Reconstruction of surveillance videos by non-iterative pseudo inverse based recovery algorithm (NIPIRA): A subjective experience

Compressed sensing is a conceptual process where the input data is compressed to a lower dimensional vector i.e. M ≤ N. Perfect recovery of the original data from these diminished measurements is carried out using various recovery procedures. Many of the procedures are iterative in nature that introduce complications such as computational complexity, increased elaspsed time etc. Hence Non-Iterative pseudo inverse based recovery algorithm (NIPIRA) is formulated to face the above said discrepancies effectively. The recovery of surveillance videos has been carried out perfectly using NIPIRA and the recovered videos are subjectively evaluated with the help of naive viewers. Mean opinion score (MOS) for 8 recovered surveillance videos, under various low level attributes and abstract attributes, are collected from 20 naive viewers. The average score given by the scorers is around 4.5 denoting the ‘Excellent’ range in MOS table proving NIPIRA to be the best algorithm for recovery of videos from compressively sensed measurements.