Experimental analysis on noise tolerance of bidirectional confidential with bilateral filter in local based optical flow for image reconstruction
Keywords:optical flow, bilateral filter, bidirectional confidential, SSIM, EVM, AWGN
Noise is the main issue causing defects in the optical flow for motion prediction where the result in the motion vector (MV) is directly impacted. In this paper, we perform an experimental analysis on numerous noise tolerance models for a local based optical flow where the main model is bidirectional confidential with bilateral filter. For performance analysis, we focused on 2 main indicators. These are Structural SIMilarity (SSIM) and Error Vector Magnitude (EVM) where SSIM was used to indicate the quality for image reconstruction issues and EVM was used to indicate the accuracy in MV issues. In our experiments, the Additive White Gaussian Noise (AWGN) was formed at several noise levels over several standard sequences for performance evaluation.
Fleet, D. J., & Jepson, A. D. (1990). Computation of component image velocity from local phase information. International journal of Computer Vision, 5(1), 77-104. DOI: 10.1007/BF00056772
Horn, B. K. P., & Schunck, B. G. (1981). Determining optical flow. Artificial Intelligence, 17, 185-203.
Kesrarat, D., & Patanavijit, V. (2010). Performance evaluation of differential optical flow algorithms based on high confidence reliability with sub-pixel displacement. Paper presented at The 33rd Engineering Conference (EECON), 1305-1308.
Kesrarat, D., & Patanavijit, V. (2011a). Experimental performance analysis of high confidence reliability based on differential optical flow algorithms over AWGN sequences with sub-pixel displacement. Paper presented at IEEE International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 1-6.
Kesrarat, D., & Patanavijit, V. (2011b). A novel robust and high reliability spatial correlation optical flow algorithm based on median motion estimation and bidirectional symmetry flow technique. Paper presented at IEEE International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 1-6.
Kesrarat, D., & Patanavijit, V. (2013). Experimental analysis of performance comparison on both linear filter and bidirectional confidential technique for spatial domain optical flow algorithm. The ECTI Transactions on Computer and Information Technology (ECTI-CIT), 7(2), 157-168.
Kesrarat, D., & Patanavijit, V. (2015). Bidirectional confidential with bilateral filter on local based optical flow for image reconstruction under noisy condition. Paper presented at IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), 1-4.
Kondo, T., & Kongpawechnon, W. (2009). Robust motion estimation methods using gradient orientation information. ScienceAsia 35 (Journal of The Science Society of Thailand), 196-202.
Li, R., & Yu, S. (2008). Confidence based optical flow algorithm for high reliability. Paper presented at the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 785-788.
Lucas, B. D., & Kanade, T. (1981). An iterative image registration technique with an application to stereo vision. Proceedings of Defense Advanced Research Projects Agency (DARPA) Image Understanding Workshop, 121-130.
Mozerrov, M. G. (2013). Constrained optical flow estimation as a matching problem. IEEE Transactions on Image Processing, 2(5), 2044-2055.
Paris, S., Kornprobst, P., Tumblin, J., & Durand, F. (2008). Bilateral filtering: Theory and applications..Foundation and Trends in Computer Graphics and Vision, 4(1), 1-73. DOI: 10.1561/0600000020
Reed, T. R. (2005). Digital image sequence processing, compression, and Analysis. Broca Raton, Fl., USA: Chemical Rubber Company (CRC) Press.
Sun, J., Li, Y., Kang, S., & Shun, H.-Y. (2005). Symmetric stereo matching for occlusion handling. Paper presented at IEEE Conference in Computer Vision and Pattern Recognition, 399-406.
How to Cite
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.