• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권9호
• /
• pp.1613-1631
• /
• 2011

Several metrics have been reported in the literature to assess stereo image quality, mostly based on visual attention or human visual sensitivity based distortion prediction with the help of disparity information, which do not consider the combined aspects of human visual processing. In this paper, visual attention and depth assisted stereo image quality assessment model (VAD-SIQAM) is devised that consists of three main components, i.e., stereo attention predictor (SAP), depth variation (DV), and stereo distortion predictor (SDP). Visual attention is modeled based on entropy and inverse contrast to detect regions or objects of interest/attention. Depth variation is fused into the attention probability to account for the amount of changed depth in distorted stereo images. Finally, the stereo distortion predictor is designed by integrating distortion probability, which is based on low-level human visual system (HVS), responses into actual attention probabilities. The results show that regions of attention are detected among the visually significant distortions in the stereo image pair. Drawbacks of human visual sensitivity based picture quality metrics are alleviated by integrating visual attention and depth information. We also show that positive correlation with ground-truth attention and depth maps are increased by up to 0.949 and 0.936 in terms of the Pearson and the Spearman correlation coefficients, respectively.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1996년도 춘계학술대회
• /
• pp.36-40
• /
• 1996

There are two prevailing techniques, mechanical and optical profilometers, to measure 3-dimensional configurations of the human skin furrows. The methods have some limitations such as, accuracies or resolutions of the acquired 3-dimensional data and consistencies according to the repeated experiments. We devised an optical profilometer that is called stereo image optical profilometer (SOP) based on stereo image processing techniques. A stereo image is a pair of images that obtained from two cameras which have different angles. From the digital stereo images, the clinical informations for skin can be obtained by some signal processing techniques. In this paper, we focused on the 3-dimensional graphical visualizations of the structures and state of the skin furrows by solving the corresponding problem from the left and right pairs of the stereo images.

• 한국지능시스템학회논문지
• /
• 제22권2호
• /
• pp.198-204
• /
• 2012

로봇들의 협동 작업을 위해서는 다양한 환경에서 다른 로봇들을 인식하고 추적하는 기술이 요구된다. 본 논문에서는 코드북 모델과 스테레오 영상 처리를 이용하여 이동 로봇을 인식하고, 퍼지 제어기를 사용해 추적하는 이동 로봇 추적 제어 시스템을 제안한다. 먼저 코드북 모델을 사용하여 영상의 전경과 배경을 분리하였다. 분리된 전경에서 색상정보를 기반으로 관심영역을 구해내고, 스테레오 영상처리를 통해 얻은 깊이 영상을 기반으로 이동 로봇까지의 실제 거리를 추정한다. 각 거리에 따라 열림 및 닫힘 연산을 적용하고, 모듈형 로봇의 크기에 맞춰 라벨링을 통해 효과적으로 이동 로봇을 인식한다. 추출된 이동 로봇의 움직임에 따른 효과적인 추적을 위하여 스테레오 영상 처리를 통해 얻은 거리 정보와 로봇의 이동 정보를 이용해 퍼지 제어기를 설계하여 이동 로봇 추적 시스템을 제안하였다. 제안한 퍼지 추적 제어 시스템의 성능은 실제 이동 로봇의 추적 실험을 통하여 검증하였다.

• 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.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 1997년도 추계학술대회논문집
• /
• pp.147-152
• /
• 1997

This paper presents a method for measuring and analyzing strains in sheet metal forming by stereo vision system. A better understanding and evaluation of the formability can be achieved by analyzing stain distribution in deformed sheet metals. By means of image processing technique, it is possible to get strain distribution efficiently. For measuring strain automatically and accurately, algorithms for camera calibration, grid detection, stereo matching and strain analysis has been developed and verified by experiments with GUI(Graphic User Interface).

