光学技术, 2023, 49 (6): 736, 网络出版: 2023-12-05  

基于主成分分析重建图像的互信息视觉伺服

Mutual information visual servo of reconstructed image based on principal component analysis
作者单位
1 北京理工大学 光电学院 精密光电测试仪器及技术北京市重点实验室, 北京 100081
2 长春理工大学 光电工程学院, 长春 130022
3 湖南师范大学 工程与设计学院, 长沙 410082
摘要
基于互信息的视觉伺服使用图像全局信息来实现伺服控制, 避免了对传统几何特征的提取、匹配和跟踪, 并且对光照变化、部分遮挡具有鲁棒性, 但由于其任务函数的高非线性, 该方法具有收敛域较小的缺点。提出了基于主成分分析(PCA)重建图像的互信息视觉伺服方法, 有效降低了任务函数的非线性。通过实验比较了基于PCA重建图像的互信息视觉伺服和基于原始图像的互信息视觉伺服收敛域大小及收敛速度, 并考虑了PCA中主成分个数的影响, 结果表明基于PCA重建图像的互信息视觉伺服有效地扩大了互信息视觉伺服的收敛域, 且具有更快的收敛速度。
Abstract
The mutual information based visual servo uses the global information of the image to realize servo control, which avoids the extraction, matching and tracking of traditional geometric features, and is robust to light changes and partial occlusion. However, due to the high nonlinearity of its cost function, this method has the disadvantage of small convergence region. A mutual information visual servo method based on principal component analysis (PCA) for dimension-reduced image reconstruction is proposed, which effectively decreases the nonlinearity of the cost function. The convergence region size and convergence speed of mutual information visual servo based on PCA reconstructed image and original image were compared through experiments, and the influence of the number of principal components in PCA is considered. The results show that the mutual information visual servo based on PCA reconstruction image effectively expands the convergence region of mutual information visual servo and has faster convergence speed.
参考文献

[1] 徐德.单目视觉伺服研究综述[J].自动化学报,2018,44(10):1729-1746.

[2] Dame A, Marchand E. Improving mutual information-based visual servoing[C]∥International Conference on Robotics and Automation. Anchorage,USA:IEEE,2010:5531-5536.

[3] Collewet C, Marchand E. Photometric visual servoing[J]. IEEE Transactions on Robotics,2011,27(4):828-834.

[4] Collewet C, Marchand E, Chaumette F. Visual servoing set free from image processing[C]∥International Conference on Robotics and Automation. Pasadena,USA:IEEE,2008 81-86.

[5] Kosecka J, Zhou Liang, Barber P, et al. Qualitative image based localization in indoors environments[C]∥Computer Society Conference on Computer Vision and Pattern Recognition. Madison, USA: IEEE,2003:II-II.

[6] Dame A, Marchand E. Entropy based visual servoing[C]∥ International Conference on Robotics and Automation. Kobe,Japan:IEEE,2009:707-713.

[7] Bateux Q, Marchand E. Histograms-based visual servoing[J]. IEEE Robotics and Automation Letters,2017,2(1):80-87.

[8] Dame A, Marchand E. Mutual information-based visual servoing [J]. IEEE Transactions on Robotics,2011,27(5):958-969.

[9] Bista S R, Giordano P R, Chaumette F. Appearance-based indoor navigation by IBVS using line segments[J]. IEEE Robotics and Automation Letters,2016,1(1):423-430.

[10] Dame A, Marchand E. Using mutual information for appearance-based visual path following[J]. Robotics and Autonomous Systems, 2013,61(3):259-270.

[11] Marchand E. Subspace-based direct visual servoing[J]. IEEE Robotics and Automation Letters,2019,4(3):2699-2706.

[12] 陶俊伟, 姜威. 改进的基于二维主分量分析的掌纹识别[J].光学技术,2007,184(02):283-286.

[13] 王一帆, 唐正宁. 基于PCA和ICA的多光谱数据降维方法[J].光学技术,2014,40(02):180-183.

[14] 赵蔷. 主成分分析方法综述[J].软件工程,2016,19(06):1-3.

[15] 王育坚, 吴明明, 高倩. 基于保局PCA的三维点云配准算法[J].光学技术,2018,44(05):562-568.

[16] 范雪莉, 冯海泓, 原猛. 基于互信息的主成分分析特征选择算法[J]. 控制与决策,2013,28(6):5.

[17] 李晓杰. 基于互信息的无人机视觉导航技术研究[D]. 北京理工大学, 2021.

[18] Malis E. Improving vision-based control using efficient second-order minimization techniques[C]∥International Conference on Robotics and Automation. New Orleans,USA:IEEE,2004:1843-1848.

徐婷婷, 胡摇, 郝群, 沈添天. 基于主成分分析重建图像的互信息视觉伺服[J]. 光学技术, 2023, 49(6): 736. XU Tingting, HU Yao, HAO Qun, SHEN Tiantian. Mutual information visual servo of reconstructed image based on principal component analysis[J]. Optical Technique, 2023, 49(6): 736.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!