超像素分割研究進展
一. 基於圖論的方法(Graph-based algorithms)：
1.Normalized cuts, 2000.
Jianbo Shi and Jitendra Malik. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI),22(8):888–905, 2000.
T. Cour, F. Benezit, and J. Shi. Spectral segmentation with multiscale graph decomposition. In IEEE Computer Vision and Pattern Recognition (CVPR) 2005,2005.
Project Home Page:
http://www.cis.upenn.edu/~jshi/software/
http://www.timotheecour.com/software/ncut/ncut.html
2. Graph-based segmentation, 2004.
Pedro Felzenszwalb and Daniel Huttenlocher. Efficient graph-based image segmentation. International Journal of Computer Vision (IJCV),59(2):167–181, September2004.
Project Home Page: http://cs.brown.edu/~pff/segment/
3. Graph cuts method,2008.
Alastair Moore, Simon Prince, Jonathan Warrell, Umar Mohammed, and Graham Jones. Superpixel Lattices. IEEE Computer Vision and Pattern Recognition (CVPR),2008.
Project Home Page: http://www.cs.sfu.ca/~mori/research/superpixels
4. GCa10 and GCb10,2010.
O. Veksler, Y. Boykov, and P.Mehrani. Superpixels and supervoxels in an energy optimization framework. In European Conference on Computer Vision (ECCV),2010.
Project Home Page: http://www.csd.uwo.ca/~olga/
5. Entropy RateSuperpixel Segmentation, 2011.
Ming-Yu Liu, Tuzel, O., Ramalingam, S. , Chellappa, R., Entropy Rate Superpixel Segmentation, CVPR,2011.
Project Home Page: http://www.umiacs.umd.edu/~mingyliu
6. Superpixels via Pseudo-Boolean Optimization,2011.
Yuhang Zhang, Richard Hartley, John Mashford and Stewart Burn, Superpixels via Pseudo-Boolean Optimization, International Conference on Computer Vision (ICCV), 2011.
Project Home Page: http://yuhang.rsise.anu.edu.au/yuhang/misc.html
二. 基於梯度下降的方法(Gradient-ascent-based algorithms)：
1.Watershed,1991.
Luc Vincent and Pierre Soille. Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analalysis and Machine Intelligence, 13(6):583–598, 1991.
2. Mean Shift,2002.
D. Comaniciu and P. Meer. Meanshift: a robust approach toward featurespace analysis. IEEE Transactions on Pattern Analysis and MachineIntelligence,24(5):603–619, May 2002.
3. Quick Shift,2008
A. Vedaldi and S. Soatto. Quickshift and kernel methods for mode seeking. In European Conferenceon Computer Vision (ECCV), 2008.
Project Home Page: http://www.vlfeat.org/download.html
4. Turbopixel,2009.
A. Levinshtein, A. Stere, K. Kutulakos, D. Fleet, S. Dickinson, and K. Siddiqi. Turbo pixels: Fast superpixels using geometric flows. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI),2009.
Project Home Page: http://www.cs.toronto.edu/~babalex/
5. SLIC,2010.
R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Susstrunk, SLIC Superpixels, 2010.
Project Home Page: http://ivrg.epfl.ch/research/superpixels
6. SEEDS, 2012.
M. Van den Bergh, X. Boix, G. Roig, B. de Capitani, L. VanGool. SEEDS: Superpixels Extracted via Energy-Driven Sampling, ECCV2012.
Project Home Page: http://www.vision.ee.ethz.ch/~boxavier/seeds/
以下引用
Song X Y，Zhou L L，Li Z G，Chen J，Zeng L，Yan B． Ｒeview on superpixel
methods in image segmentation ［J］． Journal of Image and
Graphics，2015，20( 5) : 0599-0608．［宋熙煜，周利莉，李中國，陳健，曾磊，閆鑌．
圖像分割中的超像素方法研究綜述［J］． 中國圖象圖形學報，2015，20(5) : 0599-0608．］
除上述原始SLIC算法外，還有采用其他方法計算距離的 GSLIC( SLIC with a geodesic distance meas-ure)［3］和 ASLIC( SLIC with an adaptively normalized distance measure)［3］改進算法。文獻［9］的作者還在其網站 上 發 布 了 SLIC 的 零 參 數 版 本———SLI-CO［20］，該算法能自適應地爲每個超像素選擇最優的緊密度參數。
針對 SLIC 算法的改進還有: 2011年，Ｒen等人［21］提出的基於 CUDA( compute unified device architecture) 框架的 GPU 並行加速 SLIC; 2012年，Schick 等人［22］提出的能夠直接精確控制超像素緊密度的改進 SLIC; 2013 年，Kim 等人［23］提出了在迭代更新聚類中心過程中引入 sigma 濾波以克服原始 SLIC 算法迭代誤差傳播問題的改進 SLIC。
- [3] Achanta Ｒ，Shaji A，Smith K，et al． SLIC superpixels comparedto state-of-the-art superpixel methods［J］． IEEE Transactions on Pattern Analysis and Machine Intelligence，2012，34 ( 11 ) :2274-2282. ［DOI: 10. 1109 / TPAMI． 2012. 120］
- [20] Radhakrishna Achanta． SLICO，zero parameter version of SLIC［EB/OL］． ［2014-09-16］． http: / /ivrg. epfl. ch/supplementary_material / RK_SLICSuperpixels / index. html．
- [21] Ｒen C Y，Ｒeid I． g SLIC: a real-time implementation of SLIC superpixel segmentation［Ｒ］． Oxford: University of Oxford，Department of Engineering，2011.
- [22] Schick A，Fischer M，Stiefelhagen Ｒ． Measuring and evaluating the compactness of superpixels［C］/ / Proceedings of IEEE Inter-national Conference on Pattern Ｒecognition． Washington DC，USA: IEEE，2012: 930-934.
- [23] Kim K S，Zhang D，Kang M C，et al． Improved simple linear it-erative clustering superpixels［C］/ / IEEE Symposium on Con-sumer Electronics． Washington DC，USA: IEEE，2013: 259-260. ［DOI: 10. 1109 / ISCE． 2013. 6570216]