• Journal of Navigation and Port Research
• /
• v.32 no.5
• /
• pp.355-361
• /
• 2008

Stereo matching is one of the most active research areas in computer vision. In this paper, we propose a stereo matching scheme using genetic algorithm for object depth recognition. The proposed approach considers the matching environment as an optimization problem and finds the optimal solution by using an evolutionary strategy. Accordingly, genetic operators are adapted for the circumstances of stereo matching. An individual is a disparity set. Horizontal pixel line of image is considered as a chromosome. A cost function is composed of certain constraints which are commonly used in stereo matching. Since the cost function consists of intensity, similarity and disparity smoothness, the matching process is considered at the same time in each generation. The LoG(Laplacian of Gaussian) edge is extracted and used in the determination of the chromosome. We validate our approach with experimental results on stereo images.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.179-186
• /
• 2021

For stereo matching based on deep learning, the design of network structure is crucial to the calculation of matching cost, and the time-consuming problem of convolutional neural network in image processing also needs to be solved urgently. In this paper, a method of stereo matching using sparse loss volume in parallax dimension is proposed. A sparse 3D loss volume is constructed by using a wide step length translation of the right view feature map, which reduces the video memory and computing resources required by the 3D convolution module by several times. In order to improve the accuracy of the algorithm, the nonlinear up-sampling of the matching loss in the parallax dimension is carried out by using the method of multi-category output, and the training model is combined with two kinds of loss functions. Compared with the benchmark algorithm, the proposed algorithm not only improves the accuracy but also shortens the running time by about 30%.

• Korean Journal of Remote Sensing
• /
• v.13 no.2
• /
• pp.121-132
• /
• 1997

This paper describes the development of a stereo matching algorithm for extracting Digital Elevation Model(DEM) from satellite images. This matching algorithm is based on a non-linear least squares correlation estimation but has improved matching speed. The algorithm consists of three steps: matching execution, matching control and matching optimization. Each is described. The performance of the presented algorithm is quantitatively analyzed with experiments on matching probability, matching speed and matching convergence radius.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.5
• /
• pp.65-73
• /
• 2017

In this paper, we propose a stereo matching method to improve the image quality at the hole and the disparity discontinuity regions. The stereo matching method extracts disparity map finding corresponding points between stereo image pair. However conventional stereo matching methods have a problem about the tradeoff between accuracy and precision with respect to the length of the baseline of the stereo image pair. In addition, there are hole and disparity discontinuity regions which are caused by textureless regions and occlusion regions of the stereo image pair. The proposed method extracts initial disparity map improved at disparity discontinuity and miss-matched regions using modified AD-Census-Gradient method and adaptive weighted cost aggregation. And then we conduct the disparity map refinement to improve at miss-matched regions, while also improving the accuracy of the image. Experimental results demonstrate that the proposed method produces high-quality disparity maps by successfully improving miss-matching regions and accuracy while maintaining matching performance compared to existing methods which produce disparity maps with high matching performance. And the matching performance is increased about 3.22(%) compared to latest stereo matching methods in case of test images which have high error ratio.

• Journal of information and communication convergence engineering
• /
• v.12 no.2
• /
• pp.128-134
• /
• 2014

In this paper, we present a graphics processing unit (GPU)-based matching technique for the purpose of fast feature matching between different images. The scale invariant feature transform algorithm developed by Lowe for various feature matching applications, such as stereo vision and object recognition, is computationally intensive. To address this problem, we propose a matching technique optimized for GPUs to perform computations in less time. We optimize GPUs for fast computation of keypoints to make our system quick and efficient. The proposed method uses a self-organizing map feature matching technique to perform efficient matching between the different images. The experiments are performed on various image sets to examine the performance of the system under varying conditions, such as image rotation, scaling, and blurring. The experimental results show that the proposed algorithm outperforms the existing feature matching methods, resulting in fast feature matching due to the optimization of the GPU.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.119-122
• /
• 2011

The Stereo vision using belief propagation algorithm that has been studied recently yields good performance in disparity extraction. In this paper, BP algorithm is proved theoretically to high precision for a stereo matching algorithm. We derive disparity map from stereo image by using Belief Propagation (BP) algorithm and area-based matching algorithm. Two algorithms are compared using stereo images provided by Middlebury web site. Disparity map error rate decreased from 52.3% to 2.3%.

• Journal of IKEEE
• /
• v.17 no.4
• /
• pp.517-524
• /
• 2013

Stereo matching has been grabbing the attention of researchers because it plays an important role in computer vision, remote sensing and photogrammetry. Although most methods perform well with small size images, experiments applying them to large-scale data sets under uncontrolled conditions are still lacking. In this paper, we present an empirical study on stereo matching for large-scale high-resolution satellite images. A new method is studied to solve the problem of huge size and memory requirement when dealing with large-scale high resolution satellite images. Integrating the tiling technique with the well-known dynamic programming and coarse-to-fine pyramid scheme as well as using memory wisely, the suggested method can be utilized for huge stereo satellite images. Analyzing 350 points from an image of size of 8192 x 8192, disparity results attain an acceptable accuracy with RMS error of 0.5459. Taking the trade-off between computational aspect and accuracy, our method gives an efficient stereo matching for huge satellite image files.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.817-818
• /
• 2008

In the present paper we propose a new method of intermediate view reconstruction between stereo images using belief propagation_based stereo matching. Intermediate view reconstruction is an important step for multiview 3D display. Many previous paper about intermediate view reconstruction using depth information to synthesize interview though stereo matching were proposed. But depth information is different to estimated accurately. In the present paper, in order to obtain accurate depth information, belief propagation_based stereo matching was used.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.08a
• /
• pp.73-76
• /
• 2008

We present a area-based method for stereo matching using varying weights. A central problem in a area-based stereo matching is different result from selecting a window size. Most of the previous window-based methods iteratively update windows. However, the iterative methods very sensitive the initial disparity estimation and are computationally expensive. To resolve this problem, we proposed a new function to assign weights to pixels using features. To begin with, we extract features in a given stereo images based on edge. We adjust the weights of the pixels in a given window based on correlation of the stereo images. Then, we match pixels in a given window between the reference and target images of a stereo pair. The proposed method is compared to existing matching strategies using both synthetic and real images. The experimental results show the improved accuracy of the proposed method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.82-90
• /
• 2010

In this paper, A new stereo matching method based on reliability space is proposed to acquire 3D information from 2D image. In conventional stereo matching methods, speed is sacrificed to achieve high accuracy. To increase the matching speed while maintaining a high accuracy, this paper proposes this stereo matching method. It first makes the disparity space image for comparing all of the pixels on the stereo images. Then it produce reliability space through analyzing this value. and, By comparing the reliability space according to disparity, it makes disparity map. Moreover, the parts that make regional boundary errors are corrected by classifying the boundary of each region with the reference to color edge. The performance of the proposed stereo matching method is verified by various experiments. As a result, calculation cost is reduced by 30.6%, while the image quality of proposed method has similar performance with the existing method.