• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.62-63
• /
• 2019

본 논문에서 개발하고자하는 다시점 스테레오 영상 기반의 3차원 깊이 정보 획득 기술은 스테레오 비전, light field, 가상시점, 방송 콘텐츠, 등 다양한 분야의 기술이 융합된 기술로 연구의 중요성이 매우 높다. 본 논문에서는 SGM 기반의 멀티베이스 라인 스테레오 정합 기술을 개발하고 다시점 스테레오 영상에 적용하여 깊이 정보를 획득하였다. 두 시점 간의 스테레오 정합에 있어서 다방향의 에너지 최소화 기술을 적용하고 시점 간의 정합비용함수를 누적하여 마지막으로 S공간 누적방법으로 최적의 깊이영상을 획득하였다. 기존의 스테레오 정합에 비하여 멀티베이스라인 스테레오 정합의 성능 향상을 확인하고 Middlebury 스테레오 영상을 이용하여 성능을 분석하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.70-75
• /
• 1993

We represent a method of 3-D object recognition using multi images in this paper. The recognition process is executed as follows. Object models as prior knowledgement are generated and stored on a computer. To extract features of a recognized object, three CCD cameras are set at vertices of a regular triangle and take images of an object to be recognized. By comparing extracted features with generated models, the object is recognized. In general, it is difficult to recognize 3-D objects because there are the following problems such as how to make the correspondence to both stereo images, generate and store an object model according to a recognition process, and effectively collate information gotten from input images. We resolve these problems using the method that the collation on the basis of features independent on the viewpoint, the generation of object models as enumerating some candidate models in an early recognition level, the execution a tight cooperative process among results gained by analyzing each image. We have made experiments based on real images in which polyhedral objects are used as objects to be recognized. Some of results reveal the usefulness of the proposed method.

• The Journal of the Korea Contents Association
• /
• v.9 no.5
• /
• pp.13-23
• /
• 2009

One of the main purpose of multiple-view image processing technology is support realistic 3D image to device user by using multiple viewpoint display devices and compressed data restoration devices. This paper proposes a multiple view image synthesis scheme based on RAM disk which makes possible to browse 3D images generated by applying effective composing method to real time input stereo images. The proposed scheme first converts input images to binary image. We applies edge detection algorithm such as Sobel algorithm and Prewiit algorithm to find edges used to evaluate disparities from images of 4 multi-cameras. In addition, we make use of time interval between hardware trigger and software trigger to solve the synchronization problem which has stated ambiguously in related studies. We use a unique identifier on each snapshot of images for distributed environment. With respect of performance results, the proposed scheme takes 0.67 sec in each binary array. to transfer entire images which contains left and right side with disparity information for high quality 3D image browsing. We conclude that the proposed scheme is suitable for real time 3D applications.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.1-7
• /
• 2011

The depth camera measures range information of the scene in real time using Time-of-Flight (TOF) technology. Measured depth data is then regularized and provided as a depth image. This depth image is utilized with the stereo or multi-view image to generate high-resolution depth map of the scene. However, it is required to correct noise and distortion of TOF depth image due to the technical limitation of the TOF depth camera. The corrected depth image is combined with the color image in various methods, and then we obtain the high-resolution depth of the scene. In this paper, we introduce the principal and various techniques of sensor fusion for high-quality depth generation that uses multiple camera with depth cameras.

• Journal of Korea Water Resources Association
• /
• v.56 no.spc1
• /
• pp.1027-1036
• /
• 2023

Coastal topographic information is crucial in coastal management, but point measurment based approeaches, which are labor intensive, are generally applied to land and underwater, separately. This study introduces an efficient method enabling land and undetwater surveys using an unmanned aerial vehicle (UAV). This method involves applying two different algorithms to measure the topography on land and water depth, respectively, using UAV imagery and merge them to reconstruct whole coastal digital elevation model. Acquisition of the landside terrain is achieved using the Structure-from-Motion Multi-View Stereo technique with spatial scan imagery. Independently, underwater bathymetry is retrieved by employing a depth inversion technique with a drone-acquired wave field video. After merging the two digital elevation models into a local coordinate, interpolation is performed for areas where terrain measurement is not feasible, ultimately obtaining a continuous nearshore terrain. We applied the proposed survey technique to Jangsa Beach, South Korea, and verified that detailed terrain characteristics, such as berm, can be measured. The proposed UAV-based survey method has significant efficiency in terms of time, cost, and safety compared to existing methods.

• The KIPS Transactions:PartB
• /
• v.14B no.7
• /
• pp.493-502
• /
• 2007

An on-line registration technique is presented to register multi-view range images for the 3D reconstruction of real objects. Using a range camera, we first acquire range images and photometric images continuously. In the range images, we divide object and background regions using a predefined threshold value. For the coarse registration of the range images, the centroid of the images are used. After refining the registration of range images using a projection-based technique, we use a modified KLT(Kanade-Lucas-Tomasi) tracker to match photometric features in the object images. Using the modified KLT tracker, we can track image features fast and accurately. If a range image fails to register, we acquire new range images and try to register them continuously until the registration process resumes. After enough range images are registered, they are integrated into a 3D model in offline step. Experimental results and error analysis show that the proposed method can be used to reconstruct 3D model very fast and accurately.

