• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.4
• /
• pp.16-25
• /
• 2000

In this paper, a new disparity detection algorithm which is robust to noise is presented. It detects the disparity of an arbitrary pixel through the iterative competition with neighbor pixels in the range of disparity. A diffusion process to improve stereo matching confidence is used prior to detecting disparity of an arbitrary pixel. It is used for aggregating initial matching measure of the difference map. If the image region for matching is too small, a wrong match might be found due to noise. On the contrary, the region is too big, it results in blurring of object boundaries. Therefore, we decide the image region for matching by using the diffusion process for aggregating matching measure, then detect the true disparity with proposed competition method to the distribution of matching measure. Through the proposed method we get the result of improving matching rate of 6.96% with real stereo imge. From the simulation with the stereo imge, the proposed disparity detection method significantly outperforms the conventional method to matching rate.

• Journal of KIISE:Software and Applications
• /
• v.28 no.7
• /
• pp.501-510
• /
• 2001

Generally, it is essential to estimate exact disparity for the 3D modeling from stereo images. Because existing methods calculate disparities from a whole image, they require too much cimputational time and bring about the mismatching problem. In this article, using the characteristic that the disparity vectors in stereo images are distributed not equally in a whole image but only exist about the background and obhect, we do a wavelet transformation on stereo images and estimate coarse disparity fields from the reduced lowpass field using area-based method at first-step. From these coarse disparity vectors, we generate disparity histogram and then separate object from background area using it. Afterwards, we restore only object area to the original image and estimate dense and accurate disparity by our two-step pixel-based method which does not use pixel brightness but use second gradient. We also extract feature points from the separated object area and estimate depth information by applying disparity vectors and camera parameters. Finally, we generate 3D model using both feature points and their z coordinates. By using our proposed, we can considerably reduce the computation time and estimate the precise disparity through the additional pixel-based method using LOG filter. Furthermore, our proposed foreground/background method can solve the mismatching problem of existing Delaunay triangulation and generate accurate 3D model.

• ETRI Journal
• /
• v.37 no.4
• /
• pp.752-765
• /
• 2015

We propose a novel post-processing algorithm and its very-large-scale integration architecture that simultaneously uses the passive and active stereo vision information to improve the reliability of the three-dimensional disparity in a hybrid stereo vision system. The proposed architecture consists of four steps - left-right consistency checking, semi-2D hole filling, a tiny adaptive variance checking, and a 2D weighted median filter. The experimental results show that the error rate of the proposed algorithm (5.77%) is less than that of a raw disparity (10.12%) for a real-world camera image having a $1,280{\times}720$ resolution and maximum disparity of 256. Moreover, for the famous Middlebury stereo image sets, the proposed algorithm's error rate (8.30%) is also less than that of the raw disparity (13.7%). The proposed architecture is implemented on a single commercial field-programmable gate array using only 13.01% of slice resources, which achieves a rate of 60 fps for $1,280{\times}720$ stereo images with a disparity range of 256.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.3044-3046
• /
• 2000

A Stereo matching has been an important tool for reconstructing three dimensional terrain. In this stereo matching process, DEM(Digitai Elevation Map) can be generated by the disparity from reference image to target image. Generally disparity map in matching process can be implemented by wraping from reference image to target image and if the role of reference and target is interchanged, the different DEM can be obtained. To evaluate the generated DEM from matching process, We adapted the Photorealistic synthetic image generator using ray tracing technique. The generator produce two simulated image from previous DEM and Ortho-image which is regard as Ground-truth. In this paper, we are concern about estimating more accurate DEM from these two DEMs. The several fusion methods of two DEMs are proposed to generate accurate DEM and compared with previous method. one of fusion methods is by using Cross-Correlation match score and the true DEM should have a high matching score.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.10
• /
• pp.465-472
• /
• 2015

