source: level2/competencies/FaceTracking/README.txt @ 234

Revision 162, 1.5 KB checked in by ginevra, 10 years ago (diff)
5This code allows for the detection and tracking of a face in the scene.
6Face detection is performed using Haar classifiers and is based on the
7OpenCV face detection code.
8Tracking is performed using a Camshift wrapper (see License.txt,
9in the Camshift wrapper folder, for more details) based on the Camshift
10algorithm provided by OpenCV, which tracks a combination of colours.
12The main program waits until a face is detected in the scene (using
13the function waitForFaceDetect()); when a face is detected, the tracking
14is automatically initialised using the face bounding box returned by
15the Haar classifier.
17You may need to modify the paths for the Haar classifiers (in the
18function InitFaceDetection() of the class FaceDetection) to reflect
19your directory structure.
21The functions setVmin() and setSmin() allow for the setting of the
22Camshift parameters. The suitable values to use may change according
23to your application and setup.
25The program allows for a re-initialisation of the tracking.
26The user can re-initialise the tracking process by pressing the 'r' key.
27When the 'r' key is pressed, the program waits until a face is detected
28and re-initialise the tracker using the new face bounding box.
30The code has been written and tested in Windows,
31but it should work under Linux as well.
33You will need to install OpenCV on your machine.
35Questions to:
Note: See TracBrowser for help on using the repository browser.