• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.50-57
• /
• 2007

사용자가 현재 위치해 있는 장소를 알아내는 것은 상황인식 분야에서 활발히 연구되고 있는 분야중 하나로, 이를 위해서 사용자의 몸에 다양한 센서를 장착하고 그 센서로부터 추출되는 데이터를 분석하여 사용자의 위치를 인식하는 연구가 많이 이루어져왔다. 본 논문에서는, 사용자의 몸에 장착된 카메라로부터 얻어진 영상을 이용하여 사용자의 현재 장소를 인식하는 장소 인식 시스템을 제안한다. 기존의 방법론들에 비해서 높은 성능을 보이기 위해서 본 논문에서는 두 가지 방법을 제안하였다. 먼저 한 방향만의 영상으로는 인식이 어려운 장소에서도 좋은 인식 성능을 보일 수 있도록 하기 위해, 여러 대의 카메라를 동시에 사용하여 여러 방향의 영상을 얻어내는 방법을 제안하였다. 또한 이전 시간의 장소 인식 결과로부터 현재 시간의 장소를 추론하는 데에 있어서, 각 장소들에 대해 알고 있는 사전지식을 보다 많이 적용할 수 있는 인식 모델을 제안하였다. 실제 대학 실내 환경에서의 실험을 통하여, 제안한 방법을 이용한 장소 인식기법이 좋은 성능을 보임을 확인할 수 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.128.6-128
• /
• 2001

In this paper, we present a methodology of sensing and control for a robot system designed to be capable of grasping an object and moving it to target point Stereo vision system is employed to determine to depth map which represents the distance from the camera. In stereo vision system we have used a center-referenced projection to represent the discrete match space for stereo correspondence. This center-referenced disparity space contains new occlusion points in addition to the match points which we exploit to create a concise representation of correspondence an occlusion. And from the depth map we find the target object´s pose and position in 3-D space. To find the target object´s pose and position, we use the method of the model-based recognition.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.10
• /
• pp.28-34
• /
• 1997

This paper describes an automatic measurement method for the in-line inspection of assembly tolerances of cathod ray electron guns. The method uses an optical microscope with a CCD camera as a probe. An automatic gap recognition algorthm with digital image processing and a new software autofocus algorithm based on using an optimal edge detector have been developed to improve the measuring accuracy. An inspection system has been proposed and practically implemented for in-line inspection to a real factory automation line. The inspection system consists of a gap inspection part and an eyelet. Total time consumed for inspecting all measuring items is about 10 seconds and the repeatability is below .+-. 5 .mu. m

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1997.06a
• /
• pp.125-130
• /
• 1997

In this paper we present an algorithm to generate new views of a scene, starting with images from weakly calibrated cameras. Errors in 3D scene reconstruction usually gets reflected in the quality of the new scene generated, so we seek a direct method for reprojection. In this paper, we use the knowledge of dense point matches and their affine coordinate values to estimate the corresponding affine coordinate values in the new scene. We borrow ideas from the object recognition literature, and extend them significantly to solve the problem of reprojection. Unlike the epipolar line intersection algorithms for reprojection which requires at least eight matched points across three images, we need only five matched points. The theory of reprojection is used with hardware based rendering to achieve fast rendering. We demonstrate our results of novel view generation from stereopairs for arbitrary locations of the virtual camera.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.303-304
• /
• 2006

This paper proposes detection method of vehicles using camera for auto-vehicle-system. Detection method is based on shadow detection and symmetric feature of vehicle. This method consists of three part. First is lane detection. By lane detection, we can reduce the area for vehicle detection. Second part is shadow detection. Shadow has information of vehicle width and position. Third part is symmetry. This feature is helpful for confirming the vehicle.

• Annual Conference of KIPS
• /
• 2016.04a
• /
• pp.719-722
• /
• 2016

운전자의 주의력 감쇠는 교통사고 요인에 있어서 큰 비중을 차지한다. 주의력 감쇠는 무선 통화, 기기 조작, 졸음으로 나타날 수 있는데 자동차 대형사고의 대부분은 졸음운전으로 인하여 일어나며, 졸음운전 시에는 운전자의 운전조작 및 방어 조작 능력이 현저하게 저하한다. 본 시스템은 카메라로부터 실시간으로 영상 데이터를 입력 받아 처리하여 운전자의 졸음 상태를 인식하는 시스템으로 운전자에게 졸음방지 기능을 제공한다. Haar-Like Feature cascade classifier 방법을 사용하여 얼굴 및 눈 영역 검출을 하였고 Open Eye, Closed Eye가 학습된 MLP(Multi-Layer Perceptron)를 이용해 눈 깜박임을 인식하여 PERCLOS(Percentage of Eye Close)방법으로 졸음을 판단하였다. 본 논문에서 제안한 방법의 인식률의 정확도를 검증하기 위해 인식률 테스트를 하였다.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.102-105
• /
• 2003

Up to the present studies of the car number recognition system, it is generally known to have serious problems such as relatively long processing time due to the excessive length of data extracted from the number plate based on the current image characteristics, and the image blurring with the physical damage of the brightness and darkness signals of the number plate caused by external impulses with many difficulties in the extraction of the highlighted numbers. In this Paper we used the characteristics firstly having a constant brightness of number plate, and a high density to the horizontal axis, and the influences of highlighted signal could be reduced by making reflections less through the polarized filter on the camera for any highlighted signal. For the more, the data processing time and the noise reduction are effectively implemented by using the wavelet transform of time-space scale with the considerations on the physical loss and processing time.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.6
• /
• pp.281-287
• /
• 2020

In this paper, we propose a method for estimating a walking direction by which a mobile robots follows a person using TRT (Tensor RT) pose, which is motion recognition based on deep learning. Mobile robots can measure individual movements by recognizing key points on the person's pelvis and determine the direction in which the person tries to move. Using these information and the distance between robot and human, the mobile robot can follow the person stably keeping a safe distance from people. The TRT Pose only extracts key point information to prevent privacy issues while a camera in the mobile robot records video. To validate the proposed technology, experiment is carried out successfully where human walks away or toward the mobile robot in zigzag form and the robot continuously follows human with prescribed distance.

• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.1166-1169
• /
• 2011

In this paper, we design a Circle dot Code, In our scheme, we design a dot patterns for increasing maximum capacity and also for increasing robustness to Affine Transformation. Our code Can be extended according number of data circle. We use three data circle vision code. In this type code, after acquiring camera images for the Circle dot Codes, and perform error correction decoding using four position symbols and six CRC symbols. We perform graph based dot code analysis which determines the topological distance between dot pixels. Our code can be bridged the real world and ubiquitous computing environment.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.05a
• /
• pp.40-41
• /
• 2021

The construction industry has the highest occupational accidents/injuries among all industries. Korean government installed surveillance camera systems at construction sites to reduce occupational accident rates. Construction safety managers are monitoring potential hazards at the sites through surveillance system; however, the human capability of monitoring surveillance system with their own eyes has critical issues. Therefore, this study proposed to build a deep learning-based safety monitoring system that can obtain information on the recognition, location, identification of workers and heavy equipment in the construction sites by applying multiple-object tracking with instance segmentation. To evaluate the system's performance, we utilized the MS COCO and MOT challenge metrics. These results present that it is optimal for efficiently automating monitoring surveillance system task at construction sites.