Method for converting near infrared image to RGB image and apparatus for same

An apparatus for converting a near-infrared image into an RGB image, comprising:

• one or more processors;
• a network interface;
• a memory for loading a computer program executed by the processor;
• and
• a storage for storing large-scale network data and the computer program,
• wherein the computer program, when executed, causes the one or more processors to perform the operations of:
• (A) receiving near-infrared image data to be converted into an RGB image and inputting the received data to a first network;
• (B) extracting, by the first network, feature data of a near-infrared image from the input near-infrared image data;
• and
• (C) outputting, by the first network, an estimated RGB image, wherein the first network is configured to convert the received near-infrared image data into an RGB image, using the extracted feature data of the near-infrared image, and
• wherein the first network performs knowledge distillation learning by receiving knowledge, which enables to mimic the behavior of extracting the feature data of the near-infrared image and the feature data of the RGB image, from the second network which has received as input data not only near-infrared image data as learning data but also RGB image data taken at the same time as the near-infrared image.

A computer program stored on a non-transitory computer-readable medium, when executed on a computing device, performing the steps of:

• (AA) receiving near-infrared image data to be converted into a RGB image and inputting the received data to a first network;
• (BB) extracting, by the first network, feature data of a near-infrared image from the input near-infrared image data;
• and
• (CC) outputting, by the first network, an estimated RGB image, wherein the first network is configured to convert the received near-infrared image data into an RGB image, using the extracted feature data of the near-infrared image, and
• wherein the first network performs knowledge distillation learning by receiving knowledge, which enables to mimic the behavior of extracting the feature data of the near-infrared image and the feature data of the RGB image, from the second network which has received as input data not only near-infrared image data as learning data but also RGB image data taken at the same time as the near-infrared image.