5

I've been toying around with the GrabCut algorithm (as implemented in OpenCV) on the iPhone. The performance is horrid. It takes about 10-15 seconds to run even on the simulator for an image that's about 800x800. On my phone it runs for several minutes, eventually runs out of memory, and crashes (iPhone 4). I'm sure there's probably some optimization I can do if I write my own version of the algorithm in C, but I get the feeling that no amount of optimization is going to get it anywhere near usable. I've dug up some performance measurements in some academic papers and even they were seeing 30 second runtimes on multicore 1.8 ghz CPU's.

So my only hope is the GPU, which I know literally nothing about. I've done some basic research on OpenGL ES so far, but it is a pretty in-depth topic and I don't want to waste hours or days learning the basic concepts just so I can find out whether or not I'm on the right path.

So my question is twofold:

1) Can something like GrabCut be run on the GPU? If so, I'd love to have a starting point other than "learn OpenGL ES". Ideally I would like to know what concepts I need to pay particular attention to. Keep in mind that I have no experience with OpenGL and very little experience with image processing.

2) Even if this type of algorithm can be run on the GPU, what kind of performance improvement should I expect? Considering that the current runtime is about 30 seconds AT BEST on the CPU, it seems unlikely that the GPU will put a big enough dent in the runtime to make the algorithm useful.

EDIT: For the algorithm to be "useful", I think it would have to run in 10 seconds or less.

Thanks in advance.

Kevin Craft
  • 849
  • 8
  • 18
  • Have you seen http://stackoverflow.com/questions/6328273/how-can-opengl-es-be-use-for-gpgpu-implementation ? – MSalters Aug 31 '12 at 06:58
  • So it seems that "normal processing" is possible on the GPU. Unfortunately, iPhone doesn't support OpenCL yet, so I'm still not really sure where to start, nor do I know what kind of performance improvement I could expect. – Kevin Craft Aug 31 '12 at 07:17
  • That's an incredibly complex process to decide to implement by yourself. Image segmentation on GPUs is the subject of quite a bit of research, so you might start with research publications on the topic: http://web.iiit.ac.in/~vibhavvinet/Research/ . There's also no way to answer the performance question without a working implementation on actual hardware, since you really cannot predict iOS GPU performance (I should know). On the OpenGL ES side, you can leverage something like this: https://github.com/BradLarson/GPUImage to handle lower-level details for you. – Brad Larson Aug 31 '12 at 15:06

1 Answers1

2

It seems that grabcut doesn't benefit from the image resolution. It means that the quality of the result doesn't depend directly from the quality of the input image. On the other hand the performance benefits from the size, meaning that the smaller is the image the faster is the algorithm in performing the cutout. So, try to scale the image down to 300x300, apply grabcut, take the mask out, scale the mask up to the original size , and apply the mask to the original image to obtain the result. Let me know if it works.

Luca

Luca Nardone
  • 21
  • 2