We propose a novel plane detection in disparity space and evaluate its performance. Our method simplifies and makes scenes in disparity space easily dealt with by approximating various surfaces as planes. Moreover, the approximated planes can be represented in the same size as in the real world, and can be employed for obstacle detection and camera pose estimation. Using a stereo matching technique, our method first creates a disparity image which consists of binocular disparity values at xy-coordinates in the image. Slants of disparity values are estimated by exploiting a line simplification algorithm which allows our method to reflect global changes against x or y axis. According to pairs of x and y slants, we label the disparity image. 4-connected disparities with the same label are grouped, on which least squared model estimates plane parameters. N plane models with the largest group of disparity values which satisfy their plane parameters are chosen. We quantitatively and qualitatively evaluate our plane detection. The result shows 97.9%와 86.6% of quality in our experiment respectively on cones and cylinders. Proposed method excellently extracts planes from Middlebury and KITTI dataset which are typically used for evaluation of stereo matching algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.7
• /
• pp.1667-1679
• /
• 2010

This thesis proposes an adaptive variable-sized matching window method using the characteristic points of the image and a method to increase the reliability of the cross-consistency check to raise the correctness of the final disparity image. The proposed adaptive variable-sized window method segments the image with the color information, finds the characteristic points in each segmented image, and varies the size of the matching window according to the existence of the characteristic points inside the window. Also the proposed cross-consistency check method processes the two cases with the cost values corresponding to the best disparity and the second-best disparity: when the cost values themselves are too large and when the difference between the two cost values are too small. The two proposed methods were experimented with the four test images provided by the Middleburry site. As the results from the experiments, the proposed adaptive variable-sized matching window method decreased up to 18.2% of error ratio and the proposed cross-consistency check method increased up to 7.4% of reliability.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1911-1914
• /
• 2003

This paper proposes efficient system for multiview images using backward quadtree disparity estimation. Previous quadtree method usually divides current image. In this work, backward quadtree divides reference image. So, it does not need to code quadtree data. For backward quadtree, quadtree information map is generated. By using this map, adaptive dividing is possible. And, conventional bi-directional matching method is used with backward quadtree. These methods increase subject and object quality of decoded test images. For multiview images, panorama synthesizing method was used. Panorama image and right-most image are used for reference image for intermediate view images coding.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.403-406
• /
• 1996

In this paper, the geometry between horizontal and vertical movement of lens is studied for automatic vergence control of horizontal moving axis stereo camera. When the disparity of stereo remains contant, the horizontal movement of camera lens for image disparity and the vertical movement for image focus have linear geometry. Using this linearity, we can control the vergence of stereo camera only by focusing of stereo camera lens.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.209-210
• /
• 2007

Obtained disparity map from the stereo camera by using the several stereo matching algorithms carries lots of noise because of various causes. In our approach, mode filtering and noise elimination technique using the histogram and projection-based region merging methods are adopted for improving the quality of disparity map and image segmentation. The proposed algorithms are implemented in VHDL and the real-time experimentation shows the accurately divided objects.

• Journal of Broadcast Engineering
• /
• v.17 no.5
• /
• pp.838-850
• /
• 2012

In this paper, we propose a novel algorithm that generates multi-view images by using various image features obtained from the given stereoscopic images. In the proposed algorithm, we first create an intensity gradient saliency map from the given stereo images. And then we calculate a block-based optical flow that represents the relative movement(disparity) of each block with certain size between left and right images. And we also obtain the disparities of feature points that are extracted by SIFT(scale-invariant We then create a disparity saliency map by combining these extracted disparity features. Disparity saliency map is refined through the occlusion detection and removal of false disparities. Thirdly, we extract straight line segments in order to minimize the distortion of straight lines during the image warping. Finally, we generate multi-view images by grid mesh-based image warping algorithm. Extracted image features are used as constraints during grid mesh-based image warping. The experimental results show that the proposed algorithm performs better than the conventional DIBR algorithm in terms of visual quality.