Download presentation
Presentation is loading. Please wait.
1
Fast Multi Class Distance Transforms for Video Surveillance January 2008 Theo Schouten Egon van den Broek
2
Fast Multi Class DT for Video Distance Transformation distance map D(p) = min { dist(p,q), q O }
3
Fast Multi Class DT for Video Multi Class DT class map C(p) = C(q), q O, dist(p,q) == D(p)
4
Fast Multi Class DT for Video Used original distance transformation CH11: city-block DT of Rosenfeld and Pfaltz CH34: chamfer 3,4 of Borgefors EDT4: 4-scan semi-exact EDT of Shih and Liu EDT2: 2-scan semi-exact EDT of Shih and Wu EDLT: EDT method of Maurer, Qi and Raghavan –based on dimension reduction –proces first rows then columns –partial Voronoi diagram for each row, column FEED: or own EDT
5
Fast Multi Class DT for Video Fast Exact Euclidean Distance (FEED) each q O feeds its ED to all p: D(p) = min ( D(p), ED(q,p)) border pixels bisection lines precalculate ED Faster than EDLT, EDT4, EDT2 More implementation effort more lines of code parameters and strategies
6
Fast Multi Class DT for Video Multi class extension scan methods (CH11, CH34, EDT4, EDT2): –compare d(p) with d’s of neighbours –add compare c(p) with c’s of neighbours EDLT: –add extra vector to contain class of Voronoi points –used to set class of filled-in points on row, column FEED: –change update step D(p) = min ( D(p), ED(q,p)) –if( ED(q,p) < D(p) ) D(p) = ED(q,p), C(p)=C(q)
7
Fast Multi Class DT for Video Timing Multi Class DT time in s/pixel P-4 3 GHz 1024 MB 12 KuOps, 16KB; 2048 KB P-M 1.6 GHZ 512 MB 32 KB, 32 KB ; 2048 KB image size 640 x 480 1280 x 960 2560 x 1920 640 x 480 1280 x 960 2560 x 1920 FEED0.0330.0370.0450.0360.0480.119 EDLT0.0660.0760.1950.1010.1160.317 EDT20.0590.0600.0660.1000.1040.111 CH110.013 0.0140.0180.0230.025
8
Fast Multi Class DT for Video Video frames D fixed+mov (p) = if( D fixed (p) < D mov (p) ) then D fixed+mov (p) = D fixed (p), C fixed+mov (p) = C fixed (p) else D fixed+mov (p) = D mov (p), C fixed+mov (p) = C mov (p)
9
Fast Multi Class DT for Video Fast moving part calculation fast location moving object –sequence of refining scans over the image –using RLE encoding of fixed objects use d max = max ( D fixed (p) ) to calculate D (C ) mov –only over part of the frame –bounding box of moving object extended by d max combining fixed and moving D (C ) only for part same memory locations for D fixed and D fixed+mov
10
Fast Multi Class DT for Video Extra speed-up for FEED merge the application of FEED on the moving object –with combining fixed and moving D (C ): –replace initialization D(p)= if( p O ) 0 else –by D(p) = D fixed (p) not possible for other methods –only partial evaluations of D during scans further the RLE encoding is used to speed-up FEED
11
Fast Multi Class DT for Video Timing video Multi Class DT time in s/pixel P-4 3 GHz 1024 MB 12 KuOps, 16KB; 2048 KB P-M 1.6 GHZ 512 MB 32 KB, 32 KB ; 2048 KB 640 x 480 7 fixed fullfixedvideofullfixedvideo FEED0.0350.0390.0030.0410.0450.004 EDLT0.0660.0700.0250.1020.1050.037 EDT20.0600.0640.0260.1020.1060.040 CH110.0120.0170.0130.0180.0230.019
12
Fast Multi Class DT for Video Timing video MCDT time in s/pixel P-4 3 GHz 1024 MB 12 KuOps, 16KB; 2048 KB P-M 1.6 GHZ 512 MB 32 KB, 32 KB ; 2048 KB 640 x 480 13 fixed fullfixedvideofullfixedvideo FEED0.0330.0370.0020.0380.0430.002 EDLT0.0580.0620.0120.0910.0950.019 EDT20.0610.0660.0130.1040.1090.020 CH110.0120.0170.0070.0180.0230.009
13
Fast Multi Class DT for Video Examples
14
Fast Multi Class DT for Video Conclusion extended several DT’s to –handle images with multi class objects –and to faster processing of video frames with fixed and one moving multi class objects extension methods applicable to all scans based DT’s our Fast Exact Euclidean Distance transformation –is faster (6-10) than other MC (semi-)exact EDT’s –on video frames even faster than city-block more implementation effort –tune to cache-systems, image characteristics
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.