gSLIC: a real-time implementation of SLIC superpixel segmentation

Carl Yuheng Ren, Ian Reid
University of Oxford, Department of Engineering Science, Parks Road, Oxford, UK
University of Oxford, 2011


   author={Carl Yuheng Ren and Ian Reid},

   title={gSLIC: a real-time implementation of SLIC superpixel segmentation},

   institution={University of Oxford, Department of Engineering Science},



Download Download (PDF)   View View   Source Source   Source codes Source codes




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.
No votes yet.
Please wait...
  • Róbert Birkus

    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?


    No votes yet.
    Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: