Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Keyframe-based Video Summarization Designer

799 views

Published on

https://imatge.upc.edu/web/publications/keyframe-based-video-summarization-designer

This Final Degree Work extends two previous projects and consists in carrying out an improvement of the video keyframe extraction module from one of them called Designer Master, by integrating the algorithms that were developed in the other, Object Maps.
Firstly the proposed solution is explained, which consists in a shot detection method, where the input video is sampled uniformly and afterwards, cumulative pixel-to-pixel difference is applied and a classifier decides which frames are keyframes or not.
Last, to validate our approach we conducted a user study in which both applications were compared. Users were asked to complete a survey regarding to different summaries created by means of the original application and with the one developed in this project. The results obtained were analyzed and they showed that the improvement done in the keyframes extraction module improves slightly the application performance and the quality of the generated summaries.

Published in: Technology
  • STOP GETTING RIPPED OFF! LEARN THE SHOCKING TRUTH ABOUT ACNE, DRUGS, CREAMS AND THE ONLY PATH TO LASTING ACNE FREEDOM... To get the FACTS on exactly how to eliminate your Acne from the root 100% naturally and Permanently and achieve LASTING clear skin without spending your hard-earned money on drugs and over the counters... ♣♣♣ http://scamcb.com/buk028959/pdf
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here
  • Be the first to like this

Keyframe-based Video Summarization Designer

  1. 1. KEYFRAME-BASED VIDEO SUMMARIZATION DESIGNER Carlos Ramos Caballero Advisors: Horst Eidenberger and Xavier Giró I Nieto
  2. 2. Contents  Introduction  State of the art  Methodology  Results assessment  Conclusions 2
  3. 3.  The application: Designer Master DEMONSTRATION 3
  4. 4. Contents  Introduction  State of the art  Methodology  Results assessment  Conclusions 4
  5. 5. Introduction  Motivation  Designer Master: keyframe-based video summarization interface  Object Maps: system for automatic video summarization 5 Graphical User Interface (Designer Master) Computer Vision Engine (Object Maps)
  6. 6. Introduction  Goals of the thesis 6
  7. 7. Introduction  Goals of the thesis  Improving the keyframe extraction module 7
  8. 8. Introduction  Goals of the thesis  Improving the keyframe extraction module  Assessing the improvement 8
  9. 9. Contents  Introduction  State of the art  Methodology  Results assessment  Conclusions 9
  10. 10. State of the art  Shot segmentation 10 Hierarchical decomposition and representation of video content [1] [1] http://www.scholarpedia.org/article/Video_Content_Structuring
  11. 11. State of the art  Shot segmentation example 11 Shot boundary detection example [2]. [2] Martos, M. “Content-based Video Summarization to Object Maps”, Vienna University of Technology, Austria (2013).
  12. 12. State of the art  Shot segmentation techniques  Pixel-to-pixel methods • Global pixel-to-pixel • Cumulative pixel-to-pixel  Histogram-based methods • Simple histogram • Maximum histogram • Weighted histogram  Hausdorff method 12
  13. 13. Contents  Introduction  State of the art  Methodology  Results assessment  Conclusions 13
  14. 14. Methodology: Implemented solution  System architecture overview 14
  15. 15. Methodology : Implemented solution  Uniform sampling 𝑓𝑝𝑠𝑖: frame rate of the input video. 𝐿𝑖: total number of frames of the input video. 𝑁0: total number of frames we want to keep (𝑁0=100). 15
  16. 16. Methodology : Implemented solution  Gray scale domain 16 Color model transformation RGB to YIQ.
  17. 17. Methodology : Implemented solution  Difference computation Where 𝐼(𝑡,𝑖,𝑗) represents the intensity value at frame t in pixel(𝑖,𝑗). X and Y are the width and height of the video frames, respectively. 17
  18. 18. Methodology : Implemented solution  Normalization Where 𝑑̂ is the normalized value, 256 is the number of grey levels, X and Y are the width and height of the video frames, respectively. 18
  19. 19. Methodology : Implemented solution  Decision making The threshold value used in our application is 𝜏 = 0.1 (as defined in [2]). 19 [2] Martos, M. “Content-based Video Summarization to Object Maps”, Vienna University of Technology, Austria (2013).
  20. 20. Methodology: Environment  Environment 20
  21. 21. Contents  Introduction  State of the art  Methodology  Results assessment  Conclusions 21
  22. 22. Results assessment  TEST 1: Testing the applications + ‘in situ’ survey  11 participants  Test data: The intouchables trailer 22
  23. 23. Results assessment  Example: pair of summaries 23 Designer Master v1 Designer Master v2
  24. 24. Results assessment  TEST 2: web-based survey  43 participants  Test data: The Intouchables trailer 24
  25. 25. Results assessment  EVALUATION  Quality of the generated summaries  Representativeness of the generated summaries  Mean Opinion Score • 1. Unacceptable • 2. Poor • 3. Good • 4. Very good • 5. Excellent 25
  26. 26. Results assessment  Quality generated summaries “Please, rate summary 1” 26 “Please, rate summary 2”
  27. 27. Results assessment  Quality generated summaries 27 MOS MOS – scores distribution
  28. 28. Results assessment  Representativeness of the summaries “Which summary let you better recognize the video content?” 28
  29. 29. Results assessment  Representativeness of the summaries 29
  30. 30. Results assessment  Ease-of-use of the application “Do you think the application is intuitive and easy to use?” 30
  31. 31. Results assessment  Ease-of-use of the application 31
  32. 32. Results assessment  Execution time 32
  33. 33. Contents  Introduction  State of the art  Methodology  Results assessment  Conclusions 33
  34. 34. Conclusions  Accomplishment of the initial goals  Improving the keyframe extraction module by integrating both projects.  Assessing the improvement. 34
  35. 35. Conclusions  Accomplishment of the initial goals  Improving the keyframe extraction module by integrating both projects.  Assessing the improvement.  Our work has slightly improved Designer Master  Users can create better video summaries and easily due the better quality of the extracted keyframes. 35
  36. 36. Conclusions  Accomplishment of the initial goals  Improving the keyframe extraction module by integrating both projects.  Assessing the improvement.  Our work has slightly improved Designer Master  Users can create better video summaries and easily due the better quality of the extracted keyframes.  It is hoped to develop this work into a product for the Austrian Broadcasting station ORF 36
  37. 37. Conclusions  Accomplishment of the initial goals  Improving the keyframe extraction module by integrating both projects.  Assessing the improvement.  Our work has slightly improved Designer Master  Users can create better video summaries and easily due the better quality of the extracted keyframes.  It is hoped to develop this work into a product for the Austrian Broadcasting station ORF 37
  38. 38. Thank you very much for your attention! Danke schön! Moltes gràcies! 38

×