• 한국정보과학회논문지:소프트웨어및응용
• /
• 제35권4호
• /
• pp.265-279
• /
• 2008

손 제스처를 이용한 사람과 컴퓨터간의 상호 작용은 오랜 기간 많은 사람들이 연구해 오고 있으며 커다란 발전을 보이고 있지만, 여전히 만족스러운 결과를 보이지는 못하고 있다. 본 논문에서는 동적 베이스망 프레임워크를 이용한 손 제스처 인식 방법을 제안한다. 유선 글러브를 이용하는 방법들과는 달리, 카메라 기반의 방법에서는 영상 처리와 특징 추출 단계의 결과들이 인식 성능에 큰 영향을 미친다. 제안하는 제스처 모델에서의 추론에 앞서 피부 색상 모델링 및 검출과 움직임 추적을 수행한다. 특징들간의 관계와 새로운 정보들을 쉽게 모델에 반영할 수 있는 동적 베이스망을 이용하여 두 손 제스처와 한 손 제스처 모두를 인식할 수 있는 새로운 모델을 제안한다. 10가지 독립 제스처에 대한 실험에서 최대 99.59%의 높은 인식 성능을 보였다. 제안하는 모델과 관련 방법들은 수화 인식과 같은 다른 문제들에도 적용 가능할 것으로 판단된다.

• 인터넷정보학회논문지
• /
• 제20권6호
• /
• pp.1-10
• /
• 2019

객체기반 이미지 매칭 알고리즘 기술은 이미지 프로세싱 및 컴퓨터 비전 분야에서 광범위하게 사용되어 왔다. 이러한 이미지 매칭 알고리즘 기반의 수 많은 응용 프로그램은 객체인식, 3D 모델링, 비디오 추적 및 바이오 정보학 분야에서 개발되어 왔다. 이미지 매칭 알고리즘의 좋은 예는 Scale invariant Feature Transform(SIFT) 이다. 하지만 SIFT 알고리즘 기술을 이용한 많은 응용 프로그램은 클라이언트-서버 구조가 아닌 하나의 시스템으로 운영되어 왔다. 본 논문은 모바일 플랫폼 기반에서 SIFT 알고리즘 기술을 이용하여 클라이언트-서버 구조로 이미지 매칭 시스템을 구현하였다. 제안된 시스템은 바이오 이미지 객체를 매칭하고 식별하여 사용자에게 유용한 정보를 제공한다. 또한 본 논문의 주요 방법론적 기여는 모바일 장치에 유비쿼터스 인터넷 연결을 활용하여 편리한 사용자 인터페이스와 객체간의 상호작용적인 묘사, 분할, 표현, 매칭 및 바이오 이미지를 검색한다. 본 논문은 이러한 기술과 함께 바이오 정보학에 대한 의미론적 이미지 검색을 수행하며 응용 프로그램에서 객체 이미지의 다른 점을 추출하여 신뢰할 수 있는 이미지 매칭을 수행하는 예를 제시해주었다.

• 대한임베디드공학회논문지
• /
• 제3권2호
• /
• pp.57-65
• /
• 2008

Recently many researches on intelligent robots have been studied. An intelligent robot is capable of recognizing environments or objects to autonomously perform specific tasks using sensor readings. One of fundamental problems in vision-based robot applications is to recognize where it is and to decide safe path to perform autonomous navigation. However, previous approaches only consider well-organized environments that there is no moving object and environment changes. In this paper, we introduce a novel navigation strategy to handle occlusions caused by moving objects using various computer vision techniques. Experimental results demonstrate the capability to overcome such difficulties for autonomous navigation.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 춘계학술대회 논문집
• /
• pp.253-257
• /
• 2004

Neural networks are works are used in the framework of sensor based tracking control of robot manipulators. They learn by practice movements the relationship between PSD(an analog Position Sensitive Detector) sensor readings for target positions and the joint commands to reach them. Using this configuration, the system can track or follow a moving or stationary object in real time. Furthermore, an efficient neural network architecture has been developed for real time learning. This network uses multiple sets of simple back propagation networks one of which is selected according to which division(corresponding to a cluster of the self-organizing feature map) in data space the current input data belongs to. This lends itself to a very training and processing implementation required for real time control.

