I'm looking for high-quality machine vision cameras whose vendor provides support to OpenCV. To my knowledge, only XIMEA provides support.
And about other major brands (AVT, PointGrey, Pixelink...)?
I know it's not a problem for 1394 cameras, but I think USB3.0 and GigE cameras could become a headache without vendor support? Am I wrong?
Many "high-quality machine vision cameras" provide rich and versatile APIs beyond the basic frame grabbing that OpenCV supports. It does not make sense to hide these rich APIs behind the simple OpenCV calls, since these APIs are often the reason you are using these "high-quality machine vision cameras" in the first place.
On the other hand, once you capture a frame with any API, it is very easy to let OpenCV consume this memory directly or to copy it into an OpenCV image (cv::Mat, IplImage, etc.) for further processing.
Reading cap_ximea.cpp we can find a nice set of properties, for example CV_CAP_PROP_XI_AUTO_WB and CV_CAP_PROP_XI_EXP_PRIORITY. I understand it is probably a subset of the full features in a SDK, but I think it's really nice if the machine vision camera vendor is committed with OpenCV support.
And what's the problem with "high-quality machine vision cameras"?
Asked: 2012-08-09 13:38:39 -0600
Seen: 4,740 times
Last updated: Oct 25 '12
Not an answer, but there are many reasons not to use OpenCV in a real image processing app, but the SDK dirrectly offered by the manufacturer: modularity (keep capture in a separate layer), flexibility (easily implement other vendor's driver) or need to access functionality that is not available through the generic OpenCV's VideoCapture. Also, having a solution based directly on the camera is often better in terms of processing speed.