biofag
April 28, 2011, 4:56pm
1
Hi everybody,
I’m making a program that uses a webcam to detect people’s faces and do some other stuff.
to make that i use opencv, and most specifically i use
cascade2->detectMultiScale( smallImg, faces,1.1, 2, 0|CV_HAAR_SCALE_IMAGE,cv::Size(20, 20));
function that on my core i5 3.3ghz is too slow, i get only 5 fps.
is there a way to exploit CUDA’s abilities to get face detection quickly?
On OpenCV documentation there’s a large part about cuda’s function but i found nothing useful there
I’m trying using the same method for detect traffic signs, but i’m new in cuda any advance ?
OpenCV already provides some CUDA support, according to these pages.
OpenCV provides a real-time optimized Computer Vision library, tools, and hardware. It also supports model execution for Machine Learning (ML) and Artificial Intelligence (AI).
Est. reading time: 1 minute
http://docs.opencv.org/modules/gpu/doc/gpu.html
Maybe try if this already includes your required feature set.