臺灣博碩士論文加值系統

近幾年的超像素演算法透過反覆迭代計算來求得最佳的結果，但此種方法通常需要龐大的運算量，因此往往難以達到即時的運算速度。在本論文中，我們提出了一個新的超像素提取演算法，此演算法除了可以克服傳統方法運算量的問題外，同時能夠確保超像素形狀的穩定性以及緊湊性。為達到快速提取超像素的目標，我們事先對色彩空間和座標空間進行量化，接著再透過最大後驗估計來分配每個像素所屬的超像素。由實驗結果證明，我們的超像素提取演算法除了能夠快速提取超像素外，並且能精確地保留物體的邊界。此外在多項的評估分析中，更進一步證明我們的演算法在效能和運算速度上比起其他的演算法更具有競爭力。

We propose a novel superpixel extraction method to generate regular and compact superpixels. To reduce the computational burden of iterative optimization procedure of most recent approaches, the spatial and color quantizations are performed to represent pixels and superpixels. Then, pixels are assigned to the most spatially and visually similar superpixels using maximum a posterior estimation in the pixel and region levels. As a result, the extracted superpixels can precisely adhere boundaries of objects and are extremely efficient to generate. Experimental results show that the proposed method can achieve better or competitive performance compared to the state-of-the-art superpixel extraction approaches in terms of boundary recall, undersegmentation error and achievable segmentation accuracy and is significantly faster than these approaches.

摘要 i
Abstract ii
Index iii
Figure and Table Index iv
1. Introduction 1
2. Related Work 4
2.1 Graph-based approaches 4
2.2 Gradient-ascent-based approaches 5
3. Method 8
3.1 Spatial Quantization 8
3.2 Color Quantization 10
3.3 Non-Iterative MAP Pixel Label Assignment 12
3.4 Neighborhood Refinement 14
4. Experiments 17
4.1 Parameter Selection 17
4.2 Quantitative Comparisons 24
4.3 Qualitative Comparisons 28
5. Conclusion 33
6. References 34