• 한국위성정보통신학회논문지
• /
• 제8권4호
• /
• pp.26-29
• /
• 2013

군중의 혼잡한 정도를 추정하기 위해서는 텍스처 기반의 방법을 이용하거나 움직임을 검출하여 혼잡한 정도를 추정한다. 본 논문에서는 이 두 가지를 혼합한 방법을 제안한다. 또한 ROI 영역을 설정하여 영역내의 혼잡한 정도의 기준을 명확히 하였으며, 특징 정규화를 통하여 카메라 각도 변화의 오차를 줄이고자 하였다. 이 시스템을 DSP에 탑재하여 임베디드 기반의 실시간 시스템을 구축하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.97-99
• /
• 2009

Bilateral teleoperation systems, connected to computer networks such as Internet have to deal with the time delay varying depending on factors such as congestion, bandwidth or distance. And the entire system is easy to become unstable due to irregular time delay. Passivity concept has been using as a framework to solve the stability problem in bilateral control of teleoperation. Acontrol scheme for teleoperation systems with varying time delay is proposed based on a passivity concept is proposed in this paper. One approach makinguse of the characteristic impedances is proposed to achieve a passive control. Since passive control does not mean that the system performance will be acceptable, another transmission scheme which focuses on both the passive feature and the acceptable performance is configured for varying time delay in this paper. The tracking performance has been proved through the computer simulation for varying time delay bilateral teleoperation system using Matlab Simulink.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 가을 학술발표논문집 Vol.34 No.2 (C)
• /
• pp.263-266
• /
• 2007

We introduce a vision-based hand gesture recognition fer understanding musical time and patterns without extra special devices. We suggest a simple and reliable vision-based hand gesture recognition having two features First, the motion-direction code is proposed, which is a quantized code for motion directions. Second, the conducting feature point (CFP) where the point of sudden motion changes is also proposed. The proposed hand gesture recognition system extracts the human hand region by segmenting the depth information generated by stereo matching of image sequences. And then, it follows the motion of the center of the gravity(COG) of the extracted hand region and generates the gesture features such as CFP and the direction-code finally, we obtain the current timing pattern of beat and tempo of the playing music. The experimental results on the test data set show that the musical time pattern and tempo recognition rate is over 86.42% for the motion histogram matching, and 79.75% fer the CFP tracking only.

• 제어로봇시스템학회논문지
• /
• 제15권5호
• /
• pp.473-479
• /
• 2009

This paper proposes an efficient method to locate the automated guided vehicle (AGV) into a specific parking position using artificial visual landmark and vision-based algorithm. The landmark has comer features and a HSI color arrangement for robustness against illuminant variation. The landmark is attached to left of a parking spot under a crane. For parking, an AGV detects the landmark with CCD camera fixed to the AGV using Harris comer detector and matching descriptors of the comer features. After detecting the landmark, the AGV tracks the landmark using pyramidal Lucas-Kanade feature tracker and a refinement process. Then, the AGV decreases its speed and aligns its longitudinal position with the center of the landmark. The experiments showed the AGV parked accurately at the parking spot with small standard deviation of error under bright illumination and dark illumination.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권5호
• /
• pp.1471-1483
• /
• 2023

One of the fastest-growing mobile services accessible today is mobile payments. For the safety of this service, the Near Field Communication (NFC) technology is used. However, NFC standard protocol has prioritized transmission rate over authentication feature due to the proximity of communicated devices. Unfortunately, an adversary can exploit this vulnerability with an antenna that can eavesdrop or alter the exchanged messages between NFC-enabled devices. Many researchers have proposed authentication methods for NFC connections to mitigate this challenge. However, the security and privacy of payment transactions remain insufficient. We offer a privacy-preserving, anonymity-based, safe, and efficient authentication protocol to protect users from tracking and replay attacks to guarantee secure transactions. To improve transaction security and, more importantly, to make our protocol lightweight while ensuring privacy, the proposed protocol employs a secure offline session key generation mechanism. Formal security verification is performed to assess the proposed protocol's security strength. When comparing the performance of current protocols, the suggested protocol outperforms the others.

• Journal of Electrical Engineering and Technology
• /
• 제11권6호
• /
• pp.1857-1862
• /
• 2016

Human activity recognition using depth information is an emerging and challenging technology in computer vision due to its considerable attention by many practical applications such as smart home/office system, personal health care and 3D video games. This paper presents a novel framework of 3D human body detection, tracking and recognition from depth video sequences using spatiotemporal features and modified HMM. To detect human silhouette, raw depth data is examined to extract human silhouette by considering spatial continuity and constraints of human motion information. While, frame differentiation is used to track human movements. Features extraction mechanism consists of spatial depth shape features and temporal joints features are used to improve classification performance. Both of these features are fused together to recognize different activities using the modified hidden Markov model (M-HMM). The proposed approach is evaluated on two challenging depth video datasets. Moreover, our system has significant abilities to handle subject's body parts rotation and body parts missing which provide major contributions in human activity recognition.