[1]李鹏,杨旸,方涛.应用视觉显著性的快速有偏聚类超像素算法[J].西安交通大学学报,2015,49(01):112-117.[doi:10.7652/xjtuxb201501019]
 LI Peng,YANG Yang,FANG Tao.A Fast Superpixel Algorithm with BiasedClustering Using Visual Saliency[J].Journal of Xi'an Jiaotong University,2015,49(01):112-117.[doi:10.7652/xjtuxb201501019]
点击复制

应用视觉显著性的快速有偏聚类超像素算法
分享到:

《西安交通大学学报》[ISSN:0253-987X/CN:61-1069/T]

卷:
49
期数:
2015年第01期
页码:
112-117
栏目:
出版日期:
2015-01-10

文章信息/Info

Title:
A Fast Superpixel Algorithm with BiasedClustering Using Visual Saliency
文章编号:
0253-987X(2015)01-0112-06
作者:
李鹏12杨旸2方涛1
1.上海交通大学自动化系,200240,上海;2.西安交通大学电子与信息工程学院,710049,西安
Author(s):
LI Peng12YANG Yang2FANG Tao1
1. Department of Automation, Shanghai Jiaotong University, Shanghai 200240, China;
2. School of Electronics and Information Engineering, Xi’an Jiaotong University, Xi’an 710049, China
关键词:
超像素视觉显著性有偏聚类边缘细化
Keywords:
superpixel visual saliency biasedclustering boundary refining
分类号:
TP391
DOI:
10.7652/xjtuxb201501019
文献标志码:
A
摘要:
针对正则化超像素方法的超像素数随边缘拟合要求迅速增长的问题,提出了一种有偏聚类超像素算法。结合人类视觉对目标专注程度不一的特点,在SLIC算法框架下,提出了基于视觉显著性的非均匀初始化方法和有偏聚类距离函数。算法在图像的显著性区域进行密集的过分割,保持目标边缘的细节信息,而在非显著区域仅生成稀疏的超像素,以降低分割块数,再通过一步全局聚类和边缘逐步细化过程,有效地保证了图像的边缘拟合,同时提高了算法的速度。实验表明,在相同超像素数下,所提算法在边缘查全率、欠分割错误率以及运行速度方面均优于传统算法。
Abstract:
A novel biasedclustering superpixel algorithm is proposed in the framework of SLIC to improve the problem that the conventional superpixel methods have bottleneck in controlling the tradeoff between superpixel number and boundary adherence. The algorithm employs the visual saliency into the nonuniform mesh initialization step and the biasedclustering distance function by noticing that human’s visual attentions are distinctive to different salient objects, so that dense oversegmentations are generated in salient regions to keep sufficient information for object’s boundary; while sparse segmentations are generated in nonsalient regions to reduce the number of segmentation blocks. Moreover, the ideas of onestep global clustering and gradual boundary refining are applied to speed up the algorithm. Experimental results and comparisons with several stateoftheart superpixel algorithms show that the proposed algorithm reflects the boundary adherence for salient objects well under the same number of segmentation blocks, and has a higher boundary recall and lower undersegmentation, as well as the least timeconsuming.

参考文献/References:

[1]MORI G. Guiding model search using segmentation [C]∥10th IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2005: 14171423.
[2]FULKERSON B, VEDALDI A, SOATTO S. Class segmentation and object localization with superpixel neighborhoods [C]∥12th IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2009: 670677.
[3]COMANICIU D, MEER P. Mean shift: a robust approach toward feature space analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603619.
[4]FELZENSZWALB P F, HUTTENLOCHER D P. Efficient graphbased image segmentation [J]. International Journal of Computer Vision, 2004, 59(2): 167181.
[5]VEDALDI A, SOATTO S. Quick shift and kernel methods for mode seeking [C]∥10th European Conference on Computer Vision. Berlin, Germany: Springer, 2008: 705718.
[6]SHI J, MALIK J. Normalized cuts and image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888905.
[7]MOORE A P, PRINCE S, WARRELL J, et al. Superpixel lattices [C]∥IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2008: 18.
[8]WANG J, WANG X. Vcells: simple and efficient superpixels using edgeweighted centroidal Voronoi tessellations [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(6): 12411247.
[9]ACHANTA R, SHAJI A, SMITH K, et al. SLIC superpixels compared to stateoftheart superpixel methods [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 22742281.
[10]HOU X, HAREL J, KOCH C. Image signature: highlighting sparse salient regions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(1): 194201. [11]MARTIN D, FOWLKES C, TAL D, et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics [C]∥Proceedings of Eighth IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2001: 416423.
[12]SHOTTON J, WINN J, ROTHER C, et al. Text on boost for image understanding: multiclass object recognition and segmentation by jointly modeling texture, layout, and context [J]. International Journal of Computer Vision, 2009, 81(1): 223.
[13]GOULD S, RODGERS J, COHEN D, et al. Multiclass segmentation with relative location prior [J]. International Journal of Computer Vision, 2008, 80(3): 300316.

相似文献/References:

[1]胡江策,卢朝阳,李静,等.采用超像素标注匹配的交通场景几何分割方法[J].西安交通大学学报,2018,52(08):074.[doi:10.7652/xjtuxb201808012]
 HU Jiangce,LU Zhaoyang,LI Jing,et al.A Geometric Segmentation Method for Traffic Scenes Using SuperPixel Label Matching[J].Journal of Xi'an Jiaotong University,2018,52(01):074.[doi:10.7652/xjtuxb201808012]

更新日期/Last Update: