• 한국컴퓨터정보학회논문지
• /
• 제28권9호
• /
• pp.17-25
• /
• 2023

본 논문에서는 매개변수가 더 적고, 빠르게 추정 가능한 MobileViT 기반 모델을 통해 사람 자세 추정 과업을 수행할 수 있는 모델을 제안한다. 기반 모델은 합성곱 신경망의 특징과 Vision Transformer의 특징이 결합한 구조를 통해 경량화된 성능을 입증한다. 본 연구에서 주요 매커니즘이 되는 Transformer는 그 기반의 모델들이 컴퓨터 비전 분야에서도 합성곱 신경망 기반의 모델들 대비 더 나은 성능을 보이며, 영향력이 커지게 되었다. 이는 사람 자세 추정 과업에서도 동일한 상황이며, Vision Transformer기반의 ViTPose가 COCO, OCHuman, MPII 등 사람 자세 추정 벤치마크에서 모두 최고 성능을 지키고 있는 것이 그 적절한 예시이다. 하지만 Vision Transformer는 매개변수의 수가 많고 상대적으로 많은 연산량을 요구하는 무거운 모델 구조를 가지고 있기 때문에, 학습에 있어 사용자에게 많은 비용을 야기시킨다. 이에 기반 모델은 Vision Transformer가 많은 계산량을 요구하는 부족한 Inductive Bias 계산 문제를 합성곱 신경망 구조를 통한 Local Representation으로 극복하였다. 최종적으로, 제안 모델은 MS COCO 사람 자세 추정 벤치마크에서 제공하는 Validation Set으로 ViTPose 대비 각각 5분의 1과 9분의 1만큼의 3.28GFLOPs, 972만 매개변수를 나타내었고, 69.4 Mean Average Precision을 달성하여 상대적으로 우수한 성능을 보였다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회A
• /
• pp.1553-1558
• /
• 2007

This paper presents a vision based autonomous inspection system for welding quality control of car sinking seat. In order to overcome the precision error that arises from a visible inspection by operator in the manufacturing process of a car sinking seat, this paper proposes the MVWQC (machine vision based welding quality control) system. This system consists of the CMOS camera and NI machine vision system. The image processing software for the system has been developed using the NI vision builder system. The geometry of welding bead, which is the welding quality criteria, is measured by using the captured image with median filter applied on it. Experiments have been performed to verify the proposed MVWQC of car sinking seat.

• 지식경영연구
• /
• 제11권2호
• /
• pp.57-73
• /
• 2010

This research investigated the effect of human resource practices on knowledge sharing. We developed and tested a mediation model of how human resource practices affect shared vision and codes which facilitates knowledge sharing. A field study of the R&D centers in knowledge-intensive industries showed that commitment-based human resource management systems were positively related to shared vision and codes and knowledge sharing, and the relationship between HR practices and knowledge sharing was fully mediated through shared vision and codes. This study contributed to the extant literature pertaining to the antecedents of knowledge sharing through focusing on the role of HR practices and shared vision and codes.

• Journal of Positioning, Navigation, and Timing
• /
• 제6권2호
• /
• pp.59-70
• /
• 2017

Since GPS signals are vulnerable to interference and obstruction, many alternate aiding systems have been proposed to integrate with an inertial navigation system. Among these alternate systems, the vision-aided method has become more attractive due to its benefits in weight, cost and power consumption. This paper proposes a loosely-coupled vision/INS integrated navigation method which can work in GPS-denied environments. The proposed method improves the navigation accuracy by correcting INS navigation and sensor errors using position and attitude outputs of a landmark based vision navigation system. Furthermore, it has advantage to provide redundant navigation output regardless of INS output. Computer simulations and the van tests have been carried out in order to show validity of the proposed method. The results show that the proposed method works well and gives reliable navigation outputs with better performance.

