• Title/Summary/Keyword: Omnidirectional Images

Search Result 35, Processing Time 0.15 seconds

Proposal and Implementation of Intelligent Omni-directional Video Analysis System (지능형 전방위 영상 분석 시스템 제안 및 구현)

  • Jeon, So-Yeon;Heo, Jun-Hak;Park, Goo-Man
    • Journal of Broadcast Engineering
    • /
    • v.22 no.6
    • /
    • pp.850-853
    • /
    • 2017
  • In this paper, we propose an image analysis system based on omnidirectional image and object tracking image display using super wide angle camera. In order to generate spherical images, the projection process of converting from two wide-angle images to the equirectangular panoramic image was performed and the spherical image was expressed by converting rectangular to spherical coordinate system. Object tracking was performed by selecting the desired object initially, and KCF(Kernelized Correlation Filter) algorithm was used so that robust object tracking can be performed even when the object's shape is changed. In the initial dialog, the file and mode are selected, and then the result is displayed in the new dialog. If the object tracking mode is selected, the ROI is set by dragging the desired area in the new window.

Collision Avoidance Using Omni Vision SLAM Based on Fisheye Image (어안 이미지 기반의 전방향 영상 SLAM을 이용한 충돌 회피)

  • Choi, Yun Won;Choi, Jeong Won;Im, Sung Gyu;Lee, Suk Gyu
    • Journal of Institute of Control, Robotics and Systems
    • /
    • v.22 no.3
    • /
    • pp.210-216
    • /
    • 2016
  • This paper presents a novel collision avoidance technique for mobile robots based on omni-directional vision simultaneous localization and mapping (SLAM). This method estimates the avoidance path and speed of a robot from the location of an obstacle, which can be detected using the Lucas-Kanade Optical Flow in images obtained through fish-eye cameras mounted on the robots. The conventional methods suggest avoidance paths by constructing an arbitrary force field around the obstacle found in the complete map obtained through the SLAM. Robots can also avoid obstacles by using the speed command based on the robot modeling and curved movement path of the robot. The recent research has been improved by optimizing the algorithm for the actual robot. However, research related to a robot using omni-directional vision SLAM to acquire around information at once has been comparatively less studied. The robot with the proposed algorithm avoids obstacles according to the estimated avoidance path based on the map obtained through an omni-directional vision SLAM using a fisheye image, and returns to the original path. In particular, it avoids the obstacles with various speed and direction using acceleration components based on motion information obtained by analyzing around the obstacles. The experimental results confirm the reliability of an avoidance algorithm through comparison between position obtained by the proposed algorithm and the real position collected while avoiding the obstacles.

Real-time 3D Volumetric Model Generation using Multiview RGB-D Camera (다시점 RGB-D 카메라를 이용한 실시간 3차원 체적 모델의 생성)

  • Kim, Kyung-Jin;Park, Byung-Seo;Kim, Dong-Wook;Kwon, Soon-Chul;Seo, Young-Ho
    • Journal of Broadcast Engineering
    • /
    • v.25 no.3
    • /
    • pp.439-448
    • /
    • 2020
  • In this paper, we propose a modified optimization algorithm for point cloud matching of multi-view RGB-D cameras. In general, in the computer vision field, it is very important to accurately estimate the position of the camera. The 3D model generation methods proposed in the previous research require a large number of cameras or expensive 3D cameras. Also, the methods of obtaining the external parameters of the camera through the 2D image have a large error. In this paper, we propose a matching technique for generating a 3D point cloud and mesh model that can provide omnidirectional free viewpoint using 8 low-cost RGB-D cameras. We propose a method that uses a depth map-based function optimization method with RGB images and obtains coordinate transformation parameters that can generate a high-quality 3D model without obtaining initial parameters.

The Developement of Small 360° Oral Scanner Lens Module (소형 360° 구강 스캐너 렌즈 모듈 개발)

  • Kwak, Dong-Hoon;Lee, Sun-Gu;Lee, Seung-Ho
    • Journal of IKEEE
    • /
    • v.22 no.3
    • /
    • pp.858-861
    • /
    • 2018
  • In this paper, we propose the development of a small $360^{\circ}$ oral scanner lens module. The proposed small $360^{\circ}$ oral scanner lens module consists of a small $360^{\circ}$ high resolution(4MegaPixel) lens optical system, a 15mm image sensor unit, and a small $360^{\circ}$ mouth scanner lens external shape. A small $360^{\circ}$ high resolution lens optical system produces a total of nine lenses, the outer diameter of the lens not less than 15mm for use by children through the ages of adulthood. Light drawn by a small $360^{\circ}$ high resolution lens optical system is $90^{\circ}$ flexion so that image images are delivered to image sensors. The 15mm image sensor unit sends the converted value to the ISP(Image Signal Processor) of the embedded board after an image array through the column and the row address of the image sensor. The small $360^{\circ}$ mouth scanner lens outer shape was designed to fix the race to the developed lens. Results from authorized testing agencies to assess the performance of proposed small $360^{\circ}$ oral scanner lens modules, The optical resolving power of $360^{\circ}$ lens was more than 30% at 150 cycles/mm, $360^{\circ}$ lens angle was $360^{\circ}$ in vertical direction, $42^{\circ}{\sim}85^{\circ}$ in vertical direction, and lens distortion rate was 5% or less. It produced the same result as the world's highest level.

A Study on the Narratives of Lee Ae-rim's Comic Books -Focusing on the Characteristics of Repetition, Coincidence, and Fantasy (이애림 만화 서사 연구 -반복, 우연, 환상의 특성을 중심으로)

  • Lee, Cheong
    • Journal of Popular Narrative
    • /
    • v.25 no.1
    • /
    • pp.281-313
    • /
    • 2019
  • This paper was written to investigate the narrative traits of Lee Ae-rim's Comic Books. Lee Ae-rim arrived on the scene with the boom of comic book magazines in the 1990s. Although she started her career as a Comic Book writer, she expanded her own area gradually and has been working actively as an animation director as well. The superficial characteristics of Lee Ae-rim's works can be summed up as sexuality, grotesqueness, and fantasy. In other words, Lee Ae-rim's comic books are mainly characterized by the visualization of sexual, grotesque, and fantastic shapes. Lee Ae-rim has faced challenges with her own overwhelming and compelling images like no one else. For that reason, it is true that people haven't paid careful attention to the hidden stories behind her pictures. This paper considers that looking back on the narratives that Lee Ae-rim has been interested in, from early days to recent days, that is to say, the contexts of stories, is a shortcut to reveal a point of contact between her past, present, and future. Especially, this paper focused on the properties of the circulated and repeated stories, the stories ruled by fate and coincidence, and the stories in which elements of fantasy encounter an attempt of violation. As a result, it was found that the narratives of Lee Ae-rim's comic books demand us to face suppressed desires in a new way, by wrapping up the most fundamental aspects of human being in universality and constancy with specificity and grotesqueness. The reason why Lee Ae-rim has continued the avant-garde and omnidirectional works thus far explains what our society suppresses, inversely. Moreover, the narratives of Lee Ae-rim are significant, by being devoted to the right function of art not only to disclose suppressed desires but to satisfy them. Making an in-depth investigation of the narratives of Lee Ae-rim's comic books in various contexts, this research is intended to establish a diversity of Korean comic books, by adding meaning to the creative values of individual writers.