A Novel Monocular Visual Odometer Method Based on Kinect and Improved SURF Algorithm

Li Jun Zhang; Fei Chen

doi:10.4028/www.scientific.net/AMM.556-562.4081

Paper Titles

A Robust Operator Functional State Fuzzy Modeling Approach Based on EEG Data
p.4065

RLS Parameter Identification and Emulate Based on DSP Builder of the Rapid Realization
p.4069

Statistical Characters Analysis of LF Atmospheric Noise
p.4073

Research on Horror Video Recognition Algorithms
p.4077

A Novel Monocular Visual Odometer Method Based on Kinect and Improved SURF Algorithm
p.4081

Simulation of Removal of MTBE in Groundwater by Biosparging
p.4085

A Low-Cost 3D Local Mapping and Localization Method
p.4089

Well-Posedness for Parametric Generalized Strong Vector Quasi-Equilibrium Problem
p.4093

Generalized Exponential Entropy on Intuitionistic Fuzzy Sets
p.4097

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 556-562A Novel Monocular Visual Odometer Method Based on...

A Novel Monocular Visual Odometer Method Based on Kinect and Improved SURF Algorithm

Abstract:

The paper proposes a novel monocular visual odometer method based on Kinect sensor made by Microsoft and the improved SURF algorithm. Firstly the Kinect sensor capture color images and depth images of the surrounding environment, then we use the improved SURF algorithm to extract feature points of the color images and match for them. At last, map what we get with the depth image and estimate the path information of the robot by doing 3D reconstruction and using the the least square mean value theorem. Experimental results show that by using this new method, the average matching accuracy reaches 92.6%. And even in a dynamic environment, it shows good robustness, so it comes down to the conclusion that the combination of the Kinect sensor and the improved SURF algorithm applied to visual odometer is a simple and effective method.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 556-562)

Pages:

4081-4084

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.556-562.4081

Citation:

Cite this paper

Online since:

May 2014

Authors:

Li Jun Zhang*, Fei Chen

Keywords:

Improved SURF, KINECT, Least Square Mean Value Theorem, Visual Odometer

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Nister D, Naroditsky O, Bergen J. Visual odometry[C]. Proc IEEE Computer Society Conferrence on Computer Vision and Pattern Recognition, 2004, 1: 652-659.

DOI: 10.1109/cvpr.2004.1315094

Google Scholar

[2] Pen Bo, Zhou Wen-hui, Liu Ji-lin. Harris Corner Detection-based Stereo Visual Odometry[J]. ACTA ARMAM ENTARII, 2007, 28(12): 1498-1502.

Google Scholar

[3] Wang Liang-fen. Detection Algorithm of Moving Objects Based on SIFT Features Matching and Dynamic Updating Background Model[J]. Computer Applications and Software, 2010, 27(2): 267-270.

Google Scholar

[4] Somayajula S, Joshi A A, Leahy R M. Mutual information based non-rigidmouse registration using a scale-space approach [C]Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008. 5th IEEE International Symposium on, 2008: 1147 - 1150.

DOI: 10.1109/isbi.2008.4541204

Google Scholar

[5] Herbert Bay, Andreas Ess , Tinne Tuytelaars, Luc Van Gool,. Speeded-Up Robust Features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.

DOI: 10.1016/j.cviu.2007.09.014

Google Scholar

[6] KURT KONOLIGE, PATRICK MIHELICH. Technical description of Kinect calibration [EB/OL] (2011)[2012-8-10].

Google Scholar