2014-10-07 07:53:43 -0600 | commented question | Slow OclCascadeClassifier::detectMultiScale() Exactly the same command, I set scaleFactor = 1.1 and minNeighbors = 3 in detectMultiScale parameters explicitly to be sure. And Btw, if I'm using cv::gpu::CascadeClassifier_GPU (CUDA), I get 80ms processing time. |
2014-10-07 06:34:16 -0600 | commented question | Slow OclCascadeClassifier::detectMultiScale() Well, it's not normal. I have 640*480 input frame resolution. If I'm running the same code but with CPU-based cv::CascadeClassifier I'm getting processing time 350ms per frame. |
2014-10-07 01:54:50 -0600 | answered a question | How to do face alignment without considering eye position If you don't want to locate eyes, you can for example use |
2014-10-06 12:00:31 -0600 | received badge | ● Editor (source) |
2014-10-06 10:33:05 -0600 | received badge | ● Supporter (source) |
2014-10-06 08:59:52 -0600 | asked a question | Slow OclCascadeClassifier::detectMultiScale() Hi, I have a simple demo application that detect faces in video using OclCascadeClassifier from OpenCL module. The problem is that the detectMultiScale() is really slow. First, I suspected the oclMat::upload() method, but it seems that the bottle neck is the detections itself. Here is my code: And this is the output: BTW I have nVidia GeForce GT 640M with proper driver. Thanks. Stepan |