基于局部区块加权曲率熵的多尺度网格显著性

doi:10.16182/j.issn1004731x.joss.201709014

系统仿真学报 ›› 2017, Vol. 29 ›› Issue (9): 1976-1983.doi: 10.16182/j.issn1004731x.joss.201709014

基于局部区块加权曲率熵的多尺度网格显著性

汪小东^1,2, 梁洪涛^1,2, 康凤举^1,2, 顾浩^1,2

1.西北工业大学航海学院,西安 710072;
2.水下信息处理与控制国家级重点实验室,西安 710072

收稿日期:2017-05-20 出版日期:2017-09-08 发布日期:2020-06-02

Multi-scale Mesh Saliency with Local Patch Weighted Curvature Entropy

Wang Xiaodong^1,2, Liang Hongtao^1,2, Kang Fengju^1,2, Gu Hao^1,2

1. Marine College, Northwestern Polytechnical University, Xi'an 710072, China;
2. National Key Laboratory of Underwater Information Process and Control, Xi'an 710072, China;

Received:2017-05-20 Online:2017-09-08 Published:2020-06-02
About author:Wang Xiaodong (1990-), Male, Yanan, China, Ph.D. research direction is research of system modeling and simulation.
Supported by:
Foundation items: Northwestern Polytechnical University doctoral dissertation Innovation Fund (CX201701)

摘要/Abstract

摘要： 网格显著性是三维网格模型的一个重要几何属性,已应用于许多方向。受现有算法的启发,提出了一种基于局部区块曲率熵的多尺度显著性检测算法。针对每个顶点,定义一个局部坐标系并计算该点曲率值;通过邻域累积体积定义一个改进的自适应区块,计算该点邻域球内每个邻居点相对于该区块的偏离值,将该值作为相应邻居点曲率的加权值;将所有邻居点的加权曲率熵作为该点的显著性值。该算法在时间复杂度方面具有可比较性,在显著性检测能力上占有优势。

关键词: 自适应区块, 网格显著性, 三维网格模型, 显著性

Abstract: Mesh saliency is an important geometrical characteristic of 3D mesh model and has been applied in many applications. Inspired by the existing algorithms, a novel multi-scale saliency detection method based on local patch weighted curvature entropy was proposed. A local coordinate system and curvature value of each vertex was estimated. An improved adaptive patch was defined on the tangent plane using accumulated volume of neighborhood. Furthermore, deviation of the patch of each vertex to their neighborhood was defined as the weight of curvature value. The Shannon entropy of weighted curvature values of neighbor vertices within a sphere centered at each vertex was defined as their saliency scores. Comparisons with state-of-the-art methods have shown the competitive performance in computation speed and the advantage in saliency detection ability of our method.

Key words: adaptive patch, mesh saliency, 3D mesh model, curvature

中图分类号:

TP391.9

汪小东, 梁洪涛, 康凤举, 顾浩. 基于局部区块加权曲率熵的多尺度网格显著性[J]. 系统仿真学报, 2017, 29(9): 1976-1983.

Wang Xiaodong, Liang Hongtao, Kang Fengju, Gu Hao. Multi-scale Mesh Saliency with Local Patch Weighted Curvature Entropy[J]. Journal of System Simulation, 2017, 29(9): 1976-1983.

