• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.6
• /
• pp.473-479
• /
• 2019

This study applied SGM (Semi Global Matching) to generate DSM (Digital Surface Model) using WorldView-1 high-resolution satellite stereo pair in Terrassa, Spain provided by ISPRS (International Society for Photogrammetry and Remote Sensing). The SGM is an image matching algorithm that performs the computation of the matching cost for the stereo pair in multi-paths and aggregates the computed costs sequentially. This method finally calculates the disparity corresponding to the minimum (or maximum) value of the aggregation cost. The cost was applied to MI (Mutual Information), NCC (Normalized Cross-Correlation), and CT (Census Transform) in order to the SGM. The accuracy and performance of the outline representation result in DSM by each cost are presented. Based on the images used and the subject area, the accuracy of the CT cost results was the highest, and the outline representation was also most clearly depicted. In addition, while the SGM method represented more detailed outlines than the existing software, many errors occurred in the water area.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.5C
• /
• pp.716-725
• /
• 2004

In this paper, a new multiview stereoscopic 3D display system using a VHLS(volume holographic lenticular sheet) is suggested. The VHLS, which acts just like an optical direction modulator, can be implemented by recording the diffraction gratings corresponding each directional vector of the multiview stereoscopic images in the holographic recording material by using the angularly multiplexed recording property of the conventional volume hologram. Then, this fabricated VHLS is attached to the panel of a LCD spatial light modulator and used to diffract each of the multiview image loaded in a SLM to the corresponding spatial direction for making a 3D stereo view-zone. Accordingly, in this paper, the operational principle and characteristics of the VHLS are analyzed and an optimized 4-view VHLS is fabricated by using a commercial photopolymer. Then, a new VHLS-based 4-view stereoscopic 3D display system is implemented. Through some experimental results using a 4-view image synthesized with adaptive disparity estimation algorithm, it is suggested that implementation of a new VHLS-based multiview stereoscopic 3D display system can be possible.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.8
• /
• pp.2262-2270
• /
• 1999

In this paper, we describe gesture recognition algorithm using computer vision sensor and HMM. The automatic hand region extraction has been proposed for initializing the tracking of the tele-operation gestures. For this, distance informations(disparity map) as results of stereo matching of initial left and right images are employed to isolate the hand region from a scene. PDOE(positive difference of edges) feature images adapted here have been found to be robust against noise and background brightness. The KNU/KAERI(K/K) gesture instruction set is defined for tele-operation in atomic electric power stations. The composite recognition model constructed by concatenating three gesture instruction models including pre-orders, basic orders, and post-orders has been proposed and identified by discrete HMM. Our experimental results showed that consecutive orders composed of more than two ones are correctly recognized at the rate of above 97%.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.4
• /
• pp.15-20
• /
• 2010

The three dimensional information is extracted and visualized using by stereo images of the object and the method for a 3D stereoscopic image is presented by the vergence control algorithm. The matching, which is applied a undistortion of lens and the energy function, is executed for the efficient extraction three dimensional information. Especially, applying the optimized method of matched line to the multi direction of the disparity imges. The disadvantages of multi directional method and reliability expansion method is collected. The matched interesting range of the three dimensional information is visualized using by VRML and more 3D stereoscopic image is visualized through the vergence control according to distance of the object. more improved three dimensional information is provided to observer by visualizing both of them at the same time.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.7
• /
• pp.104-115
• /
• 1999

This paper proposes an efficient method for 3D modeling of a human face from trinocular images by reconstructing face surface using range data. By using a trinocular camera system, we mitigated the tradeoff between the occlusion problem and the range resolution limitation which is the critical limitation in binocular camera system. We also propose an MPC_MBS (Matching Pixel Count Multiple Baseline Stereo) area-based matching method to reduce boundary overreach phenomenon and to improve both of accuracy and precision in matching. In this method, the computing time can be reduced significantly by removing the redundancies. In the model generation sub-pixel accurate surface data are achieved by 2D interpolation of disparity values, and are sampled to make regular triangular meshes. The data size of the triangular mesh model can be controlled by merging the vertices that lie on the same plane within user defined error threshold.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.5
• /
• pp.61-66
• /
• 2010

A stereo vision, which is based on two or more images taken from different view points, is able to build three dimensional maps of its environment having various applications including robots and home networks. SAD algorithm, which is based on area-based correlation, is widely used since its regular structure provide abundant parallelism. In this paper, we present heuristic designs of SAD algorithm to meet the demands on accuracy and resource usages in various applications. The disparity abridgement and the window abridgement algorithms can be used for vision systems in low cost and small size. The window shape algorithm can be applicable when object are in specific shapes. The adaptive window algorithm work well when accuracy is the primary concern.

