gSLIC: a real-time implementation of SLIC superpixel segmentation
University of Oxford, Department of Engineering Science, Parks Road, Oxford, UK
University of Oxford, 2011
We introduce a parallel implementation of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Our implementation uses GPU and the NVIDIA CUDA framework. Using a single graphic card, our implementation achieves speedups of 10x~20x from the sequential implementation. This allow us to use the superpixel segmentation method in real-time performance. Our implementation is compatible with the standard sequential implementation. Finally, the software is now online and is open source.
November 15, 2011 by hgpu
Comments
One response to “gSLIC: a real-time implementation of SLIC superpixel segmentation”
Your response
You must be logged in to post a comment.
Hey there, I’m analysing your project and I found something which is not used anywhere else.
You have in kernel __global__ void kIterateKmeans allocated in shared memory this:
//pixel index
__shared__ SLICClusterCenter pixelUpdateList[MAX_BLOCK_SIZE];
__shared__ float2 pixelUpdateIdx[MAX_BLOCK_SIZE];
You are setting it up, but you do not use it anywhere else, so what is it good for? I commented it and the project worked fine like before. Is it some improvement which wasn’t finished? Or what is it exactly?
Regards,
Robert