+++ /dev/null
-<HTML>\r
-<HEAD>\r
-<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1">\r
-<TITLE>3D Tracker Filter</TITLE>\r
-</HEAD>\r
-<BODY>\r
-<CENTER><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
-3D Tracker Filter\r
-</FONT></FONT></I></CENTER>\r
-</TD>\r
-</TR>\r
-</TABLE></CENTER>\r
-\r
-\r
-<H2>Description </H2>\r
-\r
-<p>\r
-The 3D tracker uses the 2D positions of objects as viewed by multiple\r
-cameras to determine the 3D position of the objects.\r
-The 3D Tracker filter is a DirectShow filter that runs under\r
-Microsoft Windows.\r
-The filter receives input from two or more cameras, passes it to \r
-2D trackers to process the video frames, then calls the OpenCV 3D\r
-tracker to combine the 2D results to compute a 3D position.\r
-</p>\r
-<p>\r
-The 2D trackers are COM objects that\r
-implement an interface called <code>ITracker</code>.\r
-The available trackers are listed in registry in the\r
-<b>Video Trackers</b> category.\r
-Before using the 3D Tracker filter, you must register the tracker(s) you\r
-want to use with <code>regsvr32.exe</code>.\r
-There is an example COM object tracker that uses the CamShift tracker\r
-already in OpenCV. There is also an example tracker called\r
-BlobTracker.\r
-</p>\r
-<p>\r
-You can run the 3D Tracker filter using the DirectShow filter graph editor,\r
-<code>graphedt.exe</code>;\r
-using the sample application provided, <code>Tracker3dDemo.exe</code>;\r
-or by writing your own application.\r
-(You can use <code>Tracker3dDemo.exe</code> as a starting point.)\r
-To use <code>Tracker3dDemo.exe</code>, you must first use <code>graphedt.exe</code> to create a filter graph \r
-for the sample app to load.\r
-</p>\r
-\r
-<h2>Setup</h2>\r
-<p>\r
-Before using the 3D Tracker filter, run the Calib filter\r
-with each of your cameras to determine the camera intrinsics.\r
-This needs to be done only once for each camera.\r
-Even if the cameras are moved, the intrinsics don't change.\r
-Save the intrinsics for each camera in a separate file.\r
-The 3D Tracker filter will ask for these filenames when you begin\r
-camera calibration in the 3D Tracker.\r
-</p>\r
-\r
-<p>\r
-When you first insert the 3D Tracker filter into a graph, it will have no pins.\r
-Use the property page to set the number of cameras, as described below,\r
-and then in GraphEdit choose <b>Refresh</b>\r
-on the <b>View</b> menu to cause GraphEdit to redisplay the filter\r
-with the selected number of input and output pins.\r
-Before you connect the inputs\r
-and outputs, set the tracker type and input frame size also.\r
-If you save the graph, the number of cameras, the tracker type,\r
-and the input size are saved with the graph.\r
-</p>\r
-\r
-<p>\r
-After you have set up the filter and connected it up,\r
-the graph will look something like this.\r
-You may have additional decompression or color conversion filters,\r
-depending on your cameras and your computer's display.\r
-</p>\r
-\r
-<CENTER><IMG SRC="3dTrackerFilterGraph.png"></CENTER>\r
-\r
-<h2>Controls</h2>\r
-<p>\r
-Right click on the 3D Tracker and choose <b>Filter Properties...</b> to bring\r
-up the filter's property page. A tab for the trackers' property page\r
-will be displayed as well if a tracker has been selected.\r
-</p>\r
-\r
-<CENTER><IMG SRC="3dTrackerPropertyPage.png"></CENTER>\r
- \r
-<p>\r
-The controls in the box can be changed only when none of the pins of\r
-the filter are connected.\r
-You must click <b>Apply</b> after changing any of the controls in the box\r
-for them to take effect.\r
-</p>\r
-<DL>\r
-<DT>Number of cameras\r
-<DD>\r
-Sets the number of input and output pins on the filter, and the number\r
-of trackers it will use. After changing this value and clicking <b>Apply</b>,\r
-you must choose <b>Refresh</b> on the <b>View</b>\r
-menu in GraphEdit to cause it to redisplay the filter with the\r
-selected number of input and output pins.\r
-</DD>\r
-</DT>\r
