• The Journal of the Korea institute of electronic communication sciences
• /
• v.6 no.3
• /
• pp.349-354
• /
• 2011

In this paper we propose a simple efficient stereo matching algorithm to recover sharp object boundaries and to obtain dense disparity map using new multiple line shape windows. To this end, we consider left-right consistency and unique constraint. From the experimental results it is found that the proposed algorithm is very good for obtaining sharp and dense disparity maps for stereo image pairs.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1281-1287
• /
• 2016

This paper presents a method of single image dehazing and feature matching for aerial remote sensing images. In the case of a aerial image, transferring the information of the original image is difficult as the contrast leans by the haze. This also causes that the image contrast decreases. Therefore, a refined transmission map based on a hidden Markov random field. Moreover, the proposed algorithm enhances the accuracy of image matching surface-based features in an aerial remote sensing image. The performance of the proposed algorithm is confirmed using a variety of aerial images captured by a Worldview-2 satellite.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.3
• /
• pp.407-415
• /
• 2012

In this paper, we propose a new stereo matching algorithm by using color information especially for stereo images containing human beings in the applications such as tele-presence system. In the proposed algorithm, we first remove the background regions by using a threshold value for stereo images obtained by stereo camera and then find an initial disparity map and segment a given image into R, G, B and white color components. We also obtain edges in the segmented image and estimate the disparity from the extract boundary regions. Finally, we generate the final disparity map by properly combining the disparity map of each color component. Experiment results show better performance compared with the window based method and the dynamic programing method especially for stereo images with human being.

• 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%.

• Journal of the Semiconductor & Display Technology
• /
• v.10 no.3
• /
• pp.99-103
• /
• 2011

The stereoscopic vision system is the algorithm to obtain the depth of target object of stereo vision image. This paper presents an efficient disparity matching method using blue edge filter and graph cut algorithm. We do recommend the use of the simple sobel edge operator. The application of B band sobel edge operator over image demonstrates result with somewhat noisy (distinct border). The basic technique is to construct a specialized graph for the energy function to be minimized such that the minimum cut on the graph also minimizes the energy (either globally or locally). This method has the advantage of saving a lot of data. We propose a preprocessing effective stereo matching method based on sobel algorithm which uses blue edge information and the graph cut, we could obtain effective depth map.

• Journal of the Semiconductor & Display Technology
• /
• v.9 no.3
• /
• pp.65-69
• /
• 2010

The stereoscopic vision system is the algorithm to obtain the depth of target object of stereo vision image. This paper presents an efficient disparity matching method using nagao filter, octree color quantization and dynamic programming algorithm. we describe methods for performing color quantization on full color RGB images, using an octree data structure. This method has the advantage of saving a lot of data. We propose a preprocessing stereo matching method based on Nagao-filter algorithm using color information. using the nagao filter, we could obtain effective depth map and using the octree color quantization, we could reduce the time of computation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.1
• /
• pp.107-115
• /
• 2014

The reduced-bit transform based bit-plane matching algorithm (BPM) can obtain the block matching result through its simple calculation and hardware design compared to the conventional block matching algorithms (BMAs), but the block matching accuracy of BPMs is somewhat low. In this paper, reduced-bit transform based sum of the absolute difference (R-SAD) is proposed to improve the block matching accuracy in comparison with the conventional BPMs and it is shown that the matching process can be obtained using the logical operations. Firstly, this method transforms the current and the reference images into their respective 2-bit images and then a truth table is obtained from the relation between input and output 2-bit images. Next, a truth table is simplified by Karnaugh map and the absolute difference is calculated by using simple logical operations. Finally, the simulation results show that the proposed R-SAD can obtain higher accuracy in block matching results compared to the conventional BPMs through the PSNR analysis in the motion compensation experiments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.3C
• /
• pp.279-287
• /
• 2009

In this paper, a hierarchical stereo matching with color information is proposed. To generate an initial disparity map, feature based stereo matching is carried out and to generate a final disparity map, hierarchical stereo matching is carried out. The boundary (edge) region is obtained by segmenting a given image into R, G, B and White components. From the obtained boundary, disparity is extracted. The initial disparity map is generated when the extracted disparity is spread to the surrounding regions by evaluating autocorrelation from each color region. The initial disparity map is used as an initial value for generating the final disparity map. The final disparity map is generated from each color region by changing the size of a block and the search range. 4 test images that are provided by Middlebury stereo vision are used to evaluate the performance of the proposed algorithm objectively. The experiment results show better performance compared to the Graph-cuts and Dynamic Programming methods. In the final disparity map, about 11% of the disparities for the entire image were inaccurate. It was verified that the boundary for the non-contiguous point was clear in the disparity map.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.5
• /
• pp.468-472
• /
• 2013

This paper deals with the indoor localization problem for a SSMR (Skid Steering Mobile Robot) subjected to wheel-ground friction and with one LRF (Laser Range Finder). In order to compensate for some friction effect, a friction related coefficient is estimated by the recursive least square algorithm and appended to the maneuvering command. Also to reduce odometric information based localization errors, the lines are extracted with scan points of LRF and matched with the ones of the corresponding map built in advance. The present friction compensation and scan map matching schemes have been applied to a laboratory SSMR, and experimental results are given to validate the localization performance along an indoor corridor.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.5
• /
• pp.451-459
• /
• 2011

Fundamentally, there are 5 systems are needed for autonomous navigation of unmanned ground vehicle: Localization, environment perception, path planning, motion planning and vehicle control. Path planning and motion planning are accomplished based on result of the environment perception process. Thus, high reliability of localization and the environment perception will be a criterion that makes a judgment overall autonomous navigation. In this paper, via map matching using vehicle dynamic model and LIDAR sensors, replace high price localization system to new one, and have researched an algorithm that lead to robust autonomous navigation. Finally, all results are verified via actual unmanned ground vehicle tests.