Abstract
Superpixel segmentation is a fundamental task in computer vision. Existing works contribute to superpixel segmentation either by improving segmentation accuracy or by reducing execution time. The former modifies existing models or develops new models to improve accuracy. The latter accelerates existing implementations or reduces algorithm complexity to improve execution rate. This work falls into the second category. Recently, a superpixel algorithm using Gaussian mixture model (GMMSP) achieves state-of-the-art performance in accuracy. After exploring this algorithm, we reached new conclusions on GMMSP that unlock potential concerning fine-grain parallelism implementation. We implement GMMSP with CUDA and make it run on GPUs. Experiments are conducted to validate the consistency between CPU and GPU implementations and to evaluate the performance of our implementation with respect to a serial and an OpenMP implementation. When we consider a full implementation with a postprocessing step executed on CPU to guarantee connectivity constraint, the proposed implementation achieves a speedup of 21× compared to the OpenMP implementation for images of size 240 × 320, using NVIDIA GTX 1080. It is also mentionable that we achieve a performance of over 1000 FPS on GTX 1080 (speedup of 77× compared to the OpenMP implementation) if the connectivity constraint is not included.
Similar content being viewed by others
Notes
Refer to [4] about the implementation of color conversion.
References
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)
Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)
Ban, Z., Liu, J., Cao, L.: Superpixel segmentation using Gaussian mixture model (2016). arXiv preprint arXiv:1612.08792
Ban, Z., Liu, J., Fouriaux, J.: GLSC: LSC superpixels at over 130 fps. J. Real-Time Image Process. 1–12 (2016)
Derue, F., Bilodeau, G., Bergevin, R.: Spikes: Superpixel-keypoints structure for robust visual tracking (2016). CoRR abs/1610.07238
Garcia-Garcia, A., Orts-Escolano, S., Garcia-Rodriguez, J., Cazorla, M.: Interactive 3D object recognition pipeline on mobile GPGPU computing platforms using low-cost RGB-D sensors. J. Real-Time Image Process. (2016). https://doi.org/10.1007/s11554-016-0607-x
Guler, P., Deniz, E.: Real-time multi-camera video analytics system on GPU. J. Real-Time Image Process. 11(3), 457–472 (2016). https://doi.org/10.1007/s11554-013-0337-2
Kesavan, Y., Ramanan, A.: One-pass clustering superpixels. In: Proceedings of the International Conference on Information and Automation for Sustainability, pp. 1–5 (2014)
Levinshtein, A., Stere, A., Kutulakos, K.N., Fleet, D.J., Dickinson, S.J., Siddiqi, K.: TurboPixels: fast superpixels using geometric flows. IEEE Trans. Pattern Anal. Mach. Intell. 31(12), 2290–2297 (2009)
Li, Z., Chen, J.: Superpixel segmentation using linear spectral clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1356–1363 (2015)
Li, Z., Wu, X.M., Chang, S.F.: Segmentation using superpixels: a bipartite graph partitioning approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 789–796 (2012)
Liu, M.Y., Tuzel, O., Ramalingam, S., Chellappa, R.: Entropy rate superpixel segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2097–2104 (2011)
Lu, Z., Fu, Z., Xiang, T., Han, P., Wang, L., Gao, X.: Learning from weak and noisy labels for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(3), 486–500 (2017)
Ma, J., Zhao, J., Yuille, A.L.: Non-rigid point set registration by preserving global and local structures. IEEE Trans. Image Process. 25(1), 53–64 (2016)
Machairas, V., Faessel, M., Cardenas-Pena, D., Chabardes, T., Walter, T., Decenciere, E.: Waterpixels. IEEE Trans. Image Process. 24(11), 3707–3716 (2015)
Mei, X., Chu, X.: Dissecting GPU memory hierarchy through microbenchmarking. IEEE Trans. Parallel Distrib. Syst. 28(1), 72–86 (2017)
Mori, G.: Guiding model search using segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1417–1423 (2005)
Nguyen, T.V., Lu, C., Sepulveda, J., Yan, S.: Adaptive nonparametric image parsing. IEEE Trans. Circuits Syst. Video Technol. 25(10), 1565–1575 (2015)
NVIDIA: CUDA toolkit documentation. https://docs.nvidia.com/cuda/ (2017)
Ren, C.Y., Prisacariu, V.A., Reid, I.D.: gSLICr: SLIC superpixels at over 250Hz (2015). ArXiv e-prints
Shen, J., Du, Y., Wang, W., Li, X.: Lazy random walks for superpixel segmentation. IEEE Trans. Image Process. 23(4), 1451–1462 (2014)
Shu, G., Dehghan, A., Shah, M.: Improving an object detector and extracting regions using superpixels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3721–3727 (2013)
Van den Bergh, M., Boix, X., Roig, G., Van Gool, L.: SEEDS: superpixels extracted via energy-driven sampling. Int. J. Comput. Vis. 111(3), 298–314 (2015)
Wang, J., Wang, X.: VCells: simple and efficient superpixels using edge-weighted centroidal voronoi tessellations. IEEE Trans. Pattern Anal. Mach. Intell. 34(6), 1241–1247 (2012)
Yan, J., Yu, Y., Zhu, X., Lei, Z., Li, S.Z.: Object detection by labeling superpixels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5107–5116 (2015)
Yang, F., Lu, H., Yang, M.H.: Robust superpixel tracking. IEEE Trans. Image Process. 23(4), 1639–1651 (2014)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ban, Z., Liu, J. & Fouriaux, J. GMMSP on GPU. J Real-Time Image Proc 17, 245–257 (2020). https://doi.org/10.1007/s11554-018-0762-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11554-018-0762-3