Presentation is loading. Please wait.

Presentation is loading. Please wait.

Automatic Video Shot Detection from MPEG Bit Stream Jianping Fan Department of Computer Science University of North Carolina at Charlotte Charlotte, NC.

Similar presentations


Presentation on theme: "Automatic Video Shot Detection from MPEG Bit Stream Jianping Fan Department of Computer Science University of North Carolina at Charlotte Charlotte, NC."— Presentation transcript:

1 Automatic Video Shot Detection from MPEG Bit Stream Jianping Fan Department of Computer Science University of North Carolina at Charlotte Charlotte, NC

2 Why we need video shots? a. Text Retrieval: Keyword Extraction Indexing Document Storage Reverse File Indexing

3 Why we need video shots? b. Database Query: Entity Extraction Indexing Database Storage B-Tree Indexing

4 Why we need video shots? c. Image Retrieval: Object Indexing Indexing Database Storage Ontology Indexing

5 Why we need video shots? MPEG Video Sequence Video shot frames

6 Why we need video shots? Story Unit in News Video Each story unit may consist of multiple connected video shots!

7 Why we need video shots? Indexing Video Shots in Storage Shot Indexing ???

8 Storage Database Query Processing Server Networks ??? Video shot =?= keyword in video? Shot is used as basic unit for video indexing!

9 1. Why we need shot detection? Potential Search on Video Shots: a.Give me some videos which consist of similar video shots! b. Give me all the videos which are related to this video shot!

10 2. Content Structure of Video Sequence Video sequence Video shot frames Shot-Based Video Content Interpretation!

11 3. Coding Structure in MPEG Video Video sequence GOP MPEG encoding shot ?

12 Interesting Questions If you are leader of MPEG around 1994, how can you design new MPEG standards which can be used for video indexing?

13 New MPEG Standard with Video Shot Video sequence GOP Video shot frames GOP is Video Shot!

14 4. What’s mean of video shot? (a) Scene Cuts; (b) Fade in & Fade out; © Dissolves & Wipes Why We Have Shots: (a) Human Editing; (b) Content Change & Camera Motion Shot Types:

15 4. What’s mean of video shot? time video Shot 1 a.Scene Cuts: Sudden change of video content or focus

16 b. Fade: gradual transition between a screen and a 4. What’s mean of video shot? constant image (fade out).

17 c. Dissolve: gradual transition from one screen to 4. What’s mean of video shot? another, the first screen fade & the second one fade out.

18 4. What’s mean of video shot? Dissolve

19 d. Wipe: a line moves across the screen & new appears behind the line 4. What’s mean of video shot?

20 Wipe

21 Video Sequence Video shot frames Conclusion: Why we have video shots? Big change between two continuous video frames!

22 How can we detect video shots? Why we can define them as cuts, wipe, ….? Because they are changed between neighboring video frames!!!! How can we measure the changes or similarities between the neighboring video frames? How can make decision on whether they are change or not?

23 5. How to detect video shot? Major Components for Shot Detection: a.Visual Representation of Video Frames: Color, Texture… b.Difference Calculation for Neighboring Video Frames c.Threshold for Decision Making: How Large is Enough?

24 5. How to detect video shot? How to measure statistical property of video frames? Color Histogram

25 5. How to detect video shot? How to measure statistical property of video frames? Color Histogram

26 5. How to detect video shot? How to measure statistical property of video frames? Texture Histogram

27 5. How to detect video shot?

28 How we can do this more efficient on MPEG videos? MPEG videos MPEG Decoder Color Histogram Difference Scene Cut Frame Output Automatic Threshold Determination a. Easy but not smart

29 Scene Cut

30 Effects on color histogram difference by scene cuts: 5. How to detect video shot?

31 How to measure the change of video content? Color Histogram Difference

32 5. How to detect video shot? How we can select the threshold automatically? a.J. Fan, D.K.Y. Yau, W.G. Aref, A. Rezgui, ``Adaptive motion- compensated video coding scheme towards content-based bit rate allocation”, Journal of Electronic Imaging, vol.9, no.4, pp , This algorithm can adapt the thresholds to different videos. b. J. Fan, et al., ``ClassView: Hierarchical video shot classification and retrieval”, IEEE Trans. on Multimedia, This algorithm can adapt thresholds to different video shots.