-\r
-<DT>Tracker type\r
-<DD>\r
-Sets the type of tracker to use for 2D tracking.\r
-The available trackers are listed in registry in the\r
-<b>Video Trackers</b> category.\r
-If the tracker you want to use isn't listed in the drop-down box,\r
-make sure it is registered.\r
-After changing the tracker type, you may close and reopen the 3D\r
-Tracker property page to cause it to display a tab for the trackers'\r
-property page as well.\r
-Although the 3D Tracker filter allows different types of trackers to\r
-be used for different cameras at the same time, the property page does\r
-not support this configuration.\r
-</DD>\r
-</DT>\r
-\r
-<DT>Any size, 640 x 480, and 320 x 240\r
-<DD>\r
-Sets the input frame size the 3D Tracker filter will accept. If\r
-<b>Any size</b> is selected, the source filter will choose the size;\r
-depending on the cameras in use, the inputs may not all be the same size.\r
-</DD>\r
-</DT>\r
-\r
-<DT>Checkerboard width and height\r
-<DD>\r
-Sets the number of columns and rows of squares in your calibration checkerboard.\r
-This will apply the next time Calibrate cameras is clicked.\r
-</DD></DT>\r
- \r
-<DT>Calibrate cameras ...\r
-<DD>\r
-Tells the filter to begin passing frames to cv3dTrackerCalibrateCameras.\r
-It pops up a dialog requesting the names of files containing the camera\r
-intrinsics as generated by CalibFilter.\r
-It uses the values in the checkerboard width and height fields.\r
-If the graph isn't running, this will take effect when the graph is run.\r
-See the next section for more information on camera calibration.\r
-</DD>\r
-</DT>\r
-\r
-<DT>Tracking results\r
-<DD>\r
-The property page also contains four fields \r
-that display the 3D coordinates of the first four objects being tracked.\r
-These fields are invisible in the image above.\r
-These fields are updated on every frame whenever the property page is open\r
-while the graph is running. If a field is gray, it means the\r
-corresponding object is not currently being tracked by at least two\r
-cameras. In this case, the location displayed is the last tracked\r
-location.\r
-</DD>\r
-</DT>\r
-\r
-</DL>\r
-\r
-<H2>Camera calibration</h2>\r
-<p>\r
-The checkerboard that is used for camera intrinsics calibration should\r
-have a large number of squares and be held close to the camera. A\r
-different checkerboard may be used to calibrate the 3D Tracker filter.\r
-It can have\r
-fewer, larger squares so it can be held farther from the camera. It must be\r
-visible to all the cameras at once. The position of the\r
-checkerboard when the 3D Tracker camera calibration is done determines\r
-the 3D coordinate system that is used to report the locations of the\r
-tracked objects. The plane of the checkerboard is the x-y plane, with\r
-the origin being the lower-left intersection on the checkerboard.\r
-</p>\r
-<p>\r
-When you begin camera calibration,\r
-you will see red circles on the images of the checkerboard as\r
-it finds corners. When it finds all the corners in an image, the\r
-circles change to rainbow colors.\r
-Once it finds all the corners in all the images at the same\r
-time, the locations of the cameras is saved and calibration stops. If\r
-this happens instantly, you may only see a flash of color in the\r
-images.\r
-To force it to keep running the calibration step even after\r
-all the corners are found, hold down the control key when you click on\r
-<b>Calibrate cameras</b>. Click <b>Calibrate cameras</b> again\r
-(without the control key) to cause it to finish calibrating.\r
-</p>\r
-<p>\r
-If you are using the BlobTracker to track infrared LEDs and\r
-you have infrared filters on the cameras, you must evenly illuminate\r
-the checkerboard with a fairly intense infrared source. A 250 watt\r
-infrared flood lamp works well. A regular (non-infrared) flood lamp\r
-probably would work as well. \r
-</p>\r
-\r
-\r
-</BODY>\r
-</HTML>\r
projects / opencv / blobdiff