• Korean Journal of Agricultural Science
• /
• v.47 no.2
• /
• pp.315-326
• /
• 2020

In this study, a real-time crop recognition system was developed for an unmanned farm machine for upland farming. The crop recognition system was developed based on a stereo camera, and an image processing framework was proposed that consists of disparity matching, localization of crop area, and estimation of crop height with coordinate transformations. The performance was evaluated by attaching the crop recognition system to a tractor for five representative crops (cabbage, potato, sesame, radish, and soybean). The test condition was set at 3 levels of distances to the crop (100, 150, and 200 cm) and 5 levels of camera height (42, 44, 46, 48, and 50 cm). The mean relative error (MRE) was used to compare the height between the measured and estimated results. As a result, the MRE of Chinese cabbage was the lowest at 1.70%, and the MRE of soybean was the highest at 4.97%. It is considered that the MRE of the crop which has more similar distribution lower. the results showed that all crop height was estimated with less than 5% MRE. The developed crop recognition system can be applied to various agricultural machinery which enhances the accuracy of crop detection and its performance in various illumination conditions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.256-257
• /
• 2022

In this paper, we introduce a method of extracting three-dimensional feature points through the movement of a single mobile device. Using a monocular camera, a 2D image is acquired according to the camera movement and a baseline is estimated. Perform stereo matching based on feature points. A feature point and a descriptor are acquired, and the feature point is matched. Using the matched feature points, the disparity is calculated and a depth value is generated. The 3D feature point is updated according to the camera movement. Finally, the feature point is reset at the time of scene change by using scene change detection. Through the above process, an average of 73.5% of additional storage space can be secured in the key point database. By applying the algorithm proposed to the depth ground truth value of the TUM Dataset and the RGB image, it was confirmed that the\re was an average distance difference of 26.88mm compared with the 3D feature point result.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1C
• /
• pp.83-91
• /
• 2004

An epipolar rectification is the process of transforming the epipolar geometry of a pair of images into a canonical form. This is accomplished by applying a homography to each image that maps the epipole to a predetermined point. In this process, rectified images transformed by homographies must be satisfied with the epipolar constraint. These homographies are not unique, however, we find out homographies that are suited to system's purpose by means of an additive constraint. Since the rectified image pair be a stereo image pair, we are able to find the disparity efficiently. Therefore, we are able to estimate the three-dimensional information of objects within an image and apply this information to object segmentation. This paper proposes a rectification method for object segmentation and applies the rectification result to the object segmentation. Using color and relative continuity of disparity for the object segmentation, the drawbacks of previous segmentation method, which are that the object is segmented to several region because of having different color information or another object is merged into one because of having similar color information, are complemented. Experimental result shows that the disparity of result image of proposed rectification method have continuity about unique object. Therefore we have confirmed that our rectification method is suitable to the object segmentation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2008.11a
• /
• pp.215-218
• /
• 2008

본 논문에서는 스테레오 카메라로부터 획득된 좌, 우 영상의 변이를 추정하여 3차원 공간 좌표(x, y, z)를 얻어내고, 거리측정과 가상공간 제어를 통해 사용자에게 현실감을 제공하는 실시간 3차원 공간 인식 시스템을 제안한다. 스테레오 카메라로 부터 획득된 좌, 우 영상은 시점의 차이 때문에 동일 물체에 대한 좌, 우 영상의 좌표 값의 차이를 발생시키는 데 이를 변이(disparity)라 정의한다. 관심 영역의 변이를 추정할 때 일반적으로 관심 영역의 모든 화소(pixel)의 변이를 추정하지만, 제안한 알고리즘에서는 관심 영역의 2차원 중심 좌표(x, y)의 변이만을 추정하여 계산량을 줄이고 실시간 처리가 가능하도록 하였다. 카메라 파라미터를 이용하여 획득된 변이로부터 깊이 정보(depth)를 얻어내고 3차원 공간 좌표를 획득한다. 손을 관심 영역으로 설정한 시스템에서 3차원 공간 좌표는 실시간으로 사용자의 손의 움직임에 의해 획득되고, 가상공간(virtual space)에 적용되어 사용자가 가상공간을 조작할 수 있는 듯한 느낌을 준다. 실험을 통해 제안한 알고리즘이 1.5m 거리 내에서의 깊이 측정시 평균 0.68cm의 오차를 가짐을 확인 할 수 있었다.