学位论文详细信息
Visual Attention-based Small Screen Adaptation for H.264 Videos
visual attention;video adaptation;H.264;Electrical and Computer Engineering
Mukherjee, Abir
University of Waterloo
关键词: visual attention;    video adaptation;    H.264;    Electrical and Computer Engineering;   
Others  :  https://uwspace.uwaterloo.ca/bitstream/10012/3929/1/A.Mukherjee_MASc_Thesis.pdf
瑞士|英语
来源: UWSPACE Waterloo Institutional Repository
PDF
【 摘 要 】

We develop a framework that uses visual attention analysis combined with temporalcoherence to detect the attended region from a H.264 video bitstream, and display it ona small screen. A visual attention module based upon Walther and Koch;;s model gives usthe attended region in I-frames. We propose a temporal coherence matching framework thatuses the motion information in P-frames to extend the attended region over the H.264video sequence. Evaluations show encouraging results with over 80% successful detection rate for objects of interest, and 85% respondents claiming satisfactory output.

【 预 览 】
附件列表
Files Size Format View
Visual Attention-based Small Screen Adaptation for H.264 Videos 495KB PDF download
  文献评价指标  
  下载次数:14次 浏览次数:27次