• 한국인터넷방송통신학회논문지
• /
• 제15권6호
• /
• pp.201-208
• /
• 2015

3차원 입체 방송을 가능하게 하기 위해서는 실세계에 존재하는 한 사물에 대한 깊이 정보를 획득하여야 한다. 따라서 본 논문에서는 네트워크 알고리즘인 신뢰확산(belief propagation) 알고리즘을 다해상도 영역에서 적용하여 3차원 정보의 근간이 되는 변이(disparity) 영상이나 깊이(depth)영상을 정확하면서도 빠르게 생성하는 것을 목적으로 한다. 신뢰확산 알고리즘은 기본적으로 여러 번의 반복을 통하여 변이정보를 보다 정확하게 갱신하게 되어 많은 연산량과 넓은 탐색영역으로 인하여 성능의 수렴까지 오랜 시간이 걸린다. 다해상도 변환은 공간영역과 주파수영역 모두에서 우수한 해상도를 갖기 때문에 이를 이용하여 스테레오 정합의 연산 속도를 증가시키고 성능을 향상시키는 것을 보여주었다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.508-511
• /
• 2006

Generally, stereo pair images are necessary for 3D viewing. In the absence of quality stereo-pair images, it is possible to synthesize a stereo-mate suitable for 3D viewing with a single image and a depth-map. In remote sensing, DEM is usually used as a depth-map. In this paper, LiDAR data was used instead of DEM to make a stereo pair from a single aerial photo. Each LiDAR point was assigned a brightness value from the original single image by registration of the image and LiDAR data. And then, imaginary exposure station and image plane were assumed. Finally, LiDAR points with already-assigned brightness values were back-projected to the imaginary plane for synthesis of a stereo-mate. The imaginary exposure station and image plane were determined to have only a horizontal shift from the original image's exposure station and plane. As a result, the stereo-mate synthesized in this paper fulfilled epipolar geometry and yielded easily-perceivable 3D viewing effect together with the original image. The 3D viewing effect was tested with anaglyph at the end.

• 한국해양공학회지
• /
• 제35권3호
• /
• pp.183-190
• /
• 2021

Tomographic particle image velocimetry (PIV) is a widely used method that measures a three-dimensional (3D) flow field by reconstructing camera images into voxel images. In 3D measurements, the setting and calibration of the camera's mapping function significantly impact the obtained results. In this study, a camera self-calibration technique is applied to tomographic PIV to reduce the occurrence of errors arising from such functions. The measured 3D particles are superimposed on the image to create a disparity map. Camera self-calibration is performed by reflecting the error of the disparity map to the center value of the particles. Vortex ring synthetic images are generated and the developed algorithm is applied. The optimal result is obtained by applying self-calibration once when the center error is less than 1 pixel and by applying self-calibration 2-3 times when it was more than 1 pixel; the maximum recovery ratio is 96%. Further self-correlation did not improve the results. The algorithm is evaluated by performing an actual rotational flow experiment, and the optimal result was obtained when self-calibration was applied once, as shown in the virtual image result. Therefore, the developed algorithm is expected to be utilized for the performance improvement of 3D flow measurements.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권1호
• /
• pp.228-246
• /
• 2011

A 3D model based approach for a face representation and recognition algorithm has been investigated as a robust solution for pose and illumination variation. Since a generative 3D face model consists of a large number of vertices, a 3D model based face recognition system is generally inefficient in computation time and complexity. In this paper, we propose a novel 3D face representation algorithm based on a pixel to vertex map (PVM) to optimize the number of vertices. We explore shape and texture coefficient vectors of the 3D model by fitting it to an input face using inverse compositional image alignment (ICIA) to evaluate face recognition performance. Experimental results show that the proposed face representation and recognition algorithm is efficient in computation time while maintaining reasonable accuracy.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2010년도 추계학술대회
• /
• pp.147-148
• /
• 2010

Recently, advancement in the visual technology has lead to the further development of the three dimensional (3D) imaging systems. The visual perception to view a pair of images simultaneously, is a crucial factor to build a stereoscopic 3D image. In this paper, we present the depth cues between the intensities of the two images when viewing with both eyes. Due to this stereoscopic effect, objects at different distances from the eyes differ in their horizontal positions, giving the depth cue of horizontal disparity. By simple image processing technique, we also present the binocular disparity map between the two images. A median filter has been used to filter out all the noises occurring in the disparity map image.

• 한국측량학회지
• /
• 제24권3호
• /
• pp.289-297
• /
• 2006

토지피복지도는 토지의 피복특성과 토지활용특성을 나타내는 자료로서 토지피복분류체계에 따라 계층적인 구조로 1998년부터 제작되고 있다. 대분류는 Landsat 위성영상을 활용하여 남 북한에 대한 작업이 완료되었으며, 중분류는 IRS-1C, IRS-1D, KOMPSAT, SPOT-5 영상을 저해상 컬러 영상과 영상융합을 한 후, 그 결과자료를 전문가가 도화하여 제작하고 있다. 특히 도화에 의한 중분류 토지피복지도 제작은 위성영상의 구매 및 자료처리, 토지피복 지도제작 과정에서 막대한 비용이 필요하다. 본 논문에서는 최근 많은 연구가 수행되고 있는 초분광 위성영상인 EO-1 Hyperion을 이용한 중분류 토지피복지도 제작 가능성을 연구했다. 많은 분광정보를 제공하는 Hyperion 영상과 기존에 사용하던 Landsat-7 ETM+ 영상의 토지피복분류 비교 연구를 수행하여 Hyperion의 분류정확도를 평가했다. 또한, Hyperion에 적합한 최적밴드선택 방법을 통하여 초분광 위성영상 활용의 효율성을 증대시켰다.

• 한국기계가공학회지
• /
• 제21권4호
• /
• pp.114-130
• /
• 2022

The purpose of this study was to investigate the possibility of increasing the efficiency of disaster relief rescue operations through collaboration among multiple aerial and ground robots. The robots create 2.5D maps, which are merged into a 2.5D map. The 2.5D map can be handled by a low-specification controller of an aerial robot and is suitable for ground robot navigation. For localization of the aerial robot, a six-degree-of-freedom pose recognition method using VIO was applied. To build a 2.5D map, an image conversion technique was employed. In addition, to merge 2.5D maps, an image similarity calculation technique based on the features on a wall was used. Localization and navigation were performed using a ground robot to evaluate the reliability of the 2.5D map. As a result, it was possible to estimate the location with an average and standard error of less than 0.3 m for the place where the 2.5D map was normally built, and there were only four collisions for the obstacle with the smallest volume. Based on the 2.5D map building and map merging system for the aerial robot used in this study, it is expected that disaster response work efficiency can be improved by combining the advantages of heterogeneous robots.

• 한국산업융합학회 논문집
• /
• 제27권3호
• /
• pp.563-572
• /
• 2024

Image processing and computer vision technologies are becoming increasingly important in a variety of application fields that require techniques and tools for sophisticated image analysis. In particular, image segmentation is a technology that plays an important role in image analysis. In this study, in order to identify recent research trends on image segmentation techniques, we used the Web of Science(WoS) database to analyze the R&D topography based on the network structure of the author's keyword co-occurrence matrix. As a result, from 2015 to 2023, as a result of the analysis of the R&D map of research articles on image segmentation, R&D in this field is largely focused on four areas of research and development: (1) researches on collecting and preprocessing image data to build higher-performance image segmentation models, (2) the researches on image segmentation using statistics-based models or machine learning algorithms, (3) the researches on image segmentation for medical image analysis, and (4) deep learning-based image segmentation-related R&D. The scientometrics-based analysis performed in this study can not only map the trajectory of R&D related to image segmentation, but can also serve as a marker for future exploration in this dynamic field.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.695-697
• /
• 2006

Elshayal $Smart{\copyright}$ software is an almost First Arabian GIS $software{\copyright}$ which completely developed by Arabian developers team and independent of any commercial software package. The software current Features are View and Edit shape files, build new layers, add existing layers, remove layers, swap layers, save layers, set layer data sources, layer properties, zoom in & zoom out, pan, identify, selecting features, invert selection, show data table, data query builder, location query builder, build network, find shortest path, print map, save map image, copy map image to clipboard, save project map, edit move vertex, edit move features, snap vertexes, set vertex XY, move settings, converting coordinate system, applying VB script, copy selected features to another layer, move selected features to another layer, delete selected features, edit data table, modify table structure, edit map features, drawing new features, GPS tracking, 3D view, etc... The software expected Features are: Viewing raster image and image geo-referencing, read other map formats such as DXF Format and Tiger Line Format.

• 제어로봇시스템학회논문지
• /
• 제19권5호
• /
• pp.457-461
• /
• 2013

This paper proposes an image feature-based real-time RGB-D (Red-Green-Blue Depth) 3D SLAM (Simultaneous Localization and Mapping) system. RGB-D data from Kinect style sensors contain a 2D image and per-pixel depth information. 6-DOF (Degree-of-Freedom) visual odometry is obtained through the 3D-RANSAC (RANdom SAmple Consensus) algorithm with 2D image features and depth data. For speed up extraction of features, parallel computation is performed with GPU acceleration. After a feature manager detects a loop closure, a graph-based SLAM algorithm optimizes trajectory of the sensor and builds a 3D point cloud based map.