Camera Motion Estimation based on Phase Correlation

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    In this paper, we introduce a new style for a relative localization estimation and trajectory determination of a camera sensor based on a vision in GPS-denied environments. The input to the system is video film taken from a camera placed on the vehicle as forward facing camera. The output of the system is a trajectory (path) of camera movement .The proposed framework consists of many main steps, the first one extracts the FFT of two consecutive frames of video. The next step is to find the entry-wise product of frequency domain of frames. The third step is extracting the FFT inverse of entry-wise product. Next, the system finds the location of a maximum peak that represents the translation motion between two frames of video. The proposed system is faster than traditional methods that depend on spatial features and system have done without any external information of camera calibration.

     

     


  • Keywords


    Pose estimation, phase correlation, visual odometry , camera motion, trajectory extraction.

  • References


      [1] Gastón Araguás and etl., “Chapter 2 Monocular Pose Estimation for an Unmanned Aerial Vehicle Using Spectral Features”, book, Springer International Publishing Switzerland, 2017, doi: 10.1007/978-3-319-44735-3_2.

      [2] Lasitha Piyathilaka and etl., “An Experimental Study on Using Visual Odometry for Short-run Self Localization of Field Robot”, IEEE, 2010 Fifth International Conference on Information and Automation for Sustainability, pp. 150-155, 2010.

      [3] D. KnuthMerwan Birem and etl., “Visual odometry based on the Fourier transform using a monocular ground-facing camera”, Springer-Verlag GmbH Germany , J Real-Time Image Proc, SPECIAL ISSUE PAPER, 2017, doi: 10.1007/s11554-017-0706-3 .

      [4] Fan YANG, Linlin WEI, Zhiwei ZHANG and Hongmei TANG, “Image Mosaic Based on Phase Correlation and Harris Operator”, Journal of Computational Information Systems vol. 8, no. 6 , 2012. IEEE Trans. Antennas Propagat., doi:10.4316/ieee.1959.3422.

      [5] Scaramuzza D. and Fraundorfer F. “Visual Odometry: Part I - The First 30 Years and Fundamentals”. IEEE Robotics and Automation Magazine, vol. 18, no. 4.2011.

      [6] Fraundorfer F. and Scaramuzza D. “Visual Odometry: Part II - Matching, Robustness, and Applications”. IEEE Robotics and Automation Magazine, vol. 19, no.2,2012.

      [7] Nolang Fanani and etl., “Predictive monocular odometry (PMO): What is possible without RANSAC and multiframe bundle adjustment?”, Image and Vision Computing (2017), doi: 10.1016/j.imavis.2017.08.002.

      [8] Dr. I sra'a Hadi1 and Hikmat Z. Neima, “Robust Video Shot Importance Measurement Based on SIFT and Optical Flow”, International Journal of Pure and Applied Mathematics, vol. 119, no. 15. 2018.

      [9] HENRIK BERG and etl., “Visual Odometry for Road Vehicles Using a Monocular Camera”, Master thises, Department of Signals and Systems ,Chalmers University Of Technology, Gothenburg, Sweden 2016.

      [10] B. Srinivasa Reddy and B. N. Chatterji, “An FFT-Based Technique for Translation, Rotation, and Scale-Invariant Image Registration”, IEEE TRANSACTIONS ON IMAGE PROCESSING, vol. 5, no. 8, 1996.

      [11] Bogdan Kwolek,” Visual Odometry Based on Gabor Filters and Sparse Bundle Adjustment”, Faculty of Electrical and Computer Engineering, Rzesz´ow University of Technology, W. Pola 2, 35-959 Rzesz´ow, Poland.

      [12] Ricardo Ramirez, “Fourier Techniques and Monocular Vision for Simplistic and Low-Cost Visual Odometry in Mobile Robots”, Research Experience for Undergraduates , South Dakota School of Mines and Technology,2016.

      [13] Israa Hadi Ali and Sarah Abdul Rizah Abd, “Proposed New Method of Enhancement Object Trajectory Based on Typical Trajectory”, AL-Bahir Quarterly Adjudicated Journal for Natural and Engineering Research and Studies, vol. 4, no. 7, 2016.

      [14] Scott E. Umbaugh, “Digital Image Processing and Analysis: Human and Computer Vision Applications with CVIPtools”,Book, Second Edition, 2010.

      [15] https://en.wikipedia.org/wiki/Hadamard_product_(matrices) , Accessed 6/7/2018.

      [16] Andreas Geiger and etl., “Vision meets Robotics: The KITTI Dataset”, International Journal of Robotics Research (IJRR),2013.


 

View

Download

Article ID: 27986
 
DOI: 10.14419/ijet.v7i4.19.27986




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.