• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.20-30
• /
• 2022

Recently, as VR (Virtual Reality) technology has been in the spotlight, 360° panoramic images that can view lively VR contents are attracting a lot of attention. Image stitching technology is a major technology for producing 360° panorama images, and many studies are being actively conducted. Typical stitching algorithms are based on feature point-based image stitching. However, conventional feature point-based image stitching methods have a problem that stitching results are intensely affected by feature points. To solve this problem, deep learning-based image stitching technologies have recently been studied, but there are still many problems when there are few overlapping areas between images or large parallax. In addition, there is a limit to complete supervised learning because labeled ground-truth panorama images cannot be obtained in a real environment. Therefore, we produced three fisheye images with different camera centers and corresponding ground truth image through carla simulator that is widely used in the autonomous driving field. We propose image stitching model that creates a 360° panorama image with the produced fisheye image. The final experimental results are virtual datasets configured similar to the actual environment, verifying stitching results that are strong against various environments and large parallax.

• Journal of Korea Game Society
• /
• v.18 no.5
• /
• pp.5-14
• /
• 2018

A lot of research has been done on image recognition technique for planar images and the performance has also been improved. However, it is difficult to recognize objects in spherical panoramic images or images in special form which are given in various environments because of the spherical distortion given in different form from the planar case. In this paper, we show that the neural network recognition approach can be used for object recognition in spherical image and suggest a method of using cubemap transform in order to increase recognition accuracy in spherical image.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.144-159
• /
• 2014

Techniques for making a single panoramic image using multiple pictures are widely studied in many areas such as computer vision, computer graphics, etc. The panorama image can be applied to various fields like virtual reality, robot vision areas which require wide-angled shots as an useful way to overcome the limitations such as picture-angle, resolutions, and internal informations of an image taken from a single camera. It is so much meaningful in a point that a panoramic image usually provides better immersion feeling than a plain image. Although there are many ways to build a panoramic image, most of them are using the way of extracting feature points and matching points of each images for making a single panoramic image. In addition, those methods use the RANSAC(RANdom SAmple Consensus) algorithm with matching points and the Homography matrix to transform the image. The SURF(Speeded Up Robust Features) algorithm which is used in this paper to extract featuring points uses an image's black and white informations and local spatial informations. The SURF is widely being used since it is very much robust at detecting image's size, view-point changes, and additionally, faster than the SIFT(Scale Invariant Features Transform) algorithm. The SURF has a shortcoming of making an error which results in decreasing the RANSAC algorithm's performance speed when extracting image's feature points. As a result, this may increase the CPU usage occupation rate. The error of detecting matching points may role as a critical reason for disqualifying panoramic image's accuracy and lucidity. In this paper, in order to minimize errors of extracting matching points, we used $3{\times}3$ region's RGB pixel values around the matching points' coordinates to perform intermediate filtering process for removing wrong matching points. We have also presented analysis and evaluation results relating to enhanced working speed for producing a panorama image, CPU usage rate, extracted matching points' decreasing rate and accuracy.

• Proceedings of the Korea Contents Association Conference
• /
• 2018.05a
• /
• pp.39-40
• /
• 2018

현재의 게임 영상 작품 중에서 파괴 특수효과는 그 강렬한 충격과 놀라움으로 광범위하게 사용된다. 360도 파노라마 영상이 가져다 주는 몰입감과 공간 감각은 파괴 특수효과의 시각 충격력을 더 강화시킨다. 본 논문의 핵심은 Houdini의 RBDSolver를 통해서 연서 소재를 모의하여 사실적인 파괴 특수효과를 제작에 있으며 또한 실질적인 제작의 방식으로 작업 흐름을 표현하고 분석하는데 있다. 따라서 Houdini이 제작한 파괴 특수효과와 360도 파노라마 영상을 결합하고 거기에다 Youtube를 사용하여 표현하는 것이 이번 연구의 새로운 포인트가 된다.

• Journal of IKEEE
• /
• v.20 no.4
• /
• pp.420-423
• /
• 2016

In this paper, we proposed an implementation of panoramic image stitching that operates in real time at the embedded environment by applying ROI based PROSAC algorithm using the directionality of the image. The conventional panoramic image stitching applies SURF or SIFT algorithm which contains unnecessary computation and a lots of data to detect feature points. In this paper, we use the direction of the input image and we proposed the method of reducing the unnecessary computation by using ROI. We use a gyro sensor and an acceleration sensor. Output data from gyro and acceleration sensors can be calibrated by complementary filter. The calibration does not affect the operating time of the proposed image stitching algorithm in embedded environment. Therefore, it is possible to operate in real-time.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.4
• /
• pp.13-18
• /
• 2013

Panorama picturing is an elongated photographing technique that connects images with rotating and moving multiple images horizontally that are partly overlapped. However, for hand-operated photographs, it is difficult to adjust overlapped parts because of tilted angles. There has been a study comparing adjacent pictures using labeling technique but it was time-consuming and had angle dissonant cases in nature. In this paper, we propose a less time-consuming paranoiac scene reconstruction method. Our method is also based on labeling-and-comparing technique but uses only 1/3 of it. Then, if there exists angle dissonance, it tries to find characteristic points by SURF algorithm and adjusts them with homography. The efficacy of this method is experimentally verified by experiments using various images

• Electronics and Telecommunications Trends
• /
• v.29 no.3
• /
• pp.37-46
• /
• 2014

3D와 UHD(Ultra High Definition) 기술의 발전과 함께 실감미디어의 응용분야가 점차 증대되면서 넓은 시야각의 고품질 파노라마 영상기술도 활발히 연구되고 있다. 실사 기반의 파노라마 영상은 현실감과 몰입감을 증대시킴으로써 시청자에게 새로운 실감미디어를 경험할 수 있는 계기가 마련되고 있다. 특히, 그 응용분야가 기존의 전시관과 스트리트 뷰 등에서 영화, 뉴스룸 등으로 점차 확산되고 있는 추세이다. 본고에서는 고품질 파노라마 기술의 현시점을 짚어보고, 요소기술과 활용분야에 대하여 소개한다. 고품질 파노라마 AV 기반의 실감미디어서비스를 위해 기술적으로 극복해야 할 사항들이 존재하지만, 다양한 분야에서의 수요가 증가함에 따른 많은 연구개발이 이루어질 것으로 예상되며, 이에 대한 추가 연구개발을 통해 지적재산권 확보와 해외기술의 국내시장 잠식에 대처할 필요가 있다.

• Journal of Broadcast Engineering
• /
• v.22 no.6
• /
• pp.785-799
• /
• 2017

One of the most widely used image media in recent years, omni-directional panorama images are attracting much attention. Since this image is ultra-high value-added, the intellectual property of this image must be protected. In this paper, we propose a blind digital watermarking method for this image. In this paper, we assume that the owner of each original image may be different, insert different watermark data into each original image, and extract the watermark from the projected image, which is a form of service of omni- directional panorama image. Therefore, the main target attack in this paper is the image distortion which occurs in the process of the omni- directional panorama image. In this method, SIFT feature points of non-stitched areas are used, and watermark data is inserted into data around each feature point. We propose two methods of using two-dimensional DWT coefficients and spatial domain data as data for inserting watermark. Both methods insert watermark data by QIM method. Through experiments, these two methods show robustness against the distortion generated in the panorama image generation process, and additionally show sufficient robustness against JPEG compression attack.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.737-739
• /
• 2016

파노라마 이미지 생성 기법의 중요한 부분은 입력 영상들로부터 특징을 추출하고, 영상간의 대응점을 찾는 작업이다. 특징 추출할 때 영상의 회전, 스케일, 밝기 변화에 강건하고 수행속도가 비교적 빠른 검출 알고리즘을 사용한다. 파노라마 이미지 생성 과정에 있어서 실제 대응하는 점들을 크게 다루기 때문에 불필요한 영역의 특징들은 오히려 연산속도의 방해 요소가 된다. 본 논문에서는 특징 추출 영역을 제한함으로써 특징 매칭 횟수 감소 및 속도 향상 방법을 제안한다. 특징의 개수가 감소되면 매칭 횟수 감소되고, 이후 이루어질 여러 계산량도 줄어 속도가 향상된다. 본 연구에 SURF(Speeded-Up Robust Feature) 알고리즘을 사용하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.169-175
• /
• 2006

In this paper we propose a method of reconstruction of cylindrical panorama using simplified projective transform from the panning image on the fixed camera. For the practical construction of cylindrical panorama we consider the rotation of the camera on the Y-axis only, even though considering the rotation components on all of the X,Y,Z axis on three-dimensional space for projective transform between general panoramas. The restriction mentioned above simplifies projective transform with existing 8 degrees of freedom into the one with 4 degrees of freedom. In the results, overall computation for projective transform can be decreased to the great extents in quantify, because the number of corresponding points required for inducing the transforming formula is gone down by half. Proposed algorithm from the simulation carried out in this paper shows similar performance and decreased computational quantity compared with existing algorithm. Also, it shows the construction of cylindrical panorama using simplified projective transform.