Gamma radioactive imaging method based on deep learning

Abstract

The invention discloses a gamma radioactive imaging method based on deep learning, and belongs to the fields of radiation detection technology and radioactivity monitoring. The gamma radioactive imaging method can shorten required time for gamma radiation imaging, improve the image quality, and accurately reflect purpose of radioactive spatial distribution. The method includes the steps that a Monte Carlo method is used for simulating process of coded imaging, and a sufficient number of coded image samples are obtained; coded images are processed and used as samples to train and test a deep learning network model, and design of a coded aperture collimator is optimized; a gamma radiation coded image of a detected target area is obtained by using a coded aperture gamma camera; the gamma radiation coded image is decoded and processed by using the deep learning network completed by training; a depth map and a optical image of the detected target area are obtained by using a depth vision detection system; and a decoded radiation hotspot image is fused with the depth map and the optical image, and a composite image of radioactive hotspot distribution of the detected target area is obtained.

Description

Technical field [0001] The invention belongs to the field of radiation detection technology and radioactivity monitoring, and in particular relates to a gamma radioactive imaging method based on deep learning. Background technique [0002] As the nuclear industry and nuclear technology applications have penetrated into various fields of national economic development, the safety supervision of radioactive materials and the ability to respond to nuclear accidents have become issues of particular concern to the nuclear safety and nuclear security industry. The traditional radioactivity distribution detection technology mainly uses radiation detectors to measure various points in the target area, or uses array detectors to perform two-dimensional imaging of the target area, but neither can obtain the accurate location of radioactive materials in the real environment. In particular, for radioactive positioning in complex scenes, it is also necessary to consider the three-dimensional s...

AI Technical Summary

Problems solved by technology

However, the traditional coded aperture collimator is designed according to complex mathematical formulas, and its encoding and decoding algorithms are relatively complex, which limits the design of the coded aperture collimator, and requires a long imaging time in a low dose rate radiation environment. The gamma radiation image is closely related to the measurement time, and high-resolution images cannot be obtained when the measurement time is short

Images