• The Bulletin of The Korean Astronomical Society
• /
• v.43 no.1
• /
• pp.72.4-73
• /
• 2018

북극 스발바르의 사면 지형에는 걸리가 발달되어 있다. 이러한 걸리는, 그 성인에는 여러 의견이 있으나, 화성에도 중고위도를 중심으로 다수 분포한다. 화성의 걸리는 2000년대에 들어 비로소 본격적으로 규명되고 있으나, 지형적 특성으로 인한 탐사의 한계로 지구에 분포하는 유사지형을 통한 비교 연구가 일반적이다(Costard, et al. 2007 등). 이 연구에서는 스발바르의 주도 롱이어비엔에서 UAV을 이용하여 획득한 DEM으로 스발바르 걸리를 측량하고, 이를 화성 중위도의 테라 사이메리아, 테라 시레넘, 노아 키스 테라에 분포하는 걸리와 비교하였다. Longyearbreen 빙하 전방에 위치한 사면을 UAV로 촬영하고, 이를 SfM-MVS(Structure from Motion & MultiView Stereo) 기법으로 3차원 점군 모델과 고해상도 DEM을 제작하여 분석하였다. 화성의 경우 MRO궤도 탐사선이 촬영한 HiRise DTM을 이용하여 분석하였다. 두 걸리는 기후와 지질 조건에 차이가 있음에도 불구하고 유사한 패턴을 보였다. 특히 테라 사이메리아에 위치한 걸리와 롱이어비엔 북사면의 걸리는 기준거리, 단면적, 폭, 경사, 제방 두께 등에서 상당한 정량적 유사관계가 있었다. 이는 두 행성의 걸리가 유사한 성인 및 형성 프로세스를 거쳤을 가능성을 시사한다. 측량 기법과 UAV 의 안정성을 개선시키면 지형 모델의 품질 향상 및 극지에서의 UAV 운용이 용이해질 것으로 기대된다. 또한 스발바르의 기후 요소 및 물리량 적용은 향후 화성 지형연구에도 응용할 수 있을 것으로 사료된다.

• 전자공학회논문지 IE
• /
• v.43 no.4
• /
• pp.105-114
• /
• 2006

In this paper, 3D input and output systems for a web-based real-time 3D video communication system using IEEE 1394 digital cameras, Intel Xeon Server system and Microsoft Directshow library is proposed. And some conditions for optimizing the operations of the stereo camera, 3D display and signal processing system are analyzed. Input & output systems are carefully selected, which can satisfy the required optimization conditions and the final 3D video communication system is implemented by using three optimized devices. The overall control system is developed with Microsoft Visual C++.Net and Microsoft DirectX 9.1 SDK. Some experimental results show that the observer can feel the natural presence from multi-view(4-view) 3D video of server system in real-time and also can feel the natural presence from 3D video of client system and finally suggest an application possibility of the proposed web-based real-time 3D video communication in real fields.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.4A
• /
• pp.239-249
• /
• 2012

Recently, the virtual view generation method using depth data is employed to support the advanced stereoscopic and auto-stereoscopic displays. Although depth data is invisible to user at 3D video rendering, its accuracy is very important since it determines the quality of generated virtual view image. Many works are related to such depth enhancement exploiting a time-of-flight (TOF) camera. In this paper, we propose a fast 3D scene capturing system using one TOF camera at center and two high-resolution cameras at both sides. Since we need two depth data for both color cameras, we obtain two views' depth data from the center using the 3D warping technique. Holes in warped depth maps are filled by referring to the surrounded background depth values. In order to reduce mismatches of object boundaries between the depth and color images, we used the joint bilateral filter on the warped depth data. Finally, using two color images and depth maps, we generated 10 additional intermediate images. To realize fast capturing system, we implemented the proposed system using multi-threading technique. Experimental results show that the proposed capturing system captured two viewpoints' color and depth videos in real-time and generated 10 additional views at 7 fps.

• Journal of Broadcast Engineering
• /
• v.14 no.4
• /
• pp.450-462
• /
• 2009

So far, many methods for segmenting single images or video have been proposed, but few methods have dealt with multiple images with analogous content. These images, which we term consistent scene images, include concurrent images of a scene and gathered images of a similar foreground, and may be collectively utilized to describe a scene or as input images for multi-view stereo. In this paper, we present a method to segment these images with minimum user input, specifically, manual segmentation of one image, by iteratively propagating information via multi-level cues with adaptive confidence depending on the nature of the images. Propagated cues are used as the bases to compute multi-level potentials in an MRF framework, and segmentation is done by energy minimization. Both cues and potentials are classified as low-, mid-, and high- levels based on whether they pertain to pixels, patches, and shapes. A major aspect of our approach is utilizing mid-level cues to compute low- and mid- level potentials, and high-level cues to compute low-, mid-, and high- level potentials, thereby making use of inherent information. Through this process, the proposed method attempts to maximize the amount of both extracted and utilized information in order to maximize the consistency of the segmentation. We demonstrate the effectiveness of the proposed method on several sets of consistent scene images and provide a comparison with results based only on mid-level cues [1].