期刊文献+

基于支持向量回归的灰度图像三维形状重构 被引量:1

Shape from Shading Based on Support Vector Regression Algorithm
下载PDF
导出
摘要 为实现未知光源的灰度图像高效重构形状,提出一种基于支持向量回归机和粒子群优化算法相结合的灰度图像重构三维表面形状的方法。通过研究和分析灰度重构形状(SFS)问题,基于支持向量回归机理论,构建了物体表面形状与其灰度图像间的非线性映射模型。对未知光照方向的实际图像进行光源方向估计,生成对应光照方向的训练样本以提高任意光照方向下的图像的形状恢复精度。为克服支持向量回归机中各参数选取无依据的不足,引入粒子群优化算法主动对各参数进行飞行寻优,使得回归模型为最优,以提高形状重构精度。最后,通过实例分析验证了所提方法的可行性及有效性。 In order to realize the shape from shading(SFS) under unknown light source parameters of single grayscale image,an efficient SFS method was proposed based on support vector regression(SVR) and particle swarm optimization(PSO) algorithm.Based on the SVR theory,a nonlinear mapping model was constructed between the grayscale image and its 3-D surface by researching into the SFS problem.The light source of the tested actual image should be estimated to generate the training samples corresponding to the light direction.It was important to select the proper SVR parameters for improvement on 3-D reconstruction precision,and the PSO algorithm was introduced.Finally,the case study had verified the feasibility and effectiveness of the proposed SFS method.
出处 《农业机械学报》 EI CAS CSCD 北大核心 2012年第2期216-220,共5页 Transactions of the Chinese Society for Agricultural Machinery
基金 国家青年科学基金资助项目(51005204) 内蒙古工业大学科学研究重点资助项目(ZD201110)
关键词 灰度重构形状 未知光源 支持向量回归 粒子群优化算法 Shape from shading Unknown light source Support vector regression Particle swarm optimization
  • 相关文献

参考文献17

  • 1Horn B K P. Height and gradient from shading[ J]. International Journal of Computer Vision, 1990,5 ( 1 ) :37 - 75.
  • 2赵辉煌,周德俭,黄春跃.SMT片式元件焊点三维质量信息提取技术[J].计算机集成制造系统,2010,16(8):1714-1719. 被引量:1
  • 3Ikeuchi K, Horn B K P. Numerical shape from shading and occluding boundaries [ J ]. Artificial Intelligence, 1981,17 (1 3) :141 - 184.
  • 4Pentland A P. Local shading analysis [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984,6 (2) :170 187.
  • 5赵辉煌,周德俭,黄春跃.一种改进的灰度重构形状光照模型及其实现[J].计算机集成制造系统,2009,15(10):1951-1955. 被引量:4
  • 6Song Limei, Qu Xinghua,Ye Shenghua. Improved SFS 3D measurement based on BP neural network[ Jl. Image and Vision Computing ,2007,25 ( 5 ) :614 - 622.
  • 7Jiang Tianzi, Liu Bing, Lu Yingli, et al. A neural network approach to shape from shading [ J]. International Journal of Computer Mathematics, 2003, 80(4) :433 -439.
  • 8尹爱军,秦树人,周传德.基于支持矢量机的从明暗恢复形状方法[J].机械工程学报,2006,42(7):186-191. 被引量:7
  • 9刘路,王太勇,蒋永翔,胡淼,宁倩.基于超球面支持向量机的刀具磨损状态识别[J].农业机械学报,2011,42(1):218-222. 被引量:14
  • 10Nello C, John S T. An introduction to support vector machines and other kernel-based learning methods [ M ].Cambridge University Press,2000.

二级参考文献89

共引文献81

同被引文献13

  • 1Farrell PJ, Ould-Haye M. Robust regression with infinite moving average errors [M] //Dependence in Probability and Statistics. Berlin: Springer Verlag, 2010: 143-157.
  • 2Freitas FD, De Souza AF, De Almeida AR. Prediction-based portfolio optimization model using neural networks [J]. Neu- rocomputing, 2009, 72 (10-12):2155-2170.
  • 3Yu L, Wang SY, Lai KK. Neural network-based mean- variance-skewness model for portfolio selection [J]. Computers Operations Research, 2008, 35 (1).. 34-46.
  • 4Pourmousavi Kani SA, Aredhali MM. Veryshort-term wind speed prediction.. A new artificial neural network-Markov chain model [J]. Energy Conversion and Management, 2011, 52 (I): 738-745.
  • 5GU JR, ZHU MC, JING LGY. Housing price fore'casting based on genetic algorithm and support vector machine [J]. Expert Systems withApplications, 2011, 38 (4), 3383-3386.
  • 6llhan Aydin, Mehmet Karakose, Ethan AI A multi-objtive ar- tifidal immune algorithm for parameter optimization in support vector machine [J]. Applied Soft Computing, 2011, 11 (1): 120-129.
  • 7陈其松,陈孝威,张欣,吴茂念.优化SVM在锅炉负荷预测中的应用[J].电子科技大学学报,2010,39(2):316-320. 被引量:2
  • 8廖伟智,孙林夫,杜平安.面向服务的汽车配件需求预测模型[J].计算机集成制造系统,2010,16(8):1778-1782. 被引量:10
  • 9李震,洪添胜,Ning Wang,洪涯,文韬,李加念.基于神经网络预测的无线传感器网络田间射频信号路径损耗[J].农业工程学报,2010,26(12):178-181. 被引量:11
  • 10张晓南,刘安心,刘斌,张宏梅,青星.基于优化PSO-SVM模型的软件可靠性预测[J].计算机应用,2011,31(7):1762-1764. 被引量:9

引证文献1

二级引证文献7

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部