• Journal of Multimedia Information System
• /
• 제9권3호
• /
• pp.183-190
• /
• 2022

Image-based 3D object detection is one of the important and difficult problems in autonomous driving and robotics, and aims to find and represent the location, dimension and orientation of the object of interest. It generates three dimensional (3D) bounding boxes with only 2D images obtained from cameras, so there is no need for devices that provide accurate depth information such as LiDAR or Radar. Image-based methods can be divided into three main categories: monocular, stereo, and multi-view 3D object detection. In this paper, we investigate the recent state-of-the-art models of the above three categories. In the multi-view 3D object detection, which appeared together with the release of the new benchmark datasets, NuScenes and Waymo, we discuss the differences from the existing monocular and stereo methods. Also, we analyze their performance and discuss the advantages and disadvantages of them. Finally, we conclude the remaining challenges and a future direction in this field.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 1997년도 춘계학술대회논문집
• /
• pp.207-212
• /
• 1997

In estimating the formability of sheet metal, the stereo vision system contributes the accuracy of strain of sheet metal, the convenience in measuring the strain of sheet metal, and the handiness in preparing the forming limit diagram by calculating the 3D values and strain of sheet metal. The algorithm has been developed so that the 3D-coordinate values of sheet metal could be calculated by image processing which is composed of camera calibration, and the stereo matching of images in two viewpoints. By comparing with experiments, the possibility and the convenience of algorithm has been verified, which could calculate the 3D-coordinate values of sheet metal automatically by using the preprocessing of the original image of sheet metal, which had the noise before adjusting the camera calibration and the stereo matching algorithm.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2010년도 하계학술대회 논문집
• /
• pp.293-293
• /
• 2010

In this paper, we propose a stereo vision based monitoring concept for passenger's safety on railroad platform. In general, basic concept of stereo image processing technique uses the correlations between left and right images, and extracts additional distance information. It provides easy removal of ambient illumination changes, which has been difficult to achieve with conventional 2D based image processing technique. In the paper, we present developed stereo camera and stereo vision based detection algorithm in order to monitor possible accidents at platform area, and verified the detection performance of proposed system with experimental results.

• 한국정보통신학회논문지
• /
• 제15권7호
• /
• pp.1583-1590
• /
• 2011

기존 방사선 검색장치는 2차원 방사선 스캔 영상을 사용하기 때문에 정확성이 낮다는 것이 문제점으로 지적되어왔다. 본 연구에서는 컨테이터 X-선 검색 영상에 대한 스테레오 영상처리 기술의 적용 가능성을 분석하였다. 일반적 방사선 검색장치에 라인 센서 하나만을 추가하여 새롭게 고안한 스테레오 영상획득 장치로부터 검사 오브젝트의 좌우 시차 정보를 달리하는 두 장의 이차원 방사선 스캔영상을 획득하였다. 획득 영상에 대해서 매칭 알고리즘을 이용하여 3차원 오브젝트 복원하는 과정을 진행하였다. 오브젝트의 투과밀도 정보인 방사선 영상의 특성상 일반 스테레오 영상처리 알고리즘 적용은 한계가 발생하였다. 이를 극복하기 위해 먼저 이차원 영상의 에지정보에 기반한 3차원 영상복원을 시도하였다. 또한 새로운 볼륨복원 방식의 3차원 복원 알고리즘을 제안하였고, 실험을 통해 오브젝트 검색에서 개선된 형상복원 방법임을 확인하였다. 제안된 기술은 제한된 스캔환경에서 CT나 MRI 적용이 어려운 오브젝트에 대해 응용이 가능할 것이다.

• 한국공작기계학회논문집
• /
• 제16권5호
• /
• pp.178-182
• /
• 2007

This study represents the efficient depth measurement for 3-dimensional microsystems using the disparity histogram from stereo images. Implementation of user-friendly Windows program written in C++ involves the various methods for the stereo-image processing in which the minimization of matching-pixel error upon the unique point for stereo images was carried out as a pre-processing method. Even though MPC among various methods was adopted in the present measurement, the resulting measurements seem to require optimizations of the windows sizes and corrections of post-manipulation for stereo images. The present work using Windows program is promising to measure the 3-dimensional depth of micro-system efficiently in implementing the 3-dimensional structure of micro-systems.