1 / 18

Luis Herranz , Jose´ M. Martı´nez

On the use of hierarchical prediction structures for efficient summary generation of H.264/AVC bitstreams. Luis Herranz , Jose´ M. Martı´nez. Image Communication 2009. Outline. Introduction System Framework Skimming Unit (SU) Coding order Generation of the summary

Télécharger la présentation

Luis Herranz , Jose´ M. Martı´nez

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. On the use of hierarchical prediction structures for efficient summary generation of H.264/AVC bitstreams Luis Herranz, Jose´ M. Martı´nez Image Communication 2009

  2. Outline • Introduction • System Framework • Skimming Unit (SU) • Coding order • Generation of the summary • Presentation of the summary • Experiment

  3. Introduction • MPEG-2 prediction structure

  4. Introduction • Hierarchical prediction structure in H.264/AVC using P frames (delay 0)

  5. Introduction • Hierarchical prediction structure in H.264/AVC using B frames (delay 8)

  6. System Framework Analyzing input bitstream Generating the summarized bitstream Skimming unit (SU) -The selection of SUs-Temporal level # frames selected

  7. Skimming Units Temporal layer 1 Index Skimming Unit (SU)

  8. Skimming Units Overlapped SUs

  9. Generation of the Summary • Bit stream adaptation guided by skimming parameters

  10. Presentation of the Summary • Constant frame rate • Variable frame rate • Signaling the changes of frame rate • Using a predefined set of SPSs

  11. Summarization Modalities • Image storyboard: • Video Skim: • Frame dropping • Fast preview Frame selection Skimming curve

  12. Image Storyboard • Clustered using K-means algorithm

  13. Video Skimming • Face detection • Moving median filter (a) Frames with face detected (b) Skimming parameters -- 32 frames per GOP (c) Skimming parameters -- 2 frames per GOP

  14. Fast Preview • Motion activity • Median filter (a) Filtered activity (b) Skimming parameters -- 32 frames GOP (c) Skimming parameters -- 2 frames GOP

  15. Subjective Evaluation Visual distortion Semantic distortion

  16. Performance Evaluation • Coding efficiency and processing time

  17. Performance Evaluation • Bit stream extraction • Low computational cost • Faster generation of the bit stream

  18. storyboard skim Fast playback

More Related