Experimental analysis on noise tolerance of bidirectional confidential with bilateral filter in local based optical flow for image reconstruction
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.
Keywords: optical flow, bilateral filter, bidirectional confidential, SSIM, EVM, AWGN.