作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (20): 183-185. doi: 10.3969/j.issn.1000-3428.2011.20.063

• 人工智能及识别技术 • 上一篇    下一篇

计算机视觉中强鲁棒性的遗传一致性估计

姚 达 a,b,周 军 a,b,薛 质 a   

  1. (上海交通大学 a. 图像通信与信息处理研究所;b. 上海市数字媒体处理与传输重点实验室,上海 200240)
  • 收稿日期:2011-04-27 出版日期:2011-10-20 发布日期:2011-10-20
  • 作者简介:姚 达(1987-),男,硕士研究生,主研方向:计算机视觉;周 军,副教授;薛 质,教授、博士生导师
  • 基金资助:
    国家“863”计划基金资助项目(2009AA01A3336, 2008B AH28B04);下一代互联网示范工程(CNGI)基金资助项目(CNGI-09- 01-02);上海市科委基金资助项目(10511501102)

Genetic Consistency Estimation for Strong Robustness in Computer Vision

YAO Da a,b, ZHOU Jun a,b, XUE Zhi a   

  1. (a. Institute of Image Communication and Information Processing; b. Shanghai Key Laboratory of Digital Media Processing and Transmissions, Shanghai Jiaotong University, Shanghai 200240, China)
  • Received:2011-04-27 Online:2011-10-20 Published:2011-10-20

摘要: 用于估计计算机视觉模型的传统鲁棒算法均存在估计精度和稳定性不高等问题。为此,结合遗传算法的全局最优性及几何模型估计的特殊性,提出一种强鲁棒性的遗传一致性估计算法,以估计各种误差和错误概率下的计算机视觉几何模型。仿真实验结果表明,相比于RANSAC、MAPSAC、MLESAC等鲁棒算法,该算法在估计精度和鲁棒性方面性能更优。

关键词: 遗传一致性估计器, 单应矩阵, 基础矩阵, 随机抽样一致性

Abstract: Traditional robust algorithms for estimating models in computer vision are inevitably affected by errors and outliers in the provided data, which makes estimation precision and stability low. This paper presents a Genetic Consistency Estimator(GCE) with strong robustness, combining global optimality of genetic algorithm and specialty of model estimation, to estimate geometric models in computer vision in a variety of errors and outliers probabilities. Experimental results prove GCE has greater precision and robustness compared with RANSAC, MAPSAC, MLESAC and other robust algorithms.

Key words: Genetic Consistency Estimator(GCE), homography matrix, fundamental matrix, Random Sampling Consistency(RANSAC)

中图分类号: