• 한국정보통신학회논문지
• /
• 제16권3호
• /
• pp.407-415
• /
• 2012

본 논문에서는 화상회의 시스템 등 인물 위주의 스테레오 영상으로부터 깊이 정보를 추출하기 위한 스테레오 정합 기법을 제안한다. 제안한 기법에서는 두 대의 스테레오 카메라로부터 획득된 영상에서 임계값을 이용하여 배경을 먼저 제거하고, 배경이 제거된 영상과 카메라 보정을 거친 영상을 이용하여 초기 변이지도(disparity map)와 R, G, B, white 4개의 색상 성분으로 분할한 영상을 생성하게 된다. 각 색상 정보로 분할된 영상의 경계(edge) 성분을 추출하고, 추출된 경계에서 정합 창을 이용하여 변이를 추정하고 각 색상 정보의 변이지도를 적절히 조합하여 최종 변이지도를 생성하게 된다. 실험 결과 제안한 기법이 기존의 영역기반(window based) 정합기법과 동적계획법(dynamic programing method) 등보다 인물 위주의 스테레오 영상에서 더 우수한 성능을 가지는 것을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.871-875
• /
• 2003

To detect and avoid obstacles is one of the important tasks of mobile navigation. In a real environment, when a mobile robot encounters dynamic obstacles, it is required to simultaneously detect and avoid obstacles for its body safely. In previous vision system, mobile robot has used it as either a passive sensor or an active sensor. This paper proposes a new obstacle detection algorithm that uses a stereo camera as both a passive sensor and an active sensor. Our system estimates the distances from obstacles by both passive-correspondence and active-correspondence using laser slit. The system operates in three steps. First, a far-off obstacle is detected by the disparity from stereo correspondence. Next, a close obstacle is acquired from laser slit beam projected in the same stereo image. Finally, we implement obstacle avoidance algorithm, adopting the modified Dynamic Window Approach (DWA), by using the acquired the obstacle's distance.

• 대한전자공학회논문지SP
• /
• 제48권2호
• /
• pp.88-95
• /
• 2011

스테레오 매칭은 두 영상의 차이를 이용하여 거리를 추정하는 연구 분야로 성능 개선과 함께 처리속도 향상을 위한 연구가 계속되고 있다. 본 논문에서는 계층적 Belief Propagation(BP) 알고리즘을 개선하여 기존의 BP에서의 수렴구간을 메시지 맵으로 만들고 이를 이용하여 처리속도를 향상시키는 Plane-converging BP 알고리즘을 제안한다. 또한 GPU 아키텍쳐인 Nvidia의 CUDA를 이용하여 다수의 계산을 병렬화 하고 이를 동시에 처리하여 실시간 어플리케이션에 적합한 스테레오 매칭 기법을 개발하였다. Plane-converging BP 알고리즘은 기존의 계층적 BP 알고리즘과 유사한 에러율을 가지면서 약 2.7배의 속도 향상을 이루었다.

• 센서학회지
• /
• 제6권2호
• /
• pp.123-130
• /
• 1997

이 논문은 다음과 같은 두가지 요소로 구성되는 독창적인 stereo vision system을 논술한다. declivity라는 새로운 개념을 도입한 자동선택 영상 분할처리 (self-adaptive image segmentation process) 와 자동선택 결정변수 (self-adaptive decision parameters) 를 응용하여 설계된 신속한 stereo matching algorithm. 현재, 실내 image의 depth map을 완성하는데 SUN-IPX 에서 3sec가 소요되나 연구중인 DSP Chip의 조합은 이 시간을 1초 이하로 단축시킬 수 있을 것이다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.1848-1851
• /
• 1997

This paper presents the development of depth detection algorithm for the 3D Endoscopic Data using a stereo matchod and depth calcuation.

• 대한기계학회논문집A
• /
• 제27권7호
• /
• pp.1110-1119
• /
• 2003

This paper deals with the synthesis of the 3-dimensional grasp planning for unknown objects. Previous studies have many problems, which the estimation time for finding the grasping points is much long and the analysis used the not-perfect 3-dimensional modeling. To overcome these limitations in this paper new algorithm is proposed, which algorithm is achieved by two steps. First step is to find the whole 3-dimensional geometrical modeling for unknown objects by using stereo matching. Second step is to find the optimal grasping points for unknown objects by using the neural network trained by the result of optimization using genetic algorithm. The algorithm is verified by computer simulation, comparing the result between neural network and optimization.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 추계학술대회논문집B
• /
• pp.410-416
• /
• 2001

An algorithm of 3-D particle image velocimetry(3D-PIV) was developed for the measurement of 3-D velocity field of complex flows. The measurement system consists of two or three CCD camera and one RGB image grabber. In this study, stereo photogrammetty was applied for the 3-D matching of tracer particles. Epipolar line was used to decect the stereo pair. 3-D CFD data was used to estimate algorithm. 3-D position data of the first frame and the second frame was used to find velocity vector. Continuity equation was applied to extract error vector. The algorithm result involved error vecotor of about 0.13 %. In Pentium III 450MHz processor, the calculation time of cross-correlation for 1500 particles needed about 1 minute.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권7호
• /
• pp.509-516
• /
• 2004

This paper proposes an image processing algorithm for detecting obstacles on road using DLI(disparity of lane-related information) that is generated by stereo images acquired from dual cameras mounted on a moving vehicle. The DLI is a disparity that is acquired using a single lane information from road lane detection. For the purpose to reduce processing time, we use small block of edge-histogram based blocking logic. This algorithm detects moving objects such as preceding vehicles and obstacles. The proposed algorithm has been implemented in a personal computer with the road image data of a typical highway. We successfully performed experiments under a wide variety of road conditions without changing parameter values or adding human intervention. Experimental results also showed that the proposed DLI is quite successful.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.310-310
• /
• 2000

The main problem in stereo vision is to find corresponding points in left and right image known as correspondence problem. Once correspondences determined, the depth information of those points are easily computed form the pairs of points in both image. In this paper, dynamic programming considering half-occluded region is used fer solving correspondence problem.

• Journal of information and communication convergence engineering
• /
• 제9권1호
• /
• pp.83-88
• /
• 2011

Abstract. Image segmentation is always a challenging task in computer vision as well as in pattern recognition. Nowadays, this method has great importance in the field of stereo vision. The disparity information extracting from the binocular image pairs has essential relevance in the fields like Stereoscopic (3D) Imaging Systems, Virtual Reality and 3D Graphics. The term 'disparity' represents the horizontal shift between left camera image and right camera image. Till now, many methods are proposed to visualize or estimate the disparity. In this paper, we present a new technique to visualize the horizontal disparity between two stereo images based on image segmentation method. The process of comparing left camera image with right camera image is popularly known as 'Stereo-Matching'. This method is used in the field of stereo vision for many years and it has large contribution in generating depth and disparity maps. Correlation based stereo-matching are used most of the times to visualize the disparity. Although, for few stereo image pairs it is easy to estimate the horizontal disparity but in case of some other stereo images it becomes quite difficult to distinguish the disparity. Therefore, in order to visualize the horizontal disparity between any stereo image pairs in more robust way, a novel stereo-matching algorithm is proposed which is named as "Quadtree Segmentation of Pixels Disparity Estimation (QSPDE)".