33 5. How to detect video shot? Relationships among continuous frames can defined as: scene cuts versus non-scene cuts probability T non-scene cut scene cut

34 5. How to detect video shot? How to obtain T automatically? Entropy for non-scene cut frames:

35 Interesting Questions What will happen on MPEG bit stream if the current video frame is a shot boundary? I B P How can we use such properties for shot detection?

36 5. How to detect video shot? b. Complex but smart approach GOP MPEG encoding If scene cuts happen on I frames in MPEG Video? How to calculate color histograms of I frames efficiently? Only decode DC coefficient!!!

37 5. How to detect video shot? b. Complex but smart approach What will happen on MPEG bit stream if there is a shot boundary? 1.5Mb/s 4Mb/s Picture Quality high low

38 Reference frame( I or P)Current P frame Most macroblocks can not find their correspondences!! If content change happens on P frames in MPEG video? Only decode the block coding types in P frames!!!

39 Previous ReferenceCurrent B frame Future Reference Most macroblocks in B current frame can only be predicted by backward way!! If content change happens on B frames in MPEG video? Only decode the coding types in B frames!!!!

40 6. Shot Detection via Edge Extraction Edges indicate the content structure of video frames!

41 6. Shot Detection via Edge Extraction MPEG videos MPEG Decoder Color Edge Detection Scene Cut Frame Output Automatic Threshold Determination a. Easy but not smart

42 6. Shot Detection via Edge Extraction a.J. Fan, W.G. Aref, M.-S. Hacid and A.K. Elmagarmid, ``An automatic isotropic color edge detection technique”, Pattern Recognition Letters, vol.22, pp ,

43 6. Shot Detection via Edge Extraction b. complex but smart Only decode only part of MPEG videos DCT What you find from this figure?

44 6. Shot Detection via Edge Extraction 1. Calculate the directional edge histogram Horizontal edges Vertical edges Northwest diagonal edges Northeast diagonal edges 2. Calculate the differences of the directional edge histogram 3. Threshold to obtain the scene cuts

45 Effects on color histogram different by Fades & Dissolves 7. Complex Shot Detection

46 Wipe Modeling Dissolve Modeling 7. Complex Shot Detection

47 8. Camera Motion Detection a.Zoom in

48 8. Camera Motion Detection b. Zoom out

49 8. Camera Motion Detection c. Left Pan

50 8. Camera Motion Detection d. Right Pan

51 Why We Need Keyframe Extraction?

52

53 Keyframe Extraction What are keyframes? Different from others! How to measure the significance of video frames? How to make the decision?

54 9. Background Modeling for Shot Detection

55

56

57

58

59

60 10. Shot-Based Video Content Representation Statistical Information Keyframe-Based Information (a)Color histogram & variance; (b) edge histogram & variance © motion histogram & variance; (a)Color histogram; (b) edge histogram © motion histogram

61 11. Shot-Oriented Video Semantics Interpretation

62 Who cares?

63 12. Who works on this topic? 1. IBM research center 2. Intel 3. Microsoft Redmond & Beijing 4. Kodak at Rochester 5. HP at Polo Alto 6. Google 7. Yahoo!

64 12. Requirement If you are asked to work on video shot detection from compressed video stream, what you should know (basic requirement)? a.MPEG video coding standard: how to decode and read MPEG file b. Knowledge on video shot analysis: Color, motion, edge, fade, dissolve, … c. Skills on C++

65 Project Introduction Design a system for automatic shot detection from MPEG video streams Interface design: read in MPEG files and display shot boundaries, or even decision process!


Download ppt "Automatic Video Shot Detection from MPEG Bit Stream Jianping Fan Department of Computer Science University of North Carolina at Charlotte Charlotte, NC."

Similar presentations


Ads by Google