Stereo Matching Based on Features of Image Patch

  • shi zhou Kyushu Institute of Technology
  • He Li Northeastern University
  • Miaomiao Zhu Kyushu Institute of Technology
  • Zhen Li Kyushu Institute of Technology
  • Mitsunori Mizumachi Kyushu Institute of Technology
  • Lifeng Zhang Kyushu Institute of Technology

Abstract

Stereo matching is a branch of 3D vision and has a wide range of applications in 3D reconstruction
and autonomous driving. Recently, stereo matching methods leverage all the information of the stereo image to calculate disparity map. However, these methods still have difficulties in texture-less areas and occlusion areas, and post-processing improves accuracy. Therefore, there is a high computational cost in feature extraction and post-processing. In this paper, we propose a stereo matching method based on features of image patches to predict the disparity of non-occlusion areas instead of full image features. And aggregation methods are performed to modify all kinds of mismatching pixels based on the correct disparity in the non-occlusion areas. Furthermore, we evaluated the proposed method on the Middlebury dataset. The result shows that the proposed method performs well in all areas.

References

H. Kien, T. Pan, Z. Wang, H. Nguyen and M. Vo, “Accurate 3D shape measurement of multiple separate objects with stereo vision”, Measurement Science and Technology, Vol.25, No.3, pp.1-7, 2014. DOI: 10.1088/0957- 0233/25/3/035401

H. Yu, T. Xing and X. Jia, “The analysis of measurement accuracy of the parallel binocular stereo vision system”, 8th International Symposium on Advanced Optical Manufacturing and Testing Technologies, 2016. DOI: 10.1117/12.2243156

S. Degadwala, D. Vyas and A. Mahajan, “Review on Stereo Vision Based Depth Estimation”, International Journal for Scientific Research in Science: Engineering and Technology, Vol.6, N.2, pp.665-671, 2019. DOI: 10.32628/IJSRSET207261

W. Luo, A. G. Schwing and R. Urtasun, “Efficient Deep Learning for Stereo Matching”, Computer Vision Foundation, pp.5695-5703, 2016. DOI: 10.1109/CVPR.2016.614

X. Song, X. Zhao, L. Fang, H. Hu and Y. Yu, “EdgeStereo: An Effective Multi-task Learning Network for Stereo Matching and Edge Detection”, International Journal of Computer Vision, Vol.128, No.4, pp.910-930, 2019. DOI: 10.1007/s11263-019-01287-w

S. Baker, D. Scharstein, J.P. Lewis, S. Roth, M. J. Black and R. Szeliski, “A Database and Evaluation Methodology for Optical Flow”, International Journal of Computer Vision, Vol.92, No.1, pp.1-31, 2011. DOI: 10.1007/s11263- 010-0390-2

L. Li, S. Zhang, X. Yu and L. Zhang, “PMSC: PatchMatch-Based Superpixel Cut for Accurate Stereo Matching”, IEEE Transactions on Circuits & Systems for Video Technology, Vol.28, No.3, pp.679-692, 2018. DOI: 10.1109/TCSVT.2016.2628782

J. Lu, K. Zhang, G. Lafruit and F. Catthoor, “REAL- TIME STEREO MATCHING: A CROSS-BASED LOCAL APPROACH”, In 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, pp.733-736, 2009. DOI: 10.1109/ICASSP.2009.4959688

Q. Yang, P. Ji, D. Li, S. Yao, and M. Zhang, “Fast stereo matching using adaptive guided filtering”, Image and Vision Computing, Vol.32, No.3, pp.202-211, 2014. DOI: 10.1016/j.imavis.2014.01.001

D. Scharstein, H. Hirschmu ̈ller, Y. Kitajima, G. Krathwohl, N. Nesˇic ́, X. Wang, and P. Westling, “High-resolution stereo datasets with subpixel-accurate ground truth”, In German Conference on Pattern Recognition, pp.1-12, 2014. DOI: 10.1007/978-3-319-11752-2_3

Published
2021-07-23
How to Cite
zhou, shi, Li, H., Zhu, M., Li, Z., Mizumachi, M., & Zhang, L. (2021). Stereo Matching Based on Features of Image Patch. Journal of the Institute of Industrial Applications Engineers, 9(3), 91. https://doi.org/10.12792/jiiae.9.91
Section
Articles