1 / 15

Edge Detection Compression and Security of Surveillance Videos

Edge Detection Compression and Security of Surveillance Videos. 張晏豪. Experimental Setting. Windows XP Intel(R ) Core(TM)2 Quad CPU Q6600 @ 2.40GHz 2GB RAM. Experimental Parameters. Threshold_sobel :Determine how many edge points you want

elvin
Télécharger la présentation

Edge Detection Compression and Security of Surveillance Videos

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. Edge DetectionCompression and Security of Surveillance Videos 張晏豪

  2. Experimental Setting • Windows XP • Intel(R) Core(TM)2 Quad CPU Q6600 @2.40GHz • 2GB RAM

  3. Experimental Parameters • Threshold_sobel:Determine how many edge points you want • Threshold_dis: If the point is in the interval (- Threshold_dis,+ Threshold_dis), the point is regarded as edge point • Threshold_score: If the amount of edge points around the line are more than threshold_score, the line is regard as true line

  4. Experimental Results • Edge points: Original image after Sobelfilter • Threshold_sobel:130 • 2949 edge points • 4346826 lines Original image Edge points

  5. Experimental Results • Threshold_sobel:130 • Threshold_dis:5 • Threshold_score:400 • Elapsed time :4738 sec

  6. Threshold_sobel:130 Threshold_dis:1.5 Threshold_score:100 Threshold_sobel:130 Threshold_dis:1.5 Threshold_score:200 Threshold_sobel:130 Threshold_dis:1.5 Threshold_score:150 Threshold_sobel:130 Threshold_dis:1.5 Threshold_score:50

  7. Experimental Results • Threshold_sobel:130 • Threshold_dis:1.5 • Threshold_score:100 • Elapsed time:4982 sec

  8. Paint the lines with top 1000 score

  9. Hough Transform • Detect lines in r-θplane

  10. Experimental Parameters • Threshold_sobel: Determine how many edge points you want • Threshold_interval: Angle increment of each detection • Threshold_votes: If the amount of edge points on the angle are more than threshold_score, the line at this angle would be painted

  11. Threshold_sobel:250 Threshold_dis:5 Threshold_score:5 Experimental Results Threshold_sobel:130 Threshold_dis:1 Threshold_score:10 Threshold_sobel:130 Threshold_interval:1 Threshold_votes:10 Threshold_sobel:130 Threshold_interval:1 Threshold_votes:5 Threshold_sobel:130 Threshold_interval:1 Threshold_votes:20 Threshold_sobel:70 Threshold_dis:1 Threshold_score:10

  12. Experimental Results • Threshold_sobel:130 • Edge points:2949 • Threshold_interval:1 • Threshold_votes:10 • Elapsed time :0.87 sec

  13. Experimental Results Threshold_sobel:130 Threshold_interval:1 Threshold_votes:5 Threshold_sobel:130 Threshold_interval:1 Threshold_votes:10 Threshold_sobel:130 Threshold_interval:1 Threshold_votes:15

  14. Experimental Results • Threshold_sobel:130 • Edge points:4866 • Threshold_interval:1 • Threshold_votes:10 • Elapsed time :1.37 sec

  15. END

More Related