基于不确定度评价的Kinect深度图预处理

doi:10.11772/j.issn.1001-9081.2016.02.0541

计算机应用 ›› 2016, Vol. 36 ›› Issue (2): 541-545.DOI: 10.11772/j.issn.1001-9081.2016.02.0541

基于不确定度评价的Kinect深度图预处理

余亚玲, 张华, 刘桂华, 史晋芳

西南科技大学信息工程学院, 四川绵阳 621010

收稿日期:2015-07-01 修回日期:2015-10-05 出版日期:2016-02-10 发布日期:2016-02-03
通讯作者: 余亚玲(1990-),女,四川内江人,硕士研究生,主要研究方向:图像处理、机器视觉。
作者简介:张华(1969-),男,四川绵阳人,教授,博士,主要研究方向:机器学习、机器人;刘桂华(1972-),女,四川绵阳人,教授,博士,主要研究方向:图像处理、机器视觉;史晋芳(1977-),女,四川绵阳人,副教授,硕士,主要研究方向:智能化测控、图像处理。
基金资助:
四川省科技创新苗子工程培育项目(2015024);西南科技大学研究生创新基金资助项目(14ycx103);2014四川省科技支撑计划项目(2014GZ0021);四川省教育厅重点项目(14ZA0090);特殊环境机器人技术四川省重点实验室开放基金资助项目(13zxtk05)。

Kinect depth map preprocessing based on uncertainty evaluation

YU Yaling, ZHANG Hua, LIU Guihua, SHI Jinfang

School of Information Engineering, Southwest University of Science and Technology, Mianyang Sichuan 621010, China

Received:2015-07-01 Revised:2015-10-05 Online:2016-02-10 Published:2016-02-03

摘要/Abstract

摘要： 针对应用在机器人三维(3D)场景感知测量中,Kinect深度图的联合双边滤波(JBF)存在降低原始场景深度信息精确度的制约性问题,提出一种新的预处理算法。首先,通过构建深度图的测量和采样模型,得到深度图的蒙特卡罗不确定度评价模型;其次,依据该模型计算得到深度值估计区间,实现噪声点与非噪声点的判定及滤除;最后,利用估计区间均值完成噪声点的修复。实验结果表明,该算法在噪声滤波的同时保证了非噪声的不变性;非噪声的不变性以及基于估计均值的噪声修复使原始深度梯度具有不变性;与联合彩色深度图的双边滤波相比,预处理结果图物体边缘轮廓清晰不变且其均方误差降低了15.25%~28.79%。因此,该预处理算法达到了提高三维场景深度信息精确度的目的。

关键词: 深度图, 蒙特卡罗模型, 不确定度评价, 噪声滤波, 深度复原

Abstract: A new Kinect depth map pretreatment algorithm was presented for the lower accuracy problem compared with the original depth information in the field of three-Dimensional (3D) scene measurement for robot's perception. Firstly, a measuring and sampling model of the depth map was developed to realize the Monte Carlo uncertainty evaluation model. Secondly, the depth value intervals were calculated to judge and filter the noise pixels. Finally, noise points were repaired with mean-value of the estimation intervals. The experimental results show that the algorithm can effectively suppress and repair the noise pixels while keeping the depth gradient and values of non-noise pixels. The Mean Square Error (MSE) of depth map after preprocessing is reduced by 15.25% to 28.79%, and the object profiles remain unchanged compared with the JBF (Joint Bilateral Filtering) based on color and depth map. Therefore, it achieves the purpose of improving the depth information accuracy in 3D scenes.

Key words: depth map, Monte Carlo model, uncertainty evaluation, noise filtering, depth recovery

中图分类号:

余亚玲, 张华, 刘桂华, 史晋芳. 基于不确定度评价的Kinect深度图预处理[J]. 计算机应用, 2016, 36(2): 541-545.