[1] A. Bodis-Szomoru, H. Riemenschneider, and L. V. Gool. "Superpixel meshes for fast edge-preserving surface reconstruction," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 2011-2020, 2015.
[2]D. Giordano, F. Murabito, S. Palazzo, and C. Spampinato. "Superpixel-based video object segmentation using perceptual organization and location prior," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 4814-4822, 2015.
[3]Z. Tian, L. Liu, Z. Zhang and B. Fei, "Superpixel-Based Segmentation for 3D Prostate MR Images, " IEEE Trans. on Medical Imaging, vol. 35, no. 3, pp. 791-801, 2016.
[4]H. Su, Z. Yin, S. Huh, T. Kanade and J. Zhu, "Interactive Cell Segmentation Based on Active and Semi-Supervised Learning," IEEE Trans. on Medical Imaging, vol. 35, no. 3,pp. 762-777, 2016.
[5]H. Kong, M. Gurcan and K. Belkacem-Boussaid, "Partitioning Histopathological Images: An Integrated Framework for Supervised Color-Texture Segmentation and Cell Splitting, " IEEE Trans. on Medical Imaging, vol. 30, no. 9, pp. 1661-1677, 2011.
[6]A. Levinshtein, S. Dickinson and C. Sminchisescu, "Multiscale symmetric part detection and grouping," in Proc. IEEE International Conf. on Computer Vision, pp. 2162-2169, 2009.
[7]H. Liang, J. Yuan and D. Thalmann, "Parsing the Hand in Depth Images," IEEE Trans. on Multimedia, vol. 16, no. 5, pp. 1241-1253, 2014.
[8]F. Yang, H. Lu, and M.-H. Yang. "Robust superpixel tracking," IEEE Trans. Image Processing, vol. 23, no. 4, pp. 1639-1651, 2014.
[9]X. Zhou, X. Li, T. J. Chin and D. Suter, "Superpixel-driven level set tracking," in Proc. IEEE International Conf. on Image Processing, pp. 409-412, 2012
[10]D. T. Lin and C. H. Hsu, "Crossroad Traffic Surveillance Using Superpixel Tracking and Vehicle Trajectory Analysis," in Proc. International Conf. Pattern Recognition, pp. 2251-2256, 2014
[11]Y. Yuan, J. Fang and Q. Wang, "Robust Superpixel Tracking via Depth Fusion," IEEE Trans. on Circuits and Systems for Video Technology, vol. 24, no. 1, pp. 15-26, Jan. 2014.
[12]J. Wang and Y. Yagi, "Many-to-Many Superpixel Matching for Robust Tracking", IEEE Trans. on Cybernetics, vol. 44, no. 7, pp. 1237-1248, 2014.
[13]Z. Liu, X. Zhang, S. Luo, and O. L. Meur. "Superpixel-based spatiotemporal saliency detection," IEEE Trans. Circuits and Systems for Video Technology, vol. 24, no. 9, pp. 1522-1540, 2014.
[14]M. Manfredi, C. Grana and R. Cucchiara, "Learning superpixel relations for supervised image segmentation," in Proc. IEEE International Conf. on Image Processing, pp. 4437-4441, 2014.
[15]S. C. Pei, W. W. Chang and C. T. Shen, "Saliency detection using superpixel belief propagation," in Proc. IEEE International Conference on Image Processing, pp. 1135-1139, 2014.
[16]Z. Liu, X. Zhang, S. Luo and O. Le Meur, "Superpixel-Based Spatiotemporal Saliency Detection," IEEE Trans. on Circuits and Systems for Video Technology, vol. 24, no. 9, pp. 1522-1540, 2014.
[17]H. Jiang, Y. Wu and Z. Yuan, "Probabilistic salient object contour detection based on superpixels," in Proc. IEEE Conf. on Image Processing, pp. 3069-3072, 2013.
[18]Z. Li, X.-M. Wu, and S.-F. Chang, "Segmentation using superpixels: A bipartite graph partitioning approach," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 789-796, 2012.
[19]J. Shi and J. Malik, "Normalized cuts and image segmentation," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888-905, 2000.
[20]R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Susstrunk, "SLIC superpixels compared to state-of-the-art superpixel methods," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 34, no. 11, pp. 2274-2282, 2012.
[21]P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik, "Contour detection and hierarchical image segmentation", IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 33, no. 5, pp. 898-916, 2011.
[22]J. Shi and J. Malik, "Normalized cuts and image segmentation," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888-905, 2000.
[23]G. Mori, "Guiding model search using segmentation," in Proc. International Conf. on Computer Vision, vol. 2, pp. 1417-1423, 2005.
[24]P. F. Felzenszwalb and D. P. Huttenlocher, "Efficient graph based image segmentation, " International Journal of Computer Vision, vol. 59, no. 2, pp. 167-181, 2004.
[25]A. P. Moore, S. J. D. Prince, J. Warrell, U. Mohammed, and G. Jones, "Superpixel lattices, " in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1-8, 2008.
[26]A. P. Moore, S. J. D. Prince, and J.Warrell, "Lattice cut – constructing superpixels using layer constraints," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 2117-2124, 2010.
[27]M.-Y. Liu, O. Tuzel, S. Ramalingam, and R. Chellappa, "Entropy rate superpixel segmentation," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 2097-2104, 2011.
[28]O. Veksler, Y. Boykov, and P. Mehrani, "Superpixels and supervoxels in an energy optimization framework," in Proc. European Conf. on Computer Vision, pp. 211-224, 2010.
[29]Y. Zhang, R. Hartley, J. Mashford, and S. Burn, "Superpixels via pseudo-boolean optimization," in Proc. International Conf. on Computer Vision, pp. 1387-1394, 2011.
[30]Z. Li and J. Chen, "Superpixel segmentation using linear spectral clustering," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 1356-1363, 2015.
[31]L. Vincent and P. Soille, "Watersheds in digital spaces: an efficient algorithm based on immersion simulations," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 6, pp. 583-598, 1991.
[32]D. Comaniciu and P. Meer, "Mean shift: a robust approach toward feature space analysis, " IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 603-619, 2002.
[33]A. Vedaldi and S. Soatto, "Quick shift and kernel methods for mode seeking," in Proc. European Conf. on Computer Vision, pp. 705-718, 2008.
[34]A. Levinshtein, A. Stere, K. Kutulakos, D. Fleet, S. Dickinson, and K. Siddiqi, "Turbopixels: Fast superpixels using geometric flows," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31, no. 12, pp. 2290-2297, 2009.
[35]G. Zeng, P. Wang, P. Wang, R. Gan, and H. Zha, "Structure sensitive superpixels via geodesic distance," in Proc. International Conf. on Computer Vision, pp. 447–454, 2011.
[36]M. Van den Bergh, X. Boix, G. Roig, B. de Capitani, and L. Van Gool, "Seeds: Superpixels extracted via energy-driven sampling," in Proc. European Conf. on Computer Vision, pp. 13-26, 2012.
[37]J. Shen, Y. Du, W. Wang, and X. Li, "Lazy random walks for superpixel segmentation, " IEEE Trans. Image Processing, vol. 23, no. 4, pp. 1451-1462, 2014.
[38]H. Fu, X. Cao, D. Tang, Y. Han, and D. Xu, "Regularity preserved superpixels and supervoxels," IEEE Trans. Multimedia, vol. 16, no. 4, pp. 1165-1175, 2014.
[39]X. Chen, S. Kwong, and J.-F. Feng, "A new compression scheme for color-quantized images," IEEE Trans. Circuits and Systems for Video Technology, vol. 12, no. 10, pp. 904-908, 2002.
[40]M. Orchard and C. Bouman, "Color quantization of images," IEEE Trans. Signal Processing, vol. 39, no. 12, pp. 2677-2690, 1991.