Image processing apparatus, image processing system, image capturing system, image processing method

An information processing system comprising processing circuitry configured to:

• obtain a first image in first projection, a second image in second projection, and a third image in the second projection that is the same as the projection of the second image;
• calculate a first corresponding area in the first image, which corresponds to the second image, through first homography transformation, based on similarity between a plurality of feature points in the first image, and a plurality of features points in the second image;
• transform a projection of a peripheral area including the first corresponding area from the first projection to the second projection, to generate a peripheral area image;
• calculate a second corresponding area in the peripheral area image, which corresponds to the second image, through second homography transformation, based on similarity between a plurality of feature points in the second image, and a plurality of feature points in the peripheral area image;
• calculate a third corresponding area in the second image, which corresponds to the third image, through third homography transformation, based on similarity between a plurality of feature points in the second image, and a plurality of feature points in the third image;
• reversely transform a projection of the second corresponding area, from the second projection to the first projection, to generate first location information based on a first specific corresponding area in the first image, which corresponds to the second corresponding area;
• calculate a fourth corresponding area in the peripheral area image, which corresponds to the third image, through the second homography transformation;
• and
• reversely transform a projection of the fourth corresponding area, from the second projection to the first projection, to generate second location information based on a second specific corresponding area in the first image, which corresponds to the fourth corresponding area.

An information processing method, comprising:

• obtaining a first image in first projection, a second image in second projection, and a third image in the second projection that is the same as the projection of the second image;
• calculating a first corresponding area in the first image, which corresponds to the second image, through first homography transformation, based on similarity between a plurality of feature points in the first image, and a plurality of features points in the second image;
• transforming a projection of a peripheral area including the first corresponding area from the first projection to the second projection, to generate a peripheral area image;
• calculating a second corresponding area in the peripheral area image, which corresponds to the second image, through second homography transformation, based on similarity between a plurality of feature points in the second image, and a plurality of feature points in the peripheral area image;
• calculating a third corresponding area in the second image, which corresponds to the third image, through third homography transformation, based on similarity between a plurality of feature points in the second image, and a plurality of feature points in the third image;
• reversely transforming a projection of the second corresponding area, from the second projection to the first projection, to generate first location information based on a first specific corresponding area in the first image, which corresponds to the second corresponding area;
• calculating a fourth corresponding area in the peripheral area image, which corresponds to the third image, through the second homography transformation;
• and
• reversely transforming a projection of the fourth corresponding area, from the second projection to the first projection, to generate second location information based on a second specific corresponding area in the first image, which corresponds to the fourth corresponding area.