Abstract: A system and method for identifying lithology based on images and XRF mineral inversion solving the problem that conventional lithology identification relies on manual work, which is time-consuming, subjective and can cause misjudgment. The identification system includes an autonomous vehicle; an X ray fluorescence spectrometer probe, and tests surrounding rock element information; image collection device; and vehicle-mounted processor. The processor inverts the received surrounding rock element information into mineral information based on a Barthes-Niggli standard mineral calculation method; and receive surrounding rock images and a corresponding inclination angle thereof, convert the surrounding rock images into image information in a one-dimensional vector format, splice the image and mineral information which is in a one-dimensional format, and distinguish the spliced information based on a preset neural network to identify rock lithology.

Abstract: A system and method for identifying lithology based on images and XRF mineral inversion solving the problem that conventional lithology identification relies on manual work, which is time-consuming, subjective and can cause misjudgment. The identification system includes an autonomous vehicle; an X ray fluorescence spectrometer probe, and tests surrounding rock element information; image collection device; and vehicle-mounted processor. The processor inverts the received surrounding rock element information into mineral information based on a Barthes-Niggli standard mineral calculation method; and receive surrounding rock images and a corresponding inclination angle thereof, convert the surrounding rock images into image information in a one-dimensional vector format, splice the image and mineral information which is in a one-dimensional format, and distinguish the spliced information based on a preset neural network to identify rock lithology.