• Journal of Electrical Engineering and information Science
• /
• v.2 no.5
• /
• pp.79-88
• /
• 1997

This paper introduces a new energy function, as maximum a posteriori(MAP) estimate of binocular disparity, that can deal with both random dot stereo-gram(RDS) and natural scenes. The energy function uses phase-magnitude as features to detect only the shift for a pair of corrupted conjugate images. Also we adopted Fleet singularity that effectively detects unstable areas of image plant and thus eliminates in advance error-prone stereo mathcing. The multi-scale concept is applied to the multi laser architecture that can search the solutions systematically from coarse to fine details and thereby avoids drastically the local minima. Using mean field approximation, we obtained a compact representation that is suitable for fast computation. In this manner, the energy function satisfies major natural constraints and requirements for implementing parallel relaxation. As an experiment, the proposed algorithm is applied to RDS and natural stereo images. As a result we will see that it reveals good performance in terms of recognition errors, parallel implementation, and noise characteristics.

• Journal of the Semiconductor & Display Technology
• /
• v.16 no.2
• /
• pp.70-74
• /
• 2017

Given two stereo images of a scene, it is possible to recover a 3D understanding of the scene. This is the primary way that the human visual system estimates depth. This process is useful in applications like robotics, where depth sensors may be expensive but a pair of cameras is relatively cheap. In this work, we combined our interests to implement a graph cut algorithm for stereo correspondence, and performed evaluation against a baseline algorithm using normalized cross correlation across a variety of metrics. Experimental trials revealed that the proposed descriptor exhibited a significant improvement, compared to the other existing methods.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.4
• /
• pp.170-179
• /
• 1993

In this study, self-organized neural network is used to solve the vorrespondence problem of the axial stereo image. Edge points are extracted from a pair of stereo images and then the edge points of rear image are assined to the output nodes of neural network. In the matching process, the two input nodes of neural networks are supplied with the coordi- nates of the edge point selected randomly from the front image. This input data activate optimal output node and its neighbor nodes whose coordinates are thought to be correspondence point for the present input data, and then their weights are allowed to updated. After several iterations of updating, the weights whose coordinates represent rear edge point are converged to the coordinates of the correspondence points in the front image. Because of the feature map properties of self-organized neural network, noise-free and smoothed depth data can be achieved.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.182-182
• /
• 2003

Generally, DEM (Digital Elevation Model) is generated by stereo-images acquired same conditions, sensor type, viewing angle, capturing elevation and etc. It is difficult to generate DEM with stereo images acquired different satellite. This study intends that it is DEM generation using pair-images with other sensor systems.

• Korean Journal of Remote Sensing
• /
• v.24 no.5
• /
• pp.483-496
• /
• 2008

Qualified ground control points (GCPs) are required to construct a digital elevation model (DEM) from a pushbroom stereo pair. An inverse geolocation algorithm for extracting GCPs from ERS SAR data and the SRTM DEM was recently developed. However, not all GCPs established by this method are accurate enough for direct application to the geometric correction of pushbroom images such as SPOT, IRS, etc, and thus a method for selecting and removing inaccurate points from the sets of GCPs is needed. In this study, we propose a method for evaluating GCP accuracy and winnowing sets of GCPs through orientation modeling of pushbroom image and validate performance of this method using SPOT stereo pair of Daejon City. It has been found that the statistical distribution of GCP positional errors is approximately Gaussian without bias, and that the residual errors estimated by orientation modeling have a linear relationship with the positional errors. Inaccurate GCPs have large positional errors and can be iteratively eliminated by thresholding the residual errors. Forty-one GCPs were initially extracted for the test, with mean the positional error values of 25.6m, 2.5m and -6.1m in the X-, Y- and Z-directions, respectively, and standard deviations of 62.4m, 37.6m and 15.0m. Twenty-one GCPs were eliminated by the proposed method, resulting in the standard deviations of the positional errors of the 20 final GCPs being reduced to 13.9m, 8.5m and 7.5m in the X-, Y- and Z-directions, respectively. Orientation modeling of the SPOT stereo pair was performed using the 20 GCPs, and the model was checked against 15 map-based points. The root mean square errors (RMSEs) of the model were 10.4m, 7.1m and 12.1m in X-, Y- and Z-directions, respectively. A SPOT DEM with a 20m ground resolution was successfully constructed using a automatic matching procedure.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.161-170
• /
• 2012

