• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.289-299
• /
• 2018

The 360 degree panoramas are picture of a wide range of images on one screen, so we can see a fairly wide range at a time. In particular, cylinderical panoramas are the most widely used spherical image, and its left and right viewing angles reach 360 degree, so you can observe front, rear, left, and right at once. Using 360 degree panorama, all directions can be monitored at the same time, so all directions can be effectively monitored compared to other methods. In this paper, we develop a system to recognize and track the movement of moving objects on a 360 degree panorama, and then present and verify the experimental results. For this goals, first, we developed a system to recognize moving objects in 360 degree panorama using DoF(Difference of Frame) algorithm. Second, based on the TLD algorithm, we developed an application that can track a specific single moving object in a 360 degree panorama and presented the experimental results.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.3
• /
• pp.61-68
• /
• 2020

In this paper, we propose a deep learning framework for predicting a depth map of a 360° panorama image. Previous works use synthetic 360° panorama datasets to train networks due to the lack of realistic datasets. However, the synthetic nature of the datasets induces features extracted by the networks to differ from those of real 360° panorama images, which inevitably leads previous methods to fail in depth prediction of real 360° panorama images. To address this gap, we use domain adaptation to learn features shared by real and synthetic panorama images. Experimental results show that our approach can greatly improve the accuracy of depth estimation on real panorama images while achieving the state-of-the-art performance on synthetic images.

• The Journal of the Korea Contents Association
• /
• v.17 no.3
• /
• pp.42-52
• /
• 2017

Panorama image is a single image obtained by combining images taken at several viewpoints through matching of corresponding points. Existing panoramic image generation methods that find the corresponding points are extracting local invariant feature points in each image to create descriptors and using descriptor matching algorithm. In the case of video sequence, frames may be a lot, so therefore it may costs significant amount of time to generate a panoramic image by the existing method and it may has done unnecessary calculations. In this paper, we propose a method to quickly create a single panoramic image from a video sequence. By assuming that there is no significant changes between frames of the video such as in locally, we use the FAST algorithm that has good repeatability and high-speed calculation to extract feature points and the Lucas-Kanade algorithm as each feature point to track for find the corresponding points in surrounding neighborhood instead of existing descriptor matching algorithms. When homographies are calculated for all images, homography is changed around the center image of video sequence to warp images and obtain a planar panoramic image. Finally, the spherical panoramic image is obtained by performing inverse transformation of the spherical coordinate system. The proposed method was confirmed through the experiments generating panorama image efficiently and more faster than the existing methods.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.6
• /
• pp.63-68
• /
• 2018

Offloading is a method of communicating, processing, and receiving results from some of the applications performed on local computers to overcome the limitations of computing resources and computational speed.Recently, it has been applied in mobile games, multimedia data, 360-degree video processing, and image processing for Internet broadcasting to speed up processing and reduce battery consumption in the mobile computing sector. This paper implements a viewer that enables users to convert various flat-panel images and view contents in a wireless Internet environment and presents actual results of an experiment so that users can easily understand the images. The 360 degree spherical image is successfully converted to a plane image with Double Panorama, Quad, Single Rectangle, 360 Overview + 3 Rectangle depending on the image acquisition position of the 360 degree camera through the interface. During the experiment, more than 100 360 degree spherical images were successfully converted into plane images through the interface below.

• Journal of Korea Multimedia Society
• /
• v.15 no.12
• /
• pp.1430-1441
• /
• 2012

In this paper, we present an algorithm that quickly and effectively estimates orthogonal vanishing points in equirectangular images of urban environment. Our algorithm is based on the RANSAC (RANdom SAmple Consensus) algorithm and on the characteristics of the line segment in the spherical panorama image of the $360^{\circ}$ longitude and $180^{\circ}$ latitude field of view. These characteristics can be used to reduce the geometric ambiguity in the line segment classification as well as to improve the robustness of vanishing point estimation. The proposed algorithm is validated experimentally on a wide set of images. The results show that our algorithm provides excellent levels of accuracy for the vanishing point estimation as well as line segment classification.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.560-563
• /
• 2021

본 논문에서는 사각형 실내 공간에서 점군 데이터를 기반으로 빠르고 정확하게 바닥, 천장, 벽면에 대한 평면 정보를 획득할 수 있는 시스템을 제안한다. 기존의 방법은 관측되지 않은 공간에 대한 평면을 예측할 수 없으며, 노이즈에 취약하고, 모든 점에 대한 기저 정보를 알아야하기 때문에 많은 연산량을 요구한다. 제안 방법은 기존의 평면 검출 방식에서 벗어나 Bounding Box 형상을 예측하는 기술을 활용한다. 또한, 제안 시스템은 구면 파노라마 비디오를 기반으로 적은 수의 프레임으로도 빠르게 실시간 점군 데이터를 확장해나간다. 제안 방법은 실험을 통해 기존의 방법보다 월등히 빠르고, 노이즈 등 환경 제약 요소에 강건함을 보인다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.952-955
• /
• 2021

사람의 자세는 구면 파노라마에서 다양한 형태로 왜곡되어 나타날 수 있다. 따라서 구면 파노라마에서의 자세 추정은 평면 이미지에서의 경우보다 정확도가 떨어진다. 본 논문에서는 인식률이 높은 얼굴 인식 기법을 도입하여 구면 파노라마 영상에서 안정적으로 사람의 자세를 추정하는 방법을 제시한다. 먼저 구면 파노라마에서 얼굴을 인식한 후에 이에 기반하여 사람의 전신 영역을 추정하고 전신 영역을 포함하는 평면 영상을 획득한다. 획득된 평면 영상에서 자세를 추정하여 스켈레톤을 얻고 이를 캐릭터 모델에 적용한다. 제안 방법을 실영상에 적용하여 실험한 결과 평면 이미지에서와 동일한 수준의 정확도를 보임을 확인하였다.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.65-75
• /
• 2017

As a 360-degree image carries information of all directions, it often has too much information. Moreover, in order to investigate a 360-degree image on a 2D display, a user has to either click and drag the image with a mouse, or project it to a 2D panorama image, which inevitably introduces severe distortions. In consequence, investigating a 360-degree image and finding an object of interest in such a 360-degree image could be a tedious task. To resolve this issue, this paper proposes a method to find a region of interest and produces a 2D naturally looking image from a given 360-degree image that best matches a description given by a user in a natural language sentence. Our method also considers photo composition so that the resulting image is aesthetically pleasing. Our method first converts a 360-degree image to a 2D cubemap. As objects in a 360-degree image may appear distorted or split into multiple pieces in a typical cubemap, leading to failure of detection of such objects, we introduce a modified cubemap. Then our method applies a Long Short Term Memory (LSTM) network based object detection method to find a region of interest with a given natural language sentence. Finally, our method produces an image that contains the detected region, and also has aesthetically pleasing composition.

• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.487-498
• /
• 2022

Depth map is an image that contains distance information in 3D space on a 2D plane and is used in various 3D vision tasks. Many existing depth estimation studies mainly use narrow FoV images, in which a significant portion of the entire scene is lost. In this paper, we propose a technique for generating 360° omnidirectional RGBD images from a sparse set of narrow FoV images. The proposed generative adversarial network based image generation model estimates the relative FoV for the entire panoramic image from a small number of non-overlapping images and produces a 360° RGB and depth image simultaneously. In addition, it shows improved performance by configuring a network reflecting the spherical characteristics of the 360° image.