the object. We designed artificial whiskers modelling the real whiskers and tested tactile localization. The robotic system needs to adjust its position against an object to help the shape recognition. We show a robotic adjustment of position based on tactile localization. The behaviour uses deflection curves of the whisker sensors for every sweep of whiskers and estimates the location of a target object.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 C
• /
• pp.1495-1497
• /
• 1996

In this study, Object restoration of ultrasonic transducer fabricated with porous piezoelectric ceramics using Modified SCL(Simple Competitive Learning) neural networks are presented. Using the acquired object data $16{\times}16$ pixels, Modified SCL neural networks using the $16{\times}16$ low resolution image was used for object restoration of $32{\times}32$ high resolution image. The experimental results show that the ultrasonic transducer fabricated with porous piezoelectric ceramics could be applied for sonar system.

• 한국공간정보시스템학회 논문지
• /
• 제10권2호
• /
• pp.13-24
• /
• 2008

차세대 실감 내비게이션 시스템은 2D 기반 내비게이션 시스템의 단점을 보완하고 보다 안전한 운전을 할 수 있도록 다양한 서비스를 제공하기 위해 연구되고 있다. 실감 내비게이션 시스템 차선인식과 도로시설물 객체 DB, 교차로 인식 모듈등의 기능 블록들로 구성된다. 본 논문에서는 실감내비게이션의 중요 요소 중 하나인 교차로 인식을 위한 신호등과 표지판 인식 시스템을 개발하였다. 개발된 알고리듬은 색상 정보를 이용해 인식 대상을 검출하고 객체의 특징을 이용하여 신호등과 표지판을 객체별로 인식할 수 있도록 하였으며 실험을 통해 검증하였다. 실험결과 신호등의 경우 60-30m의 거리에서 평균90%의 인식률을 보였으며, 표지판의 경우 90-40m의 거리에서 평균 97%의 인식률을 보였고, 프레임 당 평균 처리시간이 46msec로서 실시간 처리가 가능함을 보였다.

• International Journal of Advanced Culture Technology
• /
• 제9권2호
• /
• pp.100-105
• /
• 2021

Contactless service is rapidly emerging as a new growth strategy due to consumers who are reluctant to the face-to-face situation in the global pandemic of coronavirus disease 2019 (COVID-19), and various technologies are being developed to support the fast-growing contactless service market. In particular, the restaurant industry is one of the most desperate industrial fields requiring technologies for contactless service, and the representative technical case should be a kiosk, which has the advantage of reducing labor costs for the restaurant owners and provides psychological relaxation and satisfaction to the customer. In this paper, we propose a solution to the restaurant's store operation through the unmanned kiosk using a state-of-the-art artificial intelligence (AI) technology of image recognition. Especially, for the products that do not have barcodes in bakeries, fresh foods (fruits, vegetables, etc.), and autonomous restaurants on highways, which cause increased labor costs and many hassles, our proposed system should be very useful. The proposed system recognizes products without barcodes on the ground of image-based AI algorithm technology and makes automatic payments. To test the proposed system feasibility, we established an AI vision system using a commercial camera and conducted an image recognition test by training object detection AI models using donut images. The proposed system has a self-learning system with mismatched information in operation. The self-learning AI technology allows us to upgrade the recognition performance continuously. We proposed a fully automated payment system with AI vision technology and showed system feasibility by the performance test. The system realizes contactless service for self-checkout in the restaurant business area and improves the cost-saving in managing human resources.

• 한국멀티미디어학회논문지
• /
• 제12권6호
• /
• pp.804-814
• /
• 2009

In this paper, a novel system for avatar motion controlling by tracking face is presented. The system is composed of three main parts: firstly, LCS (Local Cluster Searching) method based face feature detection algorithm, secondly, HMM based feature points recognition algorithm, and finally, avatar controlling and animation generation algorithm. In LCS method, face region can be divided into many small piece regions in horizontal and vertical direction. Then the method will judge each cross point that if it is an object point, edge point or the background point. The HMM method will distinguish the mouth, eyes, nose etc. from these feature points. Based on the detected facial feature points, the 3D avatar is controlled by two ways: avatar orientation and animation, the avatar orientation controlling information can be acquired by analyzing facial geometric information; avatar animation can be generated from the face feature points smoothly. And finally for evaluating performance of the developed system, we implement the system on Window XP OS, the results show that the system can have an excellent performance.

• 제어로봇시스템학회논문지
• /
• 제15권4호
• /
• pp.420-425
• /
• 2009

In this paper, image detection and recognition algorithms are studied with respect to embedded carrier system. There are many suggested techniques to detect and recognize objects. But they have the propensity to need much calculation for high hit rate. Advanced and modified method needs to study for embedded systems that low power consumption and real time response are requested. The proposed methods were implemented using Intel(R) Open Source Computer Vision Library provided by Intel Corporation. And they run and tested on embedded system using a ARM920T processor by cross-compiling. They showed 1.6sec response time and 95% hit rate and supported the automated moving carrier system smoothly.

• 대한전자공학회논문지
• /
• 제20권1호
• /
• pp.1-6
• /
• 1983

시각 능력에 의한 작업 대상의 인식 기능을 갖는 로보트 시스템에 괼도한 image digiilzer와 기본적인 몇가지 소프트웨어 기법의 개발에 관한 연구 결과를 보고한다. Image digitizer는 CROMEMCO SYSTEM III 마이크로컴퓨터와 C.C.C.T.V. 카메라를 이용하여 개발하였으며, 소프트웨어 기법들은 3차원 물체의 인식에 중점을 두었는데, 이 기법들의 유용성을 간략한 물체인 직육면체에의 응용을 통해 보였다.

• 디지털융복합연구
• /
• 제5권2호
• /
• pp.1-13
• /
• 2007

Recently, RFID has emerged as the main technology in the logistic services. When the existing recognition technology based on bar codes brings about lots of problem due to its own limits. RFID becomes the center of attention to solve them. However, RFID is not without any obstacles: companies have their own operating systems, while RFID is developed regardless of each company's special features. RFID middleware system based on web service is expected to remove these obstacles. This paper shows how to operate the middleware based on web service and to lay in the DB the tag informations taken from reader system. Middle assures that companies adopting RFID system for their logistic service are given adaptability to any systems whatsoever, available by way of defining logistic information, tag information and reader information. For this purpose, we implement as the basic web service a middleware system that turns all data into XML(eXtensible Markup Language) of SOAP (Simple Object Access Protocol), the standard data.

• ETRI Journal
• /
• 제36권4호
• /
• pp.662-672
• /
• 2014

Human action recognition is used in areas such as surveillance, entertainment, and healthcare. This paper proposes a system to recognize both single and continuous human actions from monocular video sequences, based on 3D human modeling and cyclic hidden Markov models (CHMMs). First, for each frame in a monocular video sequence, the 3D coordinates of joints belonging to a human object, through actions of multiple cycles, are extracted using 3D human modeling techniques. The 3D coordinates are then converted into a set of geometrical relational features (GRFs) for dimensionality reduction and discrimination increase. For further dimensionality reduction, k-means clustering is applied to the GRFs to generate clustered feature vectors. These vectors are used to train CHMMs separately for different types of actions, based on the Baum-Welch re-estimation algorithm. For recognition of continuous actions that are concatenated from several distinct types of actions, a designed graphical model is used to systematically concatenate different separately trained CHMMs. The experimental results show the effective performance of our proposed system in both single and continuous action recognition problems.