A non-parametric depth modification model for registration between color and depth images

被引:0
|
作者
Li Peng
Yanduo Zhang
Huabing Zhou
Junjun Jiang
Jiayi Ma
机构
[1] Huazhong University of Science and Technology,Hubei Key Laboratory of Intelligent Robot
[2] Wuhan Institute of Technology,School of Computer Science and Technology
[3] Hubei Radio and TV University,Electronic Information School
[4] Harbin Institute of Technology,undefined
[5] Wuhan University,undefined
来源
Multidimensional Systems and Signal Processing | 2019年 / 30卷
关键词
Depth accuracy; Correspondence; Kinect sensor; Non-parametric model;
D O I
暂无
中图分类号
学科分类号
摘要
Despite its most popularity among all depth cameras in the computer vision applications, the Microsoft Kinect sensor suffers from low depth accuracy. In this work we propose a novel non-parametric depth modification model to improve the depth accuracy of the Kinect sensor by iteratively registering depth images and color images. In particular, we first establish a coarse correspondence based on the feature descriptor of the canny edge at each iteration, and estimate the fine correspondence using an L2E\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$L_2E$$\end{document} algorithm. We utilize the non-parametric Gaussian mixture model to replace the Gaussian single model and build the regularization term to constrain the correlations between functions. Then, based on the correspondence results, the depth data are corrected and optimized. Extensive experiments have been performed to verify the effectiveness of the proposed approach, and the results have demonstrated that our method is able to greatly enhance the depth accuracy of the Kinect sensor compared with baseline methods.
引用
收藏
页码:1129 / 1148
页数:19
相关论文
共 50 条
  • [21] CALIBRATION BETWEEN DEPTH AND COLOR SENSORS FOR COMMODITY DEPTH CAMERAS
    Zhang, Cha
    Zhang, Zhengyou
    2011 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2011,
  • [22] Unifying Framework for Decomposition Models of Parametric and Non-parametric Image Registration
    Ibrahim, Mazlinda
    Chen, Ke
    PROCEEDINGS OF THE 24TH NATIONAL SYMPOSIUM ON MATHEMATICAL SCIENCES (SKSM24): MATHEMATICAL SCIENCES EXPLORATION FOR THE UNIVERSAL PRESERVATION, 2017, 1870
  • [23] Non-Parametric Learning-based Depth Estimation from a Single Image in the Fourier Domain
    Xu, Huihui
    Jiang, Mingyan
    PROCEEDINGS OF 2018 THE 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND ARTIFICIAL INTELLIGENCE (CSAI 2018) / 2018 THE 10TH INTERNATIONAL CONFERENCE ON INFORMATION AND MULTIMEDIA TECHNOLOGY (ICIMT 2018), 2018, : 334 - 338
  • [24] A new depth image quality metric using a pair of color and depth images
    Thanh-Ha Le
    Jung, Seung-Won
    Won, Chee Sun
    MULTIMEDIA TOOLS AND APPLICATIONS, 2017, 76 (09) : 11285 - 11303
  • [25] Networks for Joint Affine and Non-parametric Image Registration
    Shen, Zhengyang
    Han, Xu
    Xu, Zhenlin
    Niethammer, Marc
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 4219 - 4228
  • [26] A new depth image quality metric using a pair of color and depth images
    Thanh-Ha Le
    Seung-Won Jung
    Chee Sun Won
    Multimedia Tools and Applications, 2017, 76 : 11285 - 11303
  • [27] Depth Estimation from Multi-scale SLIC Superpixels Using Non-parametric Learning
    Jiang, Yifeng
    Zhu, Yuesheng
    Qing, Yin
    Yang, Fan
    NINTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2017), 2017, 10420
  • [28] Diffeomorphic demons: Efficient non-parametric image registration
    Vercauteren, Tom
    Pennec, Xavier
    Perchant, Aymeric
    Ayache, Nicholas
    NEUROIMAGE, 2009, 45 (01) : S61 - S72
  • [29] Non-parametric diffeomorphic image registration with the demons algorithm
    Vereauteren, Tom
    Pennec, Xavier
    Perchant, Aymeric
    Ayache, Nicholas
    MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION- MICCAI 2007, PT 2, PROCEEDINGS, 2007, 4792 : 319 - +
  • [30] Foreground Segmentation by Combining Color and Depth Images
    Ottonelli, Simona
    Spagnolo, Paolo
    Mazzeo, Pier Luigi
    Leo, Marco
    PATTERN RECOGNITION AND IMAGE ANALYSIS, IBPRIA 2013, 2013, 7887 : 699 - 706