• Advances in robotics research
• /
• 제2권1호
• /
• pp.45-57
• /
• 2018

Even though the popularity of projection mapping continues to increase and it is being implemented in more and more settings, most current projection mapping systems are limited to special purposes, such as outdoor events, live theater and musical performances. This lack of versatility arises from the large number of projectors needed and their proper calibration. Furthermore, we cannot change the positions and poses of projectors, or their projection targets, after the projectors have been calibrated. To overcome these problems, we propose a projection mapping method using a projector robot that can perform projection mapping in more general or ubiquitous situations, such as shopping malls. We can estimate a projector's position and pose with the robot's self-localization sensors, but the accuracy of this approach remains inadequate for projection mapping. Consequently, the proposed method solves this problem by combining self-localization by robot sensors with position and pose estimation of projection targets based on a 3D model. We first obtain the projection target's 3D model and then use it to accurately estimate the target's position and pose and thus achieve accurate projection mapping with a projector robot. In addition, our proposed method performs accurate projection mapping even after a projection target has been moved, which often occur in shopping malls. In this paper, we employ Ubiquitous Display (UD), which we are researching as a projector robot, to experimentally evaluate the effectiveness of the proposed method.

• 한국지능시스템학회논문지
• /
• 제22권3호
• /
• pp.353-360
• /
• 2012

본 논문은 파티클 필터 방법을 이용하여 로봇의 외부에 설치된 특징점들과 로봇의 위치를 동시에 추정하는 SLAM 방법을 제안한다. 파티클 필터 방법은 로봇 동작의 비선형성 및 센서 오차의 비가우시안 특성을 고려할 수 있다. 제안된 방법에서 추정할 변수는 로봇의 위치와 특징점들의 위치이다. 본 연구에서 특징점은 초음파 신호를 발생시키는 4개의 비이컨들이 사용된다. 그리고 로봇은 비이컨들로부터 초음파 신호를 수신하여 각각의 비이컨까지의 거리를 계산한다. 그리고 영역센서를 이용하여 이동로봇이 동작하는 환경의 기하학적 지도정보를 생성하는 과정을 보였다. 제안된 방법은 로봇의 위치와 방향을 추정하기 때문에 영역센서에 의해 획득된 데이터를 사용하여 기하학적 지도를 생성할 수 있다. 또한 데드레크닝 방법 및 삼변측량 방법과의 로봇 위치추정 비교 실험을 통하여 제안된 방법을 평가하였다.

• 한국항공우주학회지
• /
• 제45권5호
• /
• pp.417-428
• /
• 2017

본 논문에서는 항공기 조종사 지능형 헬멧시현시스템(IHDS, Intelligent Helmet Display System)의 아키텍쳐 설계, 단위 구성품 설계, 핵심 소프트웨어 설계내용(헬멧 자세추적, 고도오차 보정 소프트웨어)을 기술하며, 단위시험 및 통합시험에 대한 결과를 기술한다. 세계적인 최신 헬멧시현시스템 개발 추세를 반영하여 3차원 전자지도 시현, FLIR(Forward Looking Infra-Red) 영상시현, 하이브리드형 헬멧자세추적, 바이저 반사형광학계, 야시카메라 영상시현 및 경량 복합소재 헬멧쉘 등의 사양을 설계에 적용하였다. 특히 3차원 전자지도 데이터의 고도오차 자동보정 기법, 고정밀 영상정합 기법, 다색(Multi-color) 조명광학계, 회절소자를 이용한 투과형 영상발광면, 헬멧자세 추정시간을 최소화하는 추적용 카메라, 장/탈착형 야시카메라, 머리 밀착용 에어포켓 등의 신개념의 설계를 제안하였다. 모든 시스템 구성품의 시제작을 완료한 후 단위시험과 시스템 통합시험을 수행하여 기능과 성능을 검증하였다.

• 스마트미디어저널
• /
• 제11권3호
• /
• pp.90-101
• /
• 2022

버스는 대중적으로 많이 이용되는 교통수단이다. 그만큼 승객의 안전관리를 위해 철저한 대비가 필요하다. 하지만 2018년 승차하기 위해 접근하는 노인을 인지하지 못하고 버스가 출발하면서 사망사고가 발생하는 등 안전 시스템이 미흡한 상황이다. 기존에 뒷문 계단 쪽 센서를 통해 끼임 사고를 방지하는 안전 시스템은 있지만, 이러한 시스템은 위 사고처럼 승하차하려는 과정에서 발생하는 사고를 예방하진 못한다. 버스 승객의 승하차 의도를 예측할 수 있다면, 위와 같은 사고를 예방하는 안전 시스템 개발에 도움이 될 것이다. 그러나 승객의 승하차 의도를 예측하는 연구는 부족한 상태이다. 따라서 본 논문에서는 버스에 부착된 카메라 영상에서 UDP-Pose를 통해 승객의 skeleton keypoints를 추출하고, 이를 활용한 1×1 CNN3D 기반의 버스 승객 승하차 의도를 예측하는 모델을 제안한다. 제안한 모델은 승객의 승하차 의도를 예측하는 부분에서 RNN, LSTM 모델보다 약 1~2% 높은 정확도를 보여준다.

• 제어로봇시스템학회논문지
• /
• 제21권2호
• /
• pp.108-114
• /
• 2015

Automated driving systems require a high level of performance regarding environmental perception, especially in urban environments. Today's on-board sensors such as radars or cameras do not reach a satisfying level of development from the point of view of robustness and availability. Thus, map data is often used as an additional data input to support these systems. An accurate digital map is used as a powerful additional sensor. In this paper, we propose a new approach for vehicle localization using a lane map and a single-layer LiDAR. The maps are created beforehand using a highly accurate DGPS and a single-layer LiDAR. A pose estimation of the vehicle was derived from an iterative closest point (ICP) match of LiDAR's intensity data to the lane map, and the estimated pose was used as an observation inside a Kalmanfilter framework. The achieved accuracy of the proposed localization algorithm is evaluated with a highly accurate DGPS to investigate the performance with respect to lateral vehicle control.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2720-2736
• /
• 2013

Multi-view face detection has become an active area for research in the last few years. In this paper, a novel multi-view human face detection algorithm based on improved real Adaboost is presented. Real Adaboost algorithm is improved by weighted combination of weak classifiers and the approximately best combination coefficients are obtained. After that, we proved that the function of sample weight adjusting method and weak classifier training method is to guarantee the independence of weak classifiers. A coarse-to-fine hierarchical face detector combining the high efficiency of Haar feature with pose estimation phase based on our real Adaboost algorithm is proposed. This algorithm reduces training time cost greatly compared with classical real Adaboost algorithm. In addition, it speeds up strong classifier converging and reduces the number of weak classifiers. For frontal face detection, the experiments on MIT+CMU frontal face test set result a 96.4% correct rate with 528 false alarms; for multi-view face in real time test set result a 94.7 % correct rate. The experimental results verified the effectiveness of the proposed approach.

• 로봇학회논문지
• /
• 제15권1호
• /
• pp.55-61
• /
• 2020

Getting on and off an elevator is one of the most important parts for multi-floor navigation of a mobile robot. In this study, we proposed the method for the pose recognition of elevator doors, safe path planning, and motion estimation of a robot using RGB-D sensors in order to safely get on and off the elevator. The accurate pose of the elevator doors is recognized using a particle filter algorithm. After the elevator door is open, the robot builds an occupancy grid map including the internal environments of the elevator to generate a safe path. The safe path prevents collision with obstacles in the elevator. While the robot gets on and off the elevator, the robot uses the optical flow algorithm of the floor image to detect the state that the robot cannot move due to an elevator door sill. The experimental results in various experiments show that the proposed method enables the robot to get on and off the elevator safely.

• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.186-203
• /
• 2020

Image-based Virtual Try-On Systems are among the most potential solution for virtual fitting which tries on a target clothes into a model person image and thus have attracted considerable research efforts. In many cases, current solutions for those fails in achieving naturally looking virtual fitted image where a target clothes is transferred into the body area of a model person of any shape and pose while keeping clothes context like texture, text, logo without distortion and artifacts. In this paper, we propose a new improved image-based virtual try-on network system based on keypoints, which we name as KP-VTON. The proposed KP-VTON first detects keypoints in the target clothes and reliably predicts keypoints in the clothes of a model person image by utilizing a dense human pose estimation. Then, through TPS transformation calculated by utilizing the keypoints as control points, the warped target clothes image, which is matched into the body area for wearing the target clothes, is obtained. Finally, a new try-on module adopting Attention U-Net is applied to handle more detailed synthesis of virtual fitted image. Extensive experiments on a well-known dataset show that the proposed KP-VTON performs better the state-of-the-art virtual try-on systems.

• 센서학회지
• /
• 제19권3호
• /
• pp.246-257
• /
• 2010

Autonomous guided robot navigation which consists of following unknown paths and avoiding unknown obstacles has been a fundamental technique for unmanned robots in outdoor environments. The unknown path following requires techniques such as path recognition, path planning, and robot pose estimation. In this paper, we propose a novel sensor fusion system for autonomous guided robot navigation in outdoor environments. The proposed system consists of three monocular cameras and an array of nine infrared range sensors. The two cameras equipped on the robot's right and left sides are used to recognize unknown paths and estimate relative robot pose on these paths through bayesian sensor fusion method, and the other camera equipped at the front of the robot is used to recognize abrupt curves and unknown obstacles. The infrared range sensor array is used to improve the robustness of obstacle avoidance. The forward camera and the infrared range sensor array are fused through rule-based method for obstacle avoidance. Experiments in outdoor environments show the mobile robot with the proposed sensor fusion system performed successfully real-time autonomous guided navigation.

• 한국정보통신학회논문지
• /
• 제8권3호
• /
• pp.702-707
• /
• 2004

본 논문은 CCD 카메라와 거리 센서를 사용하여 컨테이너의 자세 측정에 관하여 연구하였다. 특히 특징점을 추출하고 영상의 잡음을 줄이는 방법에 대하여 중점적으로 기술하였다. 가우시안 및 랜덤 노이즈를 제거하기 위하여 Euler-Lagrange 방정식을 소개하였으며 PDE(Partial Differential Equation)를 기초로 한 Euler-Lagrange 방정식을 풀기 위하여 ADI(Alternating Direction Implicit)방법을 적용하였다. 그리고 스프레더와 컨테이너의 특징점을 추출하기 위해서 기존의 황금 분할법과 이분 분할법을 이용한 방법은 지역적 최대 및 최소 값의 경우 정확한 해를 구할 수 없어서 k차 곡률 알고리즘을 이용하였다. 제안된 알고리즘은 영상의 전처리과정에서 잡음제거에 효과적이며 카메라와 거리센서를 이용한 제안 시스템은 기존시스템의 구조적 변경 없이 사용가능하기 때문에 비용이 저렴한 장점이 있다.