Dual-view angle image calibration method and apparatus, storage medium and electronic device

A non-transitory computer readable storage medium having computer-readable instructions stored thereon, wherein execution of the instructions by a processor causes the processor to perform:

• performing feature matching on a first image pair to obtain a first feature point pair set, wherein the first image pair comprises two images respectively photographed corresponding to two different view angles of a same scene;
• obtaining multiple different first fundamental matrices of the first image pair at least according to the first feature point pair set;
• obtaining first image deformation information indicating relative deformation between the first image pair after mapping transformation is performed through the multiple different first fundamental matrices and the first image pair before the mapping transformation is performed;
• determining a first optimization fundamental matrix from the multiple different first fundamental matrices at least according to the first image deformation information;
• calibrating the first image pair according to the first optimization fundamental matrix;
• storing or updating information of at least one feature point pair satisfying a predetermined matching condition and being in the first feature point pair set, and
• calibrating a second image pair according to the first optimization fundamental matrix.

An electronic device, comprising a processor and a memory;

• the memory is configured to store at least one executable instruction, wherein execution of the at least one executable instruction enables the processor to execute the following operations:
• performing feature matching on a first image pair to obtain a first feature point pair set, wherein the first image pair comprises two images respectively photographed corresponding to two different view angles of a same scene;
• obtaining multiple different first fundamental matrices of the first image pair at least according to the first feature point pair set;
• obtaining first image deformation information indicating relative deformation between the first image pair after mapping transformation is performed through the multiple different first fundamental matrices and the first image pair before the mapping transformation is performed;
• determining a first optimization fundamental matrix from the multiple different first fundamental matrices at least according to the first image deformation information;
• calibrating the first image pair according to the first optimization fundamental matrix;
• storing or updating information of at least one feature point pair satisfying a predetermined matching condition and being in the first feature point pair set, and
• calibrating a second image pair according to the first optimization fundamental matrix.