I thinking of using Haarcascades to detect faces, and there after improve tracking using the GoodFeaturesToTrack to track. I am just wondering how i should do it.. I mean the idea of using the Haar cascades is to narrow down the area I apply the GoodFeatureToTrack, i mean the function only give me some points, and how do i use those to track a face?
You can use Optical Flow to track. You will have the motion vectors for each features. You could average the different motions to get the average displacement of the bounding box.
You can get an exmple of Optical Flow here.
Some ideas. You could have a list of face objects. Haar cascades would return the list of detected faces in the current image. The tracking part would be used to predict the location of each face object and merged with the newly detected faces. If one face object doesn't receive any new detection in a certain time, you could drop this face object (false detection).
Asked: Apr 11 '15
Seen: 602 times
Last updated: Apr 11 '15
