I use Opencv 2.4.10 (current stable version). And I use
gpu::CascadeClassifier_GPU::detectMultiScale to detection faces. I want to use it async with my CUDA-kernel-code which I launch in separate
cudaStream_t. But by default
CascadeClassifier_GPU launch in the default zero-stream that make impossible to launch anything async to this on GPU.
As I see here no way to use
CascadeClassifier_GPU: OpenCV DOC link
- Can I use
- If no, then in what version of OpenCV can I do it?
UPDATE: So far the only way I've found - use a separate CPU thread to perform the function of the
gpu::CascadeClassifier_GPU::detectMultiScale and perform it on a separate GPU. But for this at least I need 2 GPUs.