YU Yaling, ZHANG Hua, LIU Guihua, SHI Jinfang. Kinect depth map preprocessing based on uncertainty evaluation[J]. Journal of Computer Applications, 2016, 36(2): 541-545.

参考文献

[1] 辛菁,苟蛟龙,马晓敏,等.基于Kinect的移动机器人大视角3维V-SLAM[J].机器人,2014,36(5):560-568. (XIN Q, GOU J L, MA X M, et al. A large viewing angle 3-dimensional V-SLAM algorithm with a Kinect-based mobile robot system[J]. Robot, 2014, 36(5): 560-568.)
[2] ZHAO Z S, FENG X, TENG S H, et al. Multiscale point correspondence using feature distribution and frequency domain alignment[J]. Mathematical Problems in Engineering, 2012, 2012(3): 295-308.
[3] 朱笑笑,曹其新,杨扬,等. 一种改进的Kinect Fusion三维重构算法[J].机器人,2014,36(2):129-136. (ZHU X X, CHAO Q X, YANG Y, et al. An improved Kinect fusion 3D reconstruction algorithm[J]. Robot, 2014, 36(2): 129-136.)
[4] ZHAO Z-S, FENG X, WEI F, et.al. Learning representative features for robot topological localization[J]. International Journal of Advanced Robotic Systems, 2013, 10: 215.
[5] YANG Q-Q, WANG L-H, LI D-X, et.al. Hierarchical joint bilateral filtering for depth post-processing[C]//ICIG2011: Proceedings of the Sixth International Conference on Image and Graphics. Washington, DC: IEEE Computer Society, 2011: 129-134.
[6] CHEN L, LIN H, LI S. Depth image enhancement for Kinect using region growing and bilateral filter[C]//ICPR 2012: Proceedings of the 2012 International Conference on Pattern Recognition. Piscataway: IEEE, 2012: 3070-3073.
[7] QIAO T-Z, DAI S-L. Depth data filtering for real-time head pose estimation with Kinect[C]//CISP 2013: Proceedings of the Sixth Congress on Image and Signal Processing. Piscataway: IEEE, 2013: 953-958.
[8] SHEN Y, LI J, LU C. Depth map enhancement method based on joint bilateral filter[C]//CISP 2014: Proceedings of the 7th Congress on Image and Signal Processing. Piscataway: IEEE, 2014: 153-158.
[9] FENG C. DAI S L. Adaptive depth map enhancement based on joint bilateral filter[C]//CGNCC 2014: Proceedings of the 2014 Conference on Guidance Navigation and Control. Piscataway: IEEE, 2014: 2568-2571.
[10] 赵玉华,袁峰,丁振良,等.基于合作目标的姿态测量系统建模及精度的蒙特卡罗估计[J].仪器仪表学报,2010,31(8):1873-1877. (ZHAO Y H, YUAN F, DING Z L, et al. Modeling of the attitude measurement system based on cooperation target and its accuracy estimation with Monte-Carlo simulation[J]. Chinese Journal of Scientific Instrument, 2010, 31(8): 1873-1877.)
[11] 陈杰春,张恒,赵丽萍.基于蒙特卡罗方法的边界检测不确定度估计[J].东北电力大学学报,2012,32(3):75-78. (CHENG J C, ZHANG H, ZHAO L P. Boundary detection uncertainty estimation based on the Monte Carlo method[J]. Journal of Northeast Dianli University, 2012, 32(3): 75-78)
[12] BATTISTA L, SCHENA E, SCHIAVONE G, et al. Calibration and uncertainty evaluation using Monte Carlo method of a simple 2D sound localization system[J]. Sensors Journal, 2013, 13(9): 3312-3318.
[13] 韩连福,付长凤,王军,等.基于QMC的齿轮测量中心测量不确定度评定方法[J].光学仪器,2015,37(2):111-115. (HAN L F, FU C F, WANG J, et al. Evaluation on uncertainty of gear center measurement based on quasi Monte-Carlo method[J]. Optical Instruments, 2015, 37(2): 111-115.)
[14] Prime Sense Ltd, GARCIA J, ZALEVSKY Z. Range mapping using speckle decorrelation: U.S. 7433024B2 [P]. 2008-10-07.
[15] 国家质量技术监督局计量司.测量不确定度评定与表示指南[M].北京:中国计量出版社,2005:22-28. (The State Bureau of Quality and Technical Supervision Measurement Department. Evaluation and expression of uncertainty measurement in guide[M]. Beijing: Chinese Metrology Press, 2005:22-28.)
[16] 陈怀艳,曹芸,韩洁.基于蒙特卡罗法的测量不确定度评定[J].电子测量与仪器学报,2011,25(4):301-307. (CHENG H Y, CHAO Y, HAN J. Evaluation of uncertainty in measurement based on a Monte Carlo method[J]. Journal of Electronic Measurement and Instrument, 2011, 25(4): 301-307.)
[17] YANG J Y, YE X C, LI K, et al. Color-guided depth recovery from RGB-D data using an adaptive autoregressive model[J]. IEEE Transactions on Image Processing, 2014, 23(8): 3443-3458.
[18] Middlebury datasets [DS/OL]. [2015-01-12]. http://vision.middlebury.edu/stereo/data/.

基于不确定度评价的Kinect深度图预处理

Kinect depth map preprocessing based on uncertainty evaluation

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

[1]	张豪, 张强, 邵思羽, 丁海斌. 深度学习在单图像三维模型重建的应用[J]. 计算机应用, 2020, 40(8): 2351-2357.
[2]	喻露, 胡剑锋, 姚磊岳. 基于人体骨架的非标准深蹲姿势检测方法[J]. 计算机应用, 2019, 39(5): 1448-1452.
[3]	曹海燕, 冯桂, 韩雪, 方定邦, 黄鑫达. 基于深度图的3D-HEVC鲁棒视频水印算法[J]. 计算机应用, 2019, 39(3): 869-873.
[4]	梁中豪, 彭德巍, 金彦旭, 郭梁. 基于交通场景区域增强的单幅图像去雾方法[J]. 计算机应用, 2018, 38(5): 1420-1426.
[5]	陈真真, 卿粼波, 何小海, 汪芸. 基于非均匀量化的小波域分布式深度图视频编码[J]. 计算机应用, 2016, 36(4): 1080-1084.
[6]	徐海宁, 陈恩庆, 梁成武. 三维动作识别时空特征提取方法[J]. 计算机应用, 2016, 36(2): 568-573.
[7]	陆中秋, 侯振杰, 陈宸, 梁久祯. 基于深度图像与骨骼数据的行为识别[J]. 计算机应用, 2016, 36(11): 2979-2984.
[8]	尚常军, 丁瑞. 基于曲率局部二值模式的深度图像手势特征提取[J]. 计算机应用, 2016, 36(10): 2885-2889.
[9]	段峰峰, 王永滨, 杨丽芳, 潘淑静. 基于主成分分析方向深度梯度直方图的立体视觉深度图特征提取[J]. 计算机应用, 2016, 36(1): 222-226.
[10]	杨全彭进业. 基于深度图像信息的手语识别算法[J]. 计算机应用, 2013, 33(10): 2882-2885.
[11]	吴琳金志刚赵安安周圆. 基于depth-map和分布式视频编码的多视点视频传输方法[J]. 计算机应用, 2012, 32(09): 2441-2444.
[12]	罗桂娥徐运彬. 基于Quaternion-Gabor小波运动估计的深度图获取技术[J]. 计算机应用, 2012, 32(01): 238-240.
[13]	邓智玭贾克斌陈锐霖伏长虹萧允治. 三维视频编码技术的发展与挑战[J]. 计算机应用, 2011, 31(09): 2453-2456.
[14]	刘然朱庆生易琳许小艳. 基于图像重投影的视图合成[J]. 计算机应用, 2010, 30(4): 898-901.