IDENTIFICATION OF SIGNAL-NOISE RELATIONSHIP (SNR) IN A Scene

摘要

Techniques for generating a two-dimensional (2D) map of signal-to-noise ratio (SNR) values for images captured by sensors are revealed. The techniques use Lookup Tables (LUTs),to create a transformation LUT that maps pixel values to SNR values. The transformation LUT can be generated by first generating an intermediate LUT that uses the operating parameters identified with the sensor to map pixel values to luminous intensity values. The luminous intensity values are then used together with an SNR model that outputs a prediction of electrons identified with a signal part and a noise part of the images captured by the sensor to map the pixel values to SNR values. The 2D map can be used to:improve the accuracy of classification of objects and/or scene features for different applications.