• 제어로봇시스템학회논문지
• /
• 제14권8호
• /
• pp.745-751
• /
• 2008

This paper presents a framework for GPS/INS/Vision based navigation system of helicopters. GPS/INS coupled algorithm has weak points such as GPS blockage and jamming, while the helicopter is a speedy and high dynamical vehicle amenable to lose the GPS signal. In case of the vision sensor, it is not affected by signal jamming and also navigation error is not accumulated. So, we have implemented an GPS/INS/Vision aided navigation system providing the robust localization suitable for helicopters operating in various environments. The core algorithm is the vision based simultaneous localization and mapping (SLAM) technique. For the verification of the SLAM algorithm, we performed flight tests. From the tests, we confirm the developed system is robust enough under the GPS blockage. The system design, software algorithm, and flight test results are described.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.777-780
• /
• 2003

We have tried to create a vision system like human eye for a long time. We have obtained some distinguished results through many studies. Stereo vision is the most similar to human eye among those. This is the process of recreating 3-D spatial information from a pair of 2-D images. In this paper, we have designed a stereo matching algorithm based on systolic array architecture using edges and pixel data. This is more advanced vision system that improves some problems of previous stereo vision systems. This decreases noise and improves matching rate using edges and pixel data and also improves processing speed using high integration one chip FPGA and compact modules. We can apply this to robot vision and automatic control vehicles and artificial satellites.

• 국제초고층학회논문집
• /
• 제12권4호
• /
• pp.321-333
• /
• 2023

Structural health monitoring is a technology or research field that extends the service life of structures and contributes to the prevention of disaster accidents by continuously evaluating the safety, stability, and serviceability of structures as well as allowing timely and proper maintenance. However, the contact-type sensors used for it require considerable time, cost, and labor for installation and maintenance. As an alternative, computer vision has attracted attention recently. Computer vision has the potential to make quality, deformation, and damage monitoring for structures contactless and automated. In this study, research cases in which computer vision was utilized for structural health monitoring are introduced, and its effects and limitations are summarized. Therefore, the applicability and future research directions of computer vision-based structural health monitoring are discussed.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1996년도 추계학술대회 논문집
• /
• pp.434-438
• /
• 1996

In this paper we present the multi-agent robot system and the vision system developed for participating in micro robot soccer tournament. The multi-agent robot system consists of micro robot, a vision system, a host computer and a communication module. Micro robot are equipped with two mini DC motors witf encoders and gearboxes, a R/F receiver, a CPU and infrared sensors for obstacle detection. A vision system is used to recognize the position of the ball and opponent robots, position and orientation of our robots. The vision system is composed of a color CCD camera and a vision processing unit(AISI vision computer). The vision algorithm is based on morphological method. And it takes about 90 msec to detect ball and 3-our robots and 3-opponent robots with reasonable accuracy

• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2011년도 정기 학술발표대회
• /
• pp.39-39
• /
• 2011

This study presents an effective vision-based system for cable bridge damage detection. In theory, cable bridges need to be inspected the outer as well as the inner part. Starting from August 2010, a new research project supported by Korea Ministry of Land, Transportation Maritime Affairs(MLTM) was initiated focusing on the damage detection of cable system. In this study, only the surface damage detection algorithm based on a vision-based system will be focused on, an overview of the vision-based cable damage detection is given in Fig. 1. Basically, the algorithm combines the image enhancement technique with principal component analysis(PCA) to detect damage on cable surfaces. In more detail, the input image from a camera is processed with image enhancement technique to improve image quality, and then it is projected into PCA sub-space. Finally, the Mahalanobis square distance is used for pattern recognition. The algorithm was verified through laboratory tests on three types of cable surface. The algorithm gave very good results, and the next step of this study is to implement the algorithm for real cable bridges.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
• /
• pp.103-106
• /
• 2003

In this paper, we present a hybrid inertial and vision-based tracking system for VR applications. One of the most important aspects of VR (Virtual Reality) is providing a correspondence between the physical and virtual world. As a result, accurate and real-time tracking of an object's position and orientation is a prerequisite for many applications in the Virtual Environments. Pure vision-based tracking has low jitter and high accuracy but cannot guarantee real-time pose recovery under all circumstances. Pure inertial tracking has high update rates and full 6DOF recovery but lacks long-term stability due to sensor noise. In order to overcome the individual drawbacks and to build better tracking system, we introduce the fusion of vision-based and inertial tracking. Sensor fusion makes the proposal tracking system robust, fast, accurate, and low jitter and noise. Hybrid tracking is implemented with Kalman Filter that operates in a predictor-corrector manner. Combining bluetooth serial communication module gives the system a full mobility and makes the system affordable, lightweight energy-efficient. and practical. Full 6DOF recovery and the full mobility of proposal system enable the user to interact with mobile device like PDA and provide the user with natural interface.