• 제어로봇시스템학회논문지
• /
• 제14권10호
• /
• pp.1053-1061
• /
• 2008

In this paper, a moving target tracking using a binocular vision for an omni-directional mobile robot is addressed. In the binocular vision, three dimensional information on the target is extracted by vision processes including calibration, image correspondence, and 3D reconstruction. The robot controller is constituted with SPI(serial peripheral interface) to communicate effectively between robot master controller and wheel controllers.

• 한국산학기술학회논문지
• /
• 제18권10호
• /
• pp.110-116
• /
• 2017

본 논문에서는 단일 센서 기기를 통해 획득된 CFA (color filter array) 영상의 효과적인 디모자이킹(demosaicking)을 위하여 방향성 기반 보간법과 영상의 비지역 특성을 이용하는 방법을 제안한다. G 채널을 복원하기 위하여 수직 및 수평방향 뿐만 아니라 대각선 방향을 고려하고, 영상의 지역적 특성을 위하여 비교적 적은 수의 픽셀을 이용하여 보간한다. 이후, 영상의 비지역적 특성을 반영하여 에지 근처에서의 복원능력 및 색상오류 등에 의한 화질열화를 개선하기 위하여 보간된 픽셀에 NLM (nonlocal means) 필터링을 적용한다. R과 B 채널은 이미 복원된 G 채널의 정보를 이용하여 방향성 기반 보간법 및 NLM 필터링을 적용하여 복원한다. 채도가 높고 색상변화가 비교적 큰 McMaster 영상에 대해서 수행한 실험결과는 제안하는 디모자이킹 방법이 기존의 방법에 비해 PSNR 기반의 객관적 성능평가 결과가 우수하고, 주관적 화질 측면에서 에지 및 텍스처와 같은 영상의 구조를 잘 보존하고 색상오류 등과 같은 왜곡현상을 감소시켜 우수한 성능을 나타냄을 알 수 있다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권7호
• /
• pp.911-921
• /
• 2004

지문영상으로부터 특징점을 정확하게 추출하는 것은 효과적인 지문인식 시스템의 구축에 매우 중요하다. 하지만 지문영상의 품질에 따라 특징점 추출의 정확도가 달라지기 때문에 지문인식 시스템에서의 영상 전처리 과정은 시스템의 성능에 크게 영향을 미친다. 본 논문에서는 지문영상으로부터 명암값의 평균 및 분산, 블록 방향성 차, 방향성 변화도, 융선과 골의 두께 비율 등의 5가지 특징을 추출하고 계층적 클러스터링 알고리즘으로 클러스터링하여 영상의 품질 특성을 분석한 후 습성(oily), 보통(neutral), 건성(dry)의 특성에 적합하게 영상을 개선하는 지식기반 전처리 방법을 제안한다. NIST DB 4와 인하대학교 데이타를 이용하여 실험한 결과, 클러스터링 기법이 영상의 특성을 제대로 구분함을 확인할 수 있었다. 또한 제안한 방법의 성능 평가를 위해 품질 지수와 블록 방향성 차이를 측정하여 일반적인 전처리 방법보다 지식기반 전처리 방법이 품질 지수와 블록 방향성 차이를 향상시킴을 확인할 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제20권11호
• /
• pp.1720-1728
• /
• 2017

Active shape model is widely used in the field of image processing especially on arbitrary meaningful shape extraction from single gray level image. Cootes et. al. showed efficient detection of variable shape from image by using covariance and mean shape from learning. There are two stages of learning and testing. Hahn applied enhanced shape alignment method rather than using Cootes's rotation and scale scheme. Hahn did not modified the profile itself. In this paper, the method using directional one dimensional profile is proposed to enhance Cootes's one dimensional profile and the shape alignment algorithm of Hahn is combined. The performance of the proposed method was superior to Cootes's and Hahn's. Average landmark estimation error for each image was 27.72 pixels and 39.46 for Cootes's and 33.73 for Hahn's each.

• 전자공학회논문지S
• /
• 제34S권3호
• /
• pp.84-96
• /
• 1997

In this paper an efficient morphologica algorithm for reducing gaussian and impulse noise in gray-scale image is presented. Based on the edge information the input image is partitioned into a flat region and an edge region, then different algorithms are selectively applied to each region. in case of impulse noise, MGR (morphologica grayscale reconstruction) algorithm with directional SE (structuring element) is applied to the flat region. For theedge region opening-closing (closing-opening) is used instead of dialation (erosion), so that the remaining noise around large objects can be removed. In case of gaussian noise, 5*5 OCCO(opening closing closing opening) and 3*3 DMF(directional morphological filter ) are used for the flat region and the edgeregion, respectively. In order to remove discontinuity at the edge boundary, the algorithm uses 3*3 OCCO around the edge region to reconstruct the final image. Experimetnal results have shown that the proposed algorithm achieves a high performance in terms of noise removal, detail preservation, and NMSE.

