Method and apparatus for performing pattern recognition for a tunable sensor system to detect neutron and gamma particles

A non-transitory computer-readable storage medium having stored thereon, computer executable instructions that, if executed by a computer system cause the computer system to perform a method for detecting particles of interest in images from a tunable sensor system, the method comprising:

• training a deep learning process to recognize known radiation-dependent signature patterns created by a particle of interest in test images;
• recombining an input image into a plurality of frames;
• passing the plurality of frames through the deep learning process in order to recognize the particle of interest in the plurality of frames;
• stitching the plurality of frames back into the input image;
• for each pixel within the input image, examining pixels connected to a respective pixel to determine if a signature pattern particular to the particle of interest is present within the input image;
• and
• determining a count of the particle of interest within the input image using the connected pixels.

A system for detecting neutrons in images from a tunable sensor system, said system comprising:

• a memory for storing a plurality of test images, an input image, and instructions associated with a deep learning process and a process for detecting particles of interest in images;
• a processor coupled to the memory, the processor being configured to operate in accordance with the instructions to:
• train the deep learning process to recognize known radiation-dependent signature patterns created by a particle of interest in test images;
• split an input image into a plurality of frames;
• pass the plurality of frames through the deep learning process in order to recognize the particle of interest in the plurality of frames;
• combine the plurality of frames back into the input image;
• for each pixel within the input image, examine pixels connected to a respective pixel to determine if a signature pattern particular to the particle of interest is present within the input image;
• and
• determine a count of the particle of interest within the input image using the connected pixels.