http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
차영상 정보를 이용한 효율적인 블록기반 스테레오 영상 변이 추정에 관한 연구
박상현,손광훈 延世大學校 電波通信共同硏究所 1999 電波通信論文誌 Vol.4 No.1
본 논문에서는 좌·우 영상의 차 영상 정보를 이용하여 3차원 스테레오 영상의 변이를 추정함에 있어서 계산량을 줄이는 변이 추정방법을 제안하였다. 좌·우 영상의 차영상을 이용하여 차영상의 블록 특성에 따라 추정하고자하는 블록들을 분류하여 각각 그 특성에 맞는 적합한 탐색범위를 가지고 변이 추정방식 과정을 수행한다. 제안한 알고리듬으로 변이 추정된 영상을 기존의 블록 기반 변이 추정 방식과 화질 개선과 변이 벡터의 정보량을 통하여 비교하였다. 본 논문에서 제안한 차영상 정보를 이용한 알고리듬은 기존의 방식보다 25% 계산량이 감소됨에도 불구하고 비교적 좋은 화질을 유지할 수 있다. In this paper, a display estimation method for reducing the calculation load in estimating the disparity of stereoscopic image using difference image information of left and right image. The algorithm this paper proposes is operated with the procedure to estimate in the appropriate search area against each block after classifying the blocks to estimate based on the block characteristics of difference image using the difference image of left and right image. The Performance and effect of algorithm this paper proposes are as follows: In comparison with the full search algorithm about calculation load, the total load is effectively decreased around 25%. However, even if the total calculation load is decreased, the degradation is only little made and the reconstructed image is also little distorted, but the Quality is still resonable to see in comparing with the full search algorithm.
No-Reference Quality Assessment for Stereoscopic Images Based on Binocular Quality Perception
Seungchul Ryu,Kwanghoon Sohn Institute of Electrical and Electronics Engineers 2014 IEEE Transactions on Circuits and Systems for Vide Vol. No.
<P>Quality perception of 3-D images is one of the most important parameters for accelerating advances in 3-D imaging fields. Despite active research in recent years for understanding the quality perception of 3-D images, binocular quality perception of asymmetric distortions in stereoscopic images is not thoroughly comprehended. In this paper, we explore the relationship between the perceptual quality of stereoscopic images and visual information, and introduce a model for binocular quality perception. Based on this binocular quality perception model, a no-reference quality metric for stereoscopic images is proposed. The proposed metric is a top-down method modeling the binocular quality perception of the human visual system in the context of blurriness and blockiness. Perceptual blurriness and blockiness scores of left and right images were computed using local blurriness, blockiness, and visual saliency information and then combined into an overall quality index using the binocular quality perception model. Experiments for image and video databases show that the proposed metric provides consistent correlations with subjective quality scores. The results also show that the proposed metric provides higher performance than existing full-reference methods even though the proposed method is a no-reference approach.</P>
Superpixel-based Vehicle Detection using Plane Normal Vector in Dispar ity Space
Seo, Jeonghyun,Sohn, Kwanghoon Korea Multimedia Society 2016 멀티미디어학회논문지 Vol.19 No.6
This paper proposes a framework of superpixel-based vehicle detection method using plane normal vector in disparity space. We utilize two common factors for detecting vehicles: Hypothesis Generation (HG) and Hypothesis Verification (HV). At the stage of HG, we set the regions of interest (ROI) by estimating the lane, and track them to reduce computational cost of the overall processes. The image is then divided into compact superpixels, each of which is viewed as a plane composed of the normal vector in disparity space. After that, the representative normal vector is computed at a superpixel-level, which alleviates the well-known problems of conventional color-based and depth-based approaches. Based on the assumption that the central-bottom of the input image is always on the navigable region, the road and obstacle candidates are simultaneously extracted by the plane normal vectors obtained from K-means algorithm. At the stage of HV, the separated obstacle candidates are verified by employing HOG and SVM as for a feature and classifying function, respectively. To achieve this, we trained SVM classifier by HOG features of KITTI training dataset. The experimental results demonstrate that the proposed vehicle detection system outperforms the conventional HOG-based methods qualitatively and quantitatively.
Single Image Depth Estimation With Integration of Parametric Learning and Non-Parametric Sampling
Jung, Hyungjoo,Sohn, Kwanghoon Korea Multimedia Society 2016 멀티미디어학회논문지 Vol.19 No.9
Understanding 3D structure of scenes is of a great interest in various vision-related tasks. In this paper, we present a unified approach for estimating depth from a single monocular image. The key idea of our approach is to take advantages both of parametric learning and non-parametric sampling method. Using a parametric convolutional network, our approach learns the relation of various monocular cues, which make a coarse global prediction. We also leverage the local prediction to refine the global prediction. It is practically estimated in a non-parametric framework. The integration of local and global predictions is accomplished by concatenating the feature maps of the global prediction with those from local ones. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods both qualitatively and quantitatively.
Automatic illumination and color compensation using mean shift and sigma filter
Heechul Han,Kwanghoon Sohn IEEE 2009 IEEE transactions on consumer electronics Vol.55 No.3
<P>We present a novel framework for automatic illumination and color compensation algorithm using mean shift and the sigma filter (ICCMS) to restore distorted images taken under the arbitrary lighting conditions. The proposed method is effective for appropriate illumination compensation, vivid color restoration, artifacts suppression, automatic parameter estimation, and low computational cost for HW implementation. We show the efficiency of the mean shift filter and sigma filter for illumination compensation with small sized kernel while considering the processing time and removing the artifacts such as HALO and noise amplification. The proposed color restoration function can restore the natural color and correct color noise artifact more perceptually compared with conventional methods. For the automatic processing, the image statistics analysis estimates suitable parameter and all constants are pre-defined. We also introduce the ROI-based parameter estimation dealing with small shadow area against spacious well-exposed background in an image for the touch-screen camera. The object evaluation is performed by CMC, CIEde2000, PSNR, SSIM, and 3D CIELAB gamut with state-of-the-art research and existing commercial solutions.</P>