I personally don't think I'd use scikit image for video work. Also the hough transform is going to be slow for video work. I'd suggest sticking with opencv and using MSER See this example https://github.com/Itseez/opencv/blob/master/samples/c/mser_sample.cpp On Jun 17, 2014 12:23 PM, "Austin Chungath" <austincv@gmail.com> wrote:

Hi,

I am trying out the ellipse hough transform as described in the following link:

http://scikit-image.org/docs/dev/auto_examples/plot_circular_elliptical_houg...

The ellipse detection in the example above with the coffee mug takes about 15 seconds to give a result. Unfortunately, I need to be able to at least do this in under a second since I am working on a video stream.

1. Is it possible to get the time taken for ellipse detection to under a second? 2. Are there any suggestions for improving the execution time? 3. Are there any other library/package that can do ellipse detection better? 4. When I use my own image instead of the coffee mug - I get an error :Buffer and memoryview are not contiguous in the same dimension I use the following code for loading the image the rest of the code is the same from the above example. image_rgb = io.imread('ellipse.png') #instead of image_rgb = data.coffee()[0:220, 160:420] Obviously I must be doing something wrong.

I had mostly been working with OpenCV so I am a bit new to skimage's way of doing things. Please feel free to assume that I am a noob and any help is much appreciated.

Thanks, Austin

-- You received this message because you are subscribed to the Google Groups "scikit-image" group. To unsubscribe from this group and stop receiving emails from it, send an email to scikit-image+unsubscribe@googlegroups.com. For more options, visit https://groups.google.com/d/optout.