• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.2
• /
• pp.441-445
• /
• 2011

In this paper, we propose an algorithm for generating panoramic videos using fixed multiple cameras. We estimate a background image from each camera. Then we calculate perspective relationships between images using extracted feature points. To eliminate stitching errors due to different image depths, we process background images and foreground images separately in the overlap regions between adjacent cameras by projecting regions of foreground images selectively. The proposed algorithm can be used to enhance the efficiency and convenience of wide-area surveillance systems.

• Annual Conference of KIPS
• /
• 2006.11a
• /
• pp.65-68
• /
• 2006

카메라로 촬영한 문서 영상의 분석 및 인식을 위한 적응적 이진화 방법을 제안한다. 먼저 카메라 영상의 화질을 분석하여 정량화하는 방법을 제안한다. 그 후 다양한 화질의 카메라 영상에 대하여 제안한 방법으로 측정한 화질과 그 화질에 적합한 이진화 파라미터간의 상관 관계를 통계적으로 분석한다. 그 후 그들간의 상관 관계를 이용하여 입력 영상의 화질에 적합한 이진화 파라미터를 자동으로 추정하도록 함으로써 화질 변화에 대한 적응력을 강화하였다. 실험을 통해 초점 및 잡영의 상태에 따라 적절한 파라미터를 추정함으로써 화질 변화에 적응하는 결과를 확인하였다.

• Proceedings of the Optical Society of Korea Conference
• /
• 2003.07a
• /
• pp.26-27
• /
• 2003

A wide variety of devices and systems exist whose main function is to generate an image. These devices and systems are used for many different purposes and find applications in many different walks of life. We are all very familiar with some of these systems such as the photographic camera (that can produce a permanent record of a scene on sensitized sheet material) and the television set (that can receive a suitably coded electromagnetic signal broadcast through space and convert it into an image). (omitted)

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1458-1463
• /
• 2004

Tracking is one of the most important pre-required task for many application such as human-computer interaction through gesture and face recognition, motion analysis, visual servoing, augment reality, industrial assembly and robot obstacle avoidance. Recently, 3D information of object is required in realtime for many aforementioned applications. 3D tracking is difficult problem to solve because during the image formation process of the camera, explicit 3D information about objects in the scene is lost. Recently, many vision system use stereo camera especially for 3D tracking. The 3D feature based tracking(3DFBT) which is on of the 3D tracking system using stereo vision have many advantage compare to other tracking methods. If we assumed the correspondence problem which is one of the subproblem of 3DFBT is solved, the accuracy of tracking depends on the accuracy of camera calibration. However, The existing calibration method based on accurate camera model so that modelling error and weakness to lens distortion are embedded. Therefore, this thesis proposes 3D feature based tracking method using SVM which is used to solve reconstruction problem.

• The Journal of Korea Robotics Society
• /
• v.11 no.1
• /
• pp.9-18
• /
• 2016

A rectangle-based relative localization method is proposed for a mobile robot based on a novel geometric formulation. In an artificial environment where a mobile robot navigates, rectangular shapes are ubiquitous. When a scene rectangle is captured using a camera attached to a mobile robot, localization can be performed and described in the relative coordinates of the scene rectangle. Especially, our method works with a single image for a scene rectangle whose aspect ratio is not known. Moreover, a camera calibration is unnecessary with an assumption of the pinhole camera model. The proposed method is largely based on the theory of coupled line cameras (CLC), which provides a basis for efficient computation with analytic solutions and intuitive geometric interpretation. We introduce the fundamentals of CLC and describe the proposed method with some experimental results in simulation environment.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.34 no.1
• /
• pp.135-137
• /
• 2005

A PC-based automatic system was developed for automatic titration in volatile basic nitrogen analysis by the microdiffusion method. The system used a CCD-type PC camera for the automatic detection of the titration end point. The camera checked whether the green value of a pixel on the red image of titrated solution became greater than the red value. The data from the automatic titration using the system were not significantly different (p>0.05) from those taken by manual titration. The agreement between means of data from manual titration and those from automatic titration was good.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.6
• /
• pp.49-58
• /
• 2014

This paper proposes a new assessment and reliability validation method of Lane Departure Assistance System based on DGPS-GIS by measuring lanes with camera vision. Assessment of lane departure is performed with yaw speed measurement and determination method for false alarm of ISO 17361 and performance validation is executed after generating departure warning boundary line by considering deviation error of LDAS using DGPS. Distance between the wheel and the lane is obtained through line abstraction using Hough transformation of the lane image with camera vision. Evaluation validation is obtained by comparing this value with the distance obtained with LDAS. The experimental result shows that the error of the extracted distance of the LDAS is within 5 cm. Also it proves performance of LDAS based on DGPS-GIS and assures effectiveness of the proposed validation method for system reliability using camera vision.

• International Journal of Highway Engineering
• /
• v.8 no.1 s.27
• /
• pp.65-75
• /
• 2006

According to development of computer technology, the utilization of the fourth generation of digital photogrammetry progresses favorable. Especially the method of using digital video camera is very practicable and has an advantage such as a profitability for the amateur. In road field which if centrical facilities of national industry, this method was utilized to acquire road information for the safety diagnosis or maintenance. In this study, 3-dimensional position information of road centerline was extracted using digital video camera which has practicality and economical efficiency. This data could be a basic source in road information project.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.286-288
• /
• 2013

감시 카메라에서 야간 시간대의 영상 품질은 매우 중요한 요소 중 하나이다. 본 논문에서는 IR LED Camera 에서 적외선 LED 를 사용한 회로적 제어를 통한 노출 제어에 문제점을 분석하고, 이를 해결하기 위한 적응적 배경 모델링과 IR 카메라의 특화된 객체 검출 방법을 제안한다. 노출 제어 방식의 배경을 제외한 적응적 배경과 객체의 합성으로 향상된 야간 영상획득 방식을 제안한다. 영상 개선 실험 결과는 기존의 회로적 노출 제어 방식의 영상보다 제안하는 방식이 프로세스의 단순화를 통한 비용 절감 효과와 야간 영상 품질 향상의 우수성을 보여준다.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.536-538
• /
• 2006

The most important factor of mobile robot is to build a map for surrounding environment and estimate its localization. This paper proposes a real-time localization and map building method through 3-D reconstruction using scale invariant feature from monocular camera. Mobile robot attached monocular camera looking wall extracts scale invariant features in each image using SIFT(Scale Invariant Feature Transform) as it follows wall. Matching is carried out by the extracted features and matching feature map that is transformed into absolute coordinates using 3-D reconstruction of point and geometrical analysis of surrounding environment build, and store it map database. After finished feature map building, the robot finds some points matched with previous feature map and find its pose by affine parameter in real time. Position error of the proposed method was maximum. 8cm and angle error was within $10^{\circ}$.