+++ /dev/null
- <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN">\r
-<HTML>\r
- <HEAD>\r
- <TITLE>Pyramidal Lucas-Kanade Feature Tracker</TITLE>\r
- <!-- Changed by: Jean-Yves Bouguet, 31-Dec-1999 -->\r
- <!-- Formatted and proofed in GNU Emacs by: Michael Chu, 00.06.03 -->\r
- <META NAME="GENERATOR" CONTENT="Microsoft FrontPage 4.0">\r
- </HEAD>\r
- <BODY TEXT="#000000" BGCOLOR="#FFFFFF" LINK="#0000CC" VLINK="#0000FF" ALINK="#FF0000">\r
- <a name="top">\r
-\r
- <!-- <CENTER>\r
- <BLOCKQUOTE> \r
- <table border = 3 WIDTH="70%" >\r
- <TR><TD>\r
- -->\r
-\r
- <CENTER>\r
- <TABLE CELLSPACING=0 CELLPADDING=5 WIDTH="90%" BGCOLOR="#6A9BED" NOSAVE >\r
- <TR NOSAVE>\r
- <TD NOSAVE>\r
- <CENTER><I><FONT COLOR="#000000"><FONT SIZE=+4> \r
- Pyramidal Lucas-Kanade Feature Tracker\r
- </FONT></FONT></I></CENTER>\r
- </TD>\r
- </TR>\r
- </TABLE>\r
- </CENTER>\r
-\r
- <!--\r
- </TD></TR>\r
- </table>\r
- </BLOCKQUOTE>\r
- </center>\r
- -->\r
-\r
-\r
- <BR>\r
-\r
- <center><IMG SRC="pict_track.jpg" alt="tool_image" width="651" height="513"></center>\r
-\r
- <BR><BR>\r
-\r
- <H1>Description</H1>\r
-\r
-\r
- This tool lets you compute optical flow based on the Lucas-Kanade\r
- feature tracker in real time. The optical flow computation is\r
- implemented in pyramidal fashion, from coarse to fine resolution.\r
- Consequently, the algorithm can handle large pixel flows, while\r
- keeping a relatively small window of integration, and therefore\r
- achieve high local accuracy (of the order of 0.1 pixel). The tracking\r
- is done by <a href="../../ref/OpenCVRef_Motion_Tracking.htm#decl_cvCalcOpticalFlowPyrLK">\r
- cvCalcOpticalFlowPyrLK</a> function that implements algorithm, described\r
- in detail in the report\r
- <a href="../../papers/algo_tracking.pdf">algo_tracking.pdf</a>.\r
-\r
- <h1>LKDemo.exe</h1>\r
- A simple demo of Lucas-Kanade in pyramid (LKpyr) was created as\r
- shown below: This demo assumes you have USB and a USB camera\r
- installed with directShow. If you are running on Microsoft*\r
- Windows* NT 4.0, this demo will only work if you have written your\r
- own video capture source filter. Microsoft Windows 2000 is best\r
- for this and all the rest of the demos.<br>\r
- <br>\r
-\r
- <center><img border="0" src="LKpyrLabled.jpg" width="858" height="272"></center>\r
- <h2 align="left">Controls</h2>\r
- <font size=+2><b>[1]</b></font> Start/Stop video capture\r
- toggle.<br>\r
- <font size=+2><b>[2]</b></font> Find a set of trackable\r
- points (labeled by green dots) and track them.<br>\r
- <font size=+2><b>[3]</b></font> Turn off the video image\r
- and just show the tracked green points from [2].<br>\r
- <font size=+2><b>[4]</b></font> Change the size of the\r
- video display window.<br>\r
- <font size=+2><b>[5]</b></font> Adjust USB camera\r
- parameters.<br>\r
- <h2 align="left">Limitations</h2>\r
-\r
- This is just a simple, "hard coded" demo. We don't allow\r
- you to change the pyramid depth nor allow you to adjust the\r
- tracking parameters nor the thresholds for acceptable points\r
- (minimum eigen value size). We do not monitor the quality of\r
- the tracked points in this demo, thus when a point is occluded, it\r
- often sticks near or on the occluding boundary. We will add user\r
- parameter adjustments and point quality monitoring next rev. --\r
- ran out of time for this demo, so sorry.\r
-\r
- <br><br>\r
- <hr noshade size=2 width=100%>\r
-\r
- </BODY> </HTML>\r
projects / opencv / blobdiff