• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10c
• /
• pp.424-427
• /
• 2007

스테레오 영상으로부터 3차원 구조를 복원하기 위해서는 깊이맵에 해당하는 시차맵을 생성해야 한다. 시차맵 생성을 위해서는 정합비용을 계산하고, 집성한 후에 시차를 계산하는 절차로 이루어진다. 본 논문에서는 스테레오 영상으로부터 빠르고 안정된 시차맵을 생성하기 위해서 후처리 과정으로 각 스캔라인에 대해서 분산을 이용하여 세그멘테이션을 한 후에 세그멘테이션 별로 평균을 내어 객체간의 구분을 명확히 한다. 조밀 시차맵을 생성하기 위해서는 시차 계산에 실패한 화소들에 대해서도 시차를 계산해야 하는데 본 논문에서는 간단하게 인접 화소의 값을 복사하는 방법으로 홀을 메우는 방법을 제안한다. 실제 환경에서의 다양한 스테레오 영상에 대한 실험 결과들은 제안된 시차맵 생성과 홀을 메우는 방법이 기존의 시차맵 생성 기법만큼 빠르고 기존의 방법보다 좀더 안정적이고 다양한 컴퓨터 비전 시스템응용에 적용될 수 있음을 보여준다.

• Journal of KIISE
• /
• v.44 no.9
• /
• pp.932-945
• /
• 2017

In this paper, a new hardware and software architecture for a stereo vision processing system including rectification, disparity estimation, and visualization was developed. The developed method, named LArge scale stereo matching method using Support Point Interpolation (LASPI), shows excellence in real-time processing for obtaining dense disparity maps from high quality image regions that contain high density support points. In the real-time processing of high definition (HD) images, LASPI does not degrade the quality level of disparity maps compared to existing stereo-matching methods such as Efficient LArge-scale Stereo matching (ELAS). LASPI has been designed to meet a high frame-rate, accurate distance resolution performance, and a low resource usage even in a limited resource environment. These characteristics enable LASPI to be deployed to safety-critical applications such as an obstacle recognition system and distance detection system for autonomous vehicles. A Field Programmable Gate Array (FPGA) for the LASPI algorithm has been implemented in order to support parallel processing and 4-stage pipelining. From various experiments, it was verified that the developed FPGA system (Xilinx Virtex-7 FPGA, 148.5MHz Clock) is capable of processing 30 HD ($1280{\times}720pixels$) frames per second in real-time while it generates disparity maps that are applicable to real vehicles.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.9
• /
• pp.639-646
• /
• 2022

Landing site searching algorithms are developed for a quadrotor using a depth map in unknown environment. Guidance and control system of Unmanned Aerial Vehicle (UAV) consists of a trajectory planner, a position and an attitude controller. Landing site is selected based on the information of the depth map which is acquired by a stereo vision sensor attached on the gimbal system pointing downwards. Flatness information is obtained by the maximum depth difference of a predefined depth map region, and the distance from the UAV is also considered. This study proposes three landing methods and compares their performance using various indices such as UAV travel distance, map accuracy, obstacle response time etc.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.11a
• /
• pp.751-754
• /
• 2005

본 논문에서는 인간의 머리부분을 흉내 낸 시각 시스템으로서, 4 축의 각도 조절이 자유로운 시스템에 두 개의 CCD 카메라를 연결하여 실시간으로 입력되는 영상 데이터로부터 레이져 포인터의 위치 정보를 추출한 후 주 카메라를 이용하여 시스템 전체를 레이저 포인터의 중심위치로 이동한 후 버전스 각도(vergence angle)를 이용하여 실시간으로 오브젝트의 절대거리를 측정하는 효과적인 시스템을 제안하였다. 객체까지의 거리는 교차식 카메라를 적용한 스테레오 비전 시스템을 사용하여 삼각측량의 방법으로 거리를 측정하였다. 실험결과 객체에 대한 거리 측정 오차가 평균 2% 나타남으로써 제안한 알고리즘을 이용한 이동객체의 거리측정 가능성을 제시하였다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.41 no.5
• /
• pp.422-428
• /
• 2013

Recently, many unmanned aerial vehicle (UAV) studies have focused on small UAVs, because they are cost effective and suitable in dangerous indoor environments where human entry is limited. Map building through distance measurement is a key technology for the autonomous flight of small UAVs. In many researches for unmanned systems, distance could be measured by using laser range finders or stereo vision sensors. Even though a laser range finder provides accurate distance measurements, it has a disadvantage of high cost. Calculating the distance using a stereo vision sensor is straightforward. However, the sensor is large and heavy, which is not suitable for small UAVs with limited payload. This paper suggests a low-cost distance measurement system using a laser pointer and a monocular vision sensor. A method to measure distance using the suggested system is explained and some experiments on map building are conducted with these distance measurements. The experimental results are compared to the actual data and the reliability of the suggested system is verified.

• Journal of Internet Computing and Services
• /
• v.11 no.6
• /
• pp.21-29
• /
• 2010

In this paper, we propose the system which detects the speaker, who is speaking currently, among a number of users. A proposed speaker detection system based on stereo vision and audio is mainly composed of the followings: a position estimation of speaker candidates using stereo camara and microphone, a current speaker detection, and a speaker information acquisition based on a mobile device. We use the haar-like features and the adaboost algorithm to detect the faces of speaker candidates with stereo camera, and the position of speaker candidates is estimated by a triangulation method. Next, the Time Delay Of Arrival (TDOA) is estimated by the Cross Power Spectrum Phase (CPSP) analysis to find the direction of source with two microphone. Finally we acquire the information of the speaker including his position, voice, and face by comparing the information of the stereo camera with that of two microphone. Furthermore, the proposed system includes a TCP client/server connection method for mobile service.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.8
• /
• pp.671-677
• /
• 2017

A new INS/Vision integrated navigation system by using multi-vision sensors is addressed in this paper. When the total number of landmark measured by the vision sensor is smaller than the allowable number, there is possibility that the navigation filter can diverge. To prevent this problem, multi-vision concept is applied to expend the field of view so that reliable number of landmarks are always guaranteed. In this work, the orientation of camera installed are 0, 120, and -120degree with respect to the body frame to improve the observability. Finally, the proposed technique is verified by using numerical simulation.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1999.12a
• /
• pp.597-604
• /
• 1999

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.05a
• /
• pp.175-175
• /
• 2004

애니메이션과 컴퓨터 게임 등의 다양한 산업에 이용되고 있는 모션캡쳐 시스템은 현재 카메라를 이용한 고가의 고속 카메라를 사용하여 일반인들이 범용으로 사용하기에는 많은 어려움이 따른다. 이에 본 연구에서는 고가의 고속카메라를 사용하는 대신 저가의 PSD 센서를 사용하여 광학방식의 모션캡쳐 시스템을 구성하였다. 또한 시스템에서 획득한 3 차원 데이터의 정확성을 위해 일반적으로 CCD 카메라에 사용되어지는 카메라 보정 알고리즘을 PSD 모션캡쳐 시스템에 적용하여 손쉽게 보정을 하면서 적은 오차를 가질 수 있는 방법을 제시하였다.(중략)

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.934-937
• /
• 2003

In this paper, authors use a stereo vision system based on the visual model of human and establish inexpensive method that recognizes moving distance using characteristic points around the robot. With the stereovision. the changes of the coordinate values of the characteristic points that are fixed around the robot are measured. Self-displacement and self-localization recognition system is proposed from coordination reconstruction with those changes. To evaluate the proposed system, several characteristic points that is made with a LED around the robot and two cheap USB PC cameras are used. The mobile robot measures the coordinate value of each characteristic point at its initial position. After moving, the robot measures the coordinate values of the characteristic points those are set at the initial position. The mobile robot compares the changes of these several coordinate values and converts transformation matrix from these coordinate changes. As a matrix of the amount and the direction of moving displacement of the mobile robot, the obtained transformation matrix represents self-displacement and self-localization by the environment.