参考文献

[1] Buschman T J, Miller E K.Top-down versus bottom-up control of attention in the prefrontal and posterior parietal cortices[J]. Science (S0036-8075), 2007, 315(5820): 1860-1862.
[2] Zanto T P, Rubens M T, Thangavel A.Causal role of the prefrontal cortex in top-down modulation of visual processing and working memory[J]. Nature Neuroscience (S1097-6256), 2011, 14(5): 656-661.
[3] Lee C H, Kim Y, Varshney A.Saliency-Guided Lighting[J]. IEICE Transactions on Information & Systems (S1745-1361), 2009, 92(2): 369-373.
[4] Lee C H, Varshney A, Jacobs D W.Mesh saliency[J]. ACM Transactions on Graphics (S0730-0301), 2005, 24(3): 659-666.
[5] Leifman G, Shtrom E, Tal A.Surface regions of interest for viewpoint selection[C]// IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2012: 414-421.
[6] Nouri A, Charrier C, Lézoray O.Multi-scale mesh saliency with local adaptive patches for viewpoint selection[J]. Signal Processing Image Communication (S0923-5965), 2015, 38: 151-166.
[7] Mao Z, Ma L, Zhao M.A Modified Laplacian Smoothing Approach with Mesh Saliency[M]. Berlin, Heidelberg, Germany: Springer, 2006: 105-113.
[8] Li Z, Ma L, Jin X.A new feature-preserving mesh-smoothing algorithm[J]. The Visual Computer (S1432-2315), 2009, 25(2): 139-148.
[9] Chen X, Saparov A, Pang B.Schelling Points on 3D Surface Meshes[J]. ACM Transactions on Graphics (S0730-0301), 2012, 31(4): 13-15.
[10] Wu J, Shen X, Zhu W.Mesh saliency with global rarity[J]. Graphical Models (S1524-0711), 2013, 75(5): 255-264.
[11] Song R, Liu Y, Martin R R.Mesh saliency via spectral processing[J]. ACM Transactions on Graphics (S0730-0301), 2014, 33(1): 57-76.
[12] Limper M, Kuijper A, Fellner D W.Mesh Saliency Analysis via Local Curvature Entropy[C]// Proceedings of the 37th Annual Conference of the European Association for Computer Graphics: Short Papers, France: Eurographics Association, 2016: 13-16.
[13] Tao P, Cao J, Li S.Mesh saliency via ranking unsalient patches in a descriptor space[J]. Computers & Graphics (S0097-8493), 2014, 46: 264-274.
[14] Liu X, Tao P, Cao J.Mesh saliency detection via double absorbing Markov chain in feature space[J]. The Visual Computer (S0272-1716), 2016, 32(9): 1121-1132.
[15] Nouri A, Charrier C, Lézoray O.Mesh saliency with adaptive local patches[C]// SPIE Electronic Imaging, Three-Dimensional Image Processing, Measurement (3DIPM), and Applications. USA: SPIE, 2015, 9393.
[16] Taubin G.Estimating the tensor of curvature of a surface from a polyhedral approximation[C]// International Conference on Computer Vision. USA: IEEE, 1995: 902-907.
[17] Gumhold S.Feature Extraction from Point Clouds[C]// 2001, Proc. 10th International Meshing Roundtable. USA: Sandia National Laboratories, 2001: 293-305.
[18] Neumann L, Sbert M, Gooch B.Viewpoint quality: Measures and applications[C]// Proceedings of the 1st Eurographics Workshop on Computational Aesthetics in Graphics, Visualization and Imaging. France: Eurographics Association, 2005: 185-192.
[19] Giorgi D, Biasotti S, Paraboschi L.Shape Retrieval Contest 2007: Watertight Models Track[J]. SHREC Competition, 2007, 8(7): 5-10.

基于局部区块加权曲率熵的多尺度网格显著性

Multi-scale Mesh Saliency with Local Patch Weighted Curvature Entropy

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

编辑推荐

Metrics

本文评价

[1]	王鑫, 张春燕, 宁晨. 基于Gestalt优化的红外视频时空显著性检测[J]. 系统仿真学报, 2020, 32(6): 1021-1031.
[2]	李晓阳, 万丽莉, 李赫男, 王升辉. 结合显著性检测和图割的RGBD图像共分割算法[J]. 系统仿真学报, 2018, 30(7): 2558-2567.
[3]	王仕民, 叶继华, 王明文, 左家莉, 刘长红. 基于多尺度区域协方差的显著性特征提取方法[J]. 系统仿真学报, 2018, 30(7): 2767-2775.
[4]	王松伟, 黄淑漫, 师丽, 王梦珂. 鸽视顶盖快速显著感知编码模型研究[J]. 系统仿真学报, 2018, 30(11): 4086-4099.
[5]	王仕民, 叶继华, 程柏良, 王明文. 基于多尺度张量空间的改进Itti视觉显著性检测[J]. 系统仿真学报, 2016, 28(9): 2138-2145.
[6]	周强强, 王志成, 赵卫东, 陈宇飞, 王刚. 联合灰色关联度和先验的图像显著性分析[J]. 系统仿真学报, 2015, 27(7): 1511-1519.