• Journal of Information Processing Systems
• /
• 제8권4호
• /
• pp.685-692
• /
• 2012

B frame bi-directional predictions and the DIRECT mode coding of the H.264 video compression standard necessitate a complex mode decision process, resulting in a long computation time. To make H.264 feasible, this paper proposes an image backtrack-based fast (IBFD) algorithm and evaluates the performances of two promising fast algorithms (i.e., AFDM and IBFD). Evaluation results show that an image backtrack-based fast (IBFD) algorithm can determine DIRECT mode macroblocks with 13% higher accuracy, as compared with the AFDM. Furthermore, IBFD is shown to reduce the motion estimation time of B frames by up to 23% with a negligible quality degradation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권9호
• /
• pp.4549-4566
• /
• 2017

This work presents a novel facial descriptor, which is named as multiscale adaptive local directional texture pattern (MALDTP) and employed for expression recognition. We apply an adaptive threshold value to encode facial image in different scales, and concatenate a series of histograms based on the MALDTP to generate facial descriptor in term of Gabor filters. In addition, some dedicated experiments were conducted to evaluate the performance of the MALDTP method in a person-independent way. The experimental results demonstrate that our proposed method achieves higher recognition rate than local directional texture pattern (LDTP). Moreover, the MALDTP method has lower computational complexity, fewer storage space and higher classification accuracy than local Gabor binary pattern histogram sequence (LGBPHS) method. In a nutshell, the proposed MALDTP method can not only avoid choosing the threshold by experience but also contain much more structural and contrast information of facial image than LDTP.

• 제어로봇시스템학회논문지
• /
• 제21권7호
• /
• pp.634-640
• /
• 2015

This paper proposes a novel three-dimensional mapping algorithm in Omni-Directional Vision SLAM based on a fisheye image and laser scanner data. The performance of SLAM has been improved by various estimation methods, sensors with multiple functions, or sensor fusion. Conventional 3D SLAM approaches which mainly employed RGB-D cameras to obtain depth information are not suitable for mobile robot applications because RGB-D camera system with multiple cameras have a greater size and slow processing time for the calculation of the depth information for omni-directional images. In this paper, we used a fisheye camera installed facing downwards and a two-dimensional laser scanner separate from the camera at a constant distance. We calculated fusion points from the plane coordinates of obstacles obtained by the information of the two-dimensional laser scanner and the outline of obstacles obtained by the omni-directional image sensor that can acquire surround view at the same time. The effectiveness of the proposed method is confirmed through comparison between maps obtained using the proposed algorithm and real maps.

• 한국통신학회논문지
• /
• 제32권2C호
• /
• pp.124-131
• /
• 2007

본 논문에서는 전송 에러로 인해 발생하는 영상의 손실을 정밀한 방향성 보간(FDI: Fine Directional Interpolation)을 이용하여 복원하는 기법을 제안한다. 제안된 알고리즘은 공간 방향 벡터(SDV: Spatial Direction Vector)를 도입한다. 공간 방향 벡터는 손실블럭 주위의 영상 데이터의 에지 정보를 추출하여 구한다. 이 후 손실된 영상 블록은 공간 방향 벡터를 이용하여 픽셀단위로 적응적으로 보간함으로써 복원된다. 이러한 방식은 평탄한 영역뿐만 아니라 에지를 포함한 복잡한 영역도 우수하게 복원할 수 있다. 실험결과 제안된 방식은 기존의 공간적 에러은닉 방법과 비교하여 성능이 우수하다는 것을 알 수 있다.

• 전자공학회논문지B
• /
• 제30B권9호
• /
• pp.76-83
• /
• 1993

A morphological filtering algorithm using directional information is presented. Directional filtering technique is effective in reducing noises and preserving edges. The proposed directional filtering is composed of two stage filtering processes. The opening and closing operations in the lst stage are performed for the pixels is aligned to the vertical, horizontal, and two diagonal directions, respectively. The opening operation supresses the positive impulse noises, while the closing operation the negative ones. Then, each directional result and their average value are filtered by the opening or closing operations in the 2nd stage. The averaging operation diminishes the effects of Gaussian noises in the homogeneous regions. Thus, the morphological operation in the 1 st stageremoves the impulse noises and in 2nd stage reduces. Gaussian ones. The experimental results show that the proposed filtering is superior to the existing nonlinear filtering in the aspects of the subjective quality. Also, the morphological filtering method reduces the computational loads.