This paper presents an efficient and robust approach for determining the correspondence between unbalanced stereo images. The disparity vectors were used instead of feature points, such as corners, to calculate a correspondence relationship. For a faster and optimal estimation, the vectors were classified into several regions, and the homography of each region was calculated using the RANSAC algorithm. The correspondence image was calculated from the images transformed by each homography. Although it provided good results under normal conditions, it was difficult to obtain reliable results in an unbalanced stereo pair. Therefore, a balancing method is also proposed to minimize the unbalance effects using the histogram specification and structural similarity index. The experimental results showed that the proposed approach outperformed the baseline algorithms with respect to the speed and peak-signal-to-noise ratio. This work can be applied to practical fields including 3D depth map acquisition, fast stereo coding, 2D-to-3D conversion, etc.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.63-68
• /
• 2010

In this paper, we propose a multiresolution stereo matching method based on genetic algorithm using edge information. The proposed approach considers the matching environment as an optimization problem and finds the solution by using a genetic algorithm. A cost function composes of certain constraints which are commonly used in stereo matching. We defines the structure of chromosomes using edge pixel information of reference image of stereo pair. To increase the efficiency of process, we apply image pyramid method to stereo matching and calculate the initial disparity map at the coarsest resolution. Then initial disparity map is propagated to the next finer resolution, interpolated and performed disparity refinement. We valid our approach not only reduce the search time for correspondence but alse ensure the validity of matching.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.5
• /
• pp.1157-1163
• /
• 2000

In this paper, we present a novel and practical stereo vision system that uses only one camera and four mirrors placed in front of the camera. The equivalent of a stereo pair of images are formed as left and right halves of a single CCD image by using four mirrors placed in front of the ten of a CCD camera. An object arbitrary point in 3D space is transformed into two virtual points by the four mirrors. As in the conventional stereo system, the displacement between the two conjugate image points of the two virtual points is directly related to the depth of the object point. This system has the following advantages over traditional two camera stereo that identical system parameters, easy calibration and easy acquisition of stereo data.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.4A
• /
• pp.371-382
• /
• 2002

A camera model with optical axes parallel has been widely used for stereo vision applications. A pair of input ages are obtained from a convergent-looking stereo camera model based on the human visual system in this per, and each image is divided into quadrant regions with respect to the fixation point. The reasoning of quadrant partitions is based on the human visual system and is proven by a geometrical method. Image patches : constructed from the right and left stereo images. A modified cepstrum filter is applied to the patches and disparity vectors are determined by peak detection algorithm. The three-dimensional information for synthetic ages is obtained from the measured disparity and the convergent stereo camera model. It is shown that the experimental results of the proposed method for various stereo images are accurate around the fixation point like the human visual system.

• Korean Journal of Remote Sensing
• /
• v.28 no.2
• /
• pp.191-202
• /
• 2012

A high resolution satellite imagery such as KOMPSAT-2 includes a material containing rational polynomial coefficient (RPC) for three-dimensional geopositioning. However, image geometries which are calculated from the RPC must have inevitable systematic errors. Thus, it is necessary to correct systematic errors of the RPC using several ground control points (GCPs). In this paper, we propose an efficient method for automatic correction of image geometries using tie points of a stereo pair and the Shuttle Radar Topography Mission (SRTM) Digital Elevation Model (DEM) without GCPs. This method includes four steps: 1) tie points extraction, 2) determination of the ground coordinates of the tie points, 3) refinement of the ground coordinates using SRTM DEM, and 4) RPC adjustment model parameter estimation. We validates the performance of the proposed method using KOMPSAT-2 stereo pair. The root mean square errors (RMSE) achieved from check points (CPs) were about 3.55 m, 9.70 m and 3.58 m in X, Y;and Z directions. This means that we can automatically correct the systematic error of RPC using SRTM DEM.