应用特征估计的距离图像多尺度滤波

冯肖维; 何永义; 方明伦; 张军高

doi:doi:10.3788/ope.20111905.1118

光学精密工程, 2011, 19 (5): 1118, 网络出版: 2011-06-15

应用特征估计的距离图像多尺度滤波

Multi-scale smoothing of noisy range image using feature estimation

论文大纲

冯肖维 ^*何永义方明伦张军高

作者单位

上海大学 CIMS及机器人研究所，上海 200072

自适应滤波特征估计尺度空间无嗅卡尔曼滤波器激光测距仪 adaptive smoothing feature estimation scale space UKF laser rangefinder

摘要

为了提取含有噪声的激光扫描距离图像中的特征，提出了一种多尺度自适应滤波方法。该方法由特征估计和多尺度滤波两部分组成。利用无嗅卡尔曼滤波器构建自适应特征估计器，估计扫描点间的几何拓扑关系，并用估计过程中所获得的Mahalanobis距离构建扩散滤波核，对原始距离像进行多尺度滤波处理。为了能够仅依靠单一模型实现对环境中不同几何元素的有效估计，介绍了一种根据距离像局部特性进行自适应调整的曲线估计模型。试验结果表明，在噪声方差为2.25×10-4 m2时，经自适应滤波处理后的图像的最高峰值信噪比增益达10.55 dB，均方误差减小58.24%。与基于固定模型的滤波相比，本文所述自适应模型滤波法能够使特征提取的正确率提高10%，而时间消耗减少55%。

Abstract

An adaptive smoothing algorithm within a scale space framework is proposed to extract the features of noisy range image of a laser rangefinder. The method is composed of feature estimation and multi-scale smoothing. A Unscented Kalman Filter(UKF) is used to construct an adaptive feature estimator to estimate the topology of points,then the Mahalanobis distances obtained by estimation are taken to calculate the smoothing mask. In order to provide a more efficient estimation of different major geometries by a single model, an adaptive curve model which varies depending on the local nature of range image is employed. Experimental results indicate that the Peak Signal-to-Noise Ratio (PSNR) gain of the adaptive algorithm has reached 10.55 dB and the Mean Square Error(MSE) has been reduced by 58.24% when the noise variance is 2.25×10-4 m2. The proposed method with a adaptive model can improve the correctness of feature extraction by 10% comparing to the smoothing algorithm with a fixed neighborhood model, while the time consuming is reduced by about 55%.

参考文献

[1] BAGLIVO L, BELLOMO N, MIORI G, et al.. An object localization and reaching method for wheeled mobile robots using laser rangefinder［C］. Proceedings of 4th International IEEE Conference on Intelligent Systems, 2008:5-11.

[2] MISONO Y, GOTO Y, TARUTOKO Y, et al.. Development of laser rangefinder-based SLAM algorithm for mobile robot navigation ［C］. IEEE Conferences SICE'07, 2007:392-396.

[3] 赵翠莲, 范志坚, 孙亮, 等. 体素连通性的深度图像拉伸特征提取［J］. 光学精密工程, 2009,17(4):930-936.

ZHAO C L, FAN ZH J, SUN L, et al.. Extrusion feature extraction of range image by voxel directed connectivity ［J］. Opt. Precision Eng., 2009,17(4):930-936. (in Chinese)

[4] 邓超, 张涛, 姚清华. 应用小波神经网络处理CCD图像噪声［J］. 光学精密工程, 2008,26(2):345-351.

DENG CH, ZHAN G T, YAO Q H. Application of wavelet neural network in removing CCD noise of digital images ［J］. Opt. Precision Eng., 2008, 26(2):345-351. (in Chinese)

[5] 王明佳, 张旭光, 韩广良, 等. 自适应权值滤波消除图像椒盐噪声的方法［J］. 光学精密工程, 2007, 15(5):779-783.

WANG M J, ZHANG X G, HAN G L, et al.. Elimination of impulse noise by auto-adapted weight filter［J］. Opt. Precision Eng., 2007,15(5):779-783. (in Chinese)

[6] MADHAVAN R, DURRANT-WHYTE H F. Natural landmark-based autonomous vehicle navigation ［J］. Robotics and Autonomous Systems, 2004,46:79-95.

[7] TANG F, ADAMS M, IBANEZ-GUZMAN J, et al.. Pose invariant, fobust feature extraction from range data with a modified scale space approach ［C］. Proceedings of the International Conference on Robotics and Automation, 2004:3173- 3179.

[8] ZHANG S, XIE L, ADAMS M, et al.. Geometrical feature extraction using 2D range scanners ［C］. Proceedings of the 5th International Conference on Control and Automation, 2003:901- 905.

[9] FENG X W, HE Y Y, HUANG W X, et al.. Natural landmarks extraction method from range image for mobile robot ［C］. 2nd International Congress on Image and Signal Processing, 2009:1-5.

[10] HUMMEL R A, KIMIA B, ZUCKER S W. Deblurring Gaussian blur［J］. Computer Vision, Graphics, and Image Processing, 1987,38:66-80.

[11] PERONA P, MALIK J. Scale-space and edge detection using anisotropic diffusion ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990,12(7):629-639.

[12] SAINT-MARC P, CHEN J S, MEDIONI G. Adaptive smoothing: a general tool for early vision ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991(64):514-529.

[13] JULIER S J, UHLMANN J K. Unscented filtering and nonlinear estimation［J］. Proceedings of the IEEE, 2004:401-422.

[14] GONZALEZ R C, WOODS R E. Digital Image Processing［M］. 2nd ed.Beijing: Electronic and Industrial Press, 2002.

冯肖维, 何永义, 方明伦, 张军高. 应用特征估计的距离图像多尺度滤波[J]. 光学精密工程, 2011, 19(5): 1118. FENG Xiao-wei, HE Yong-yi, FANG Ming-lun, ZHANG Jun-gao. Multi-scale smoothing of noisy range image using feature estimation[J]. Optics and Precision Engineering, 2011, 19(5): 1118.

应用特征估计的距离图像多尺度滤波

关于本站 Cookie 的使用提示

全站搜索

应用特征估计的距离图像多尺度滤波

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索