淡江大學機構典藏:Item 987654321/115792
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 58335/91896 (63%)
造访人次 : 32615      在线人数 : 50
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻


    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/115792


    题名: Real-Time Implementation of an Adaptive Simultaneous Dynamic Range Compression and Local Contrast Enhancement Algorithm on a GPU
    作者: Chi-Yi Tsai;Chih-Hung Huang
    关键词: Color image enhancement;Dynamic range compression;Contrast enhancement;Real-time implementation;GPU acceleration;NVIDIA CUDA
    日期: 2019-06
    上传时间: 2019-02-21 12:10:38 (UTC+8)
    出版者: Springer Berlin Heidelberg
    摘要: Dynamic range compression is a fundamental function required in digital video cameras and display monitors to improve the visual appeal of color images. This paper presents a real-time implementation of an algorithm for adaptive dynamic range compression and contrast enhancement on a graphics processing unit (GPU). To achieve this, we first designed an adaptive intensity transfer function to handle the enhancement of standard-dynamic-range (8 bits/channel) images with both low- and high-intensity. The proposed algorithm then combines the intensity transfer function with an existing simultaneous dynamic range compression and local contrast enhancement (SDRCLCE) algorithm for the simultaneous compression of dynamic range and enhancement of local contrast. To reach real-time performance in processing high-resolution color images, the proposed algorithm is implemented using an NVIDIA GeForce GTX 650 Ti GPU based on NVIDIA’s Compute Unified Device Architecture (CUDA) parallel programming running on a 3.33GHz Intel Core i5-661 CPU. Compared with a LUT-accelerated implementation, the proposed GPU implementation was shown to accelerate the processing of 1024×1024 color images by 11.1 times and color images of 4096×4096 pixels by 7.5 times, including the cost of memory copy between the host and device.
    關聯: Journal of Real-Time Image Processing 16(2), p.321-337
    DOI: 10.1007/s11554-015-0532-4
    显示于类别:[電機工程學系暨研究所] 期刊論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    index.html0KbHTML48检视/开启

    在機構典藏中所有的数据项都受到原著作权保护.

    TAIR相关文章

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回馈