Method, apparatus, and computer program product for point-to-point translation between images

A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions to:

• receive three-dimensional coordinates of points in a first image of an environment captured in first sensor data by a first image sensor from a first perspective;
• project the three-dimensional coordinates of points in the first image of the environment onto a plane of projection to form first projected points;
• receive second sensor data from a second image sensor, wherein the second sensor data comprises a second image of the environment captured from a second perspective;
• project rays from the second sensor data into the plane of projection to generate second projected points, wherein the rays comprise lines that extend from a position of the second sensor through image correspondence points of the second sensor data;
• compute pairwise vectors between corresponding pairs of the first projected points of the first sensor data and the second projected points of the second sensor data;
• and
• generate a translation vector from the pairwise vectors wherein the translation vector represents a shift of the second image sensor data to correspond to a ground truth data.

A method comprising:

• receiving first sensor data from a first image sensor, wherein the first sensor data comprises a first image of an environment captured from a first perspective;
• receiving second sensor data from a second image sensor, wherein the second sensor data comprises a second image of the environment captured from a second perspective;
• identifying image correspondence points between the first sensor data and the second sensor data;
• computing pairwise vectors between corresponding pairs of first projected points of the first sensor data and second projected points of the second sensor data;
• clustering the pairwise vectors according to magnitