• Title/Summary/Keyword: Mosaic Rendering

Search Result 12, Processing Time 0.019 seconds

Photo Mosaics using Quad-tree structure on GPU (사진트리 구조를 이용한 포토 모자이크의 GPU구현)

  • Yang, Jin-Suk;Joo, Choong-Jae;Oh, Kyoung-Su
    • Journal of the Korea Computer Graphics Society
    • /
    • v.17 no.1
    • /
    • pp.25-31
    • /
    • 2011
  • Photomosaic is a method of representation an input image in forms of mosaics by a set of small tile images. Generally, equal rectangular tiles are used in photo mosaics. Therefore, there are limitations to expression of mosaic according to characteristic of images. In this paper, photo mosaics using quad-tree structure is proposed to create tiles in varies sizes. Initially, color variance per each level of an input image is computed using the mipmap of graphic hardware. Depending on the value of Valiance, the input image is divided into tiles in varies sizes. Each tile finds the most similar reference image and replaces with it. As a result, the method provides another pictorial effectiveness by dividing the input image into tiles in varies sizes depending on color held by the input image. In addition, whole processing is done on the graphic hardware and thereby we achieve faster performance.

Sequence Images Registration by using KLT Feature Detection and Tracking (KLT특징점 검출 및 추적에 의한 비디오영상등록)

  • Ochirbat, Sukhee;Park, Sang-Eon;Shin, Sung-Woong;Yoo, Hwan-Hee
    • Journal of Korean Society for Geospatial Information Science
    • /
    • v.16 no.2
    • /
    • pp.49-56
    • /
    • 2008
  • Image registration is one of the critical techniques of image mosaic which has many applications such as generating panoramas, video monitoring, image rendering and reconstruction, etc. The fundamental tasks of image registration are point features extraction and tracking which take much computation time. KLT(Kanade-Lucas-Tomasi) feature tracker has proposed for extracting and tracking features through image sequences. The aim of this study is to demonstrate the usage of effective and robust KLT feature detector and tracker for an image registration using the sequence image frames captured by UAV video camera. In result, by using iterative implementation of the KLT tracker, the features extracted from the first frame of image sequences could be successfully tracked through all frames. The process of feature tracking in the various frames with rotation, translation and small scaling could be improved by a careful choice of the process condition and KLT pyramid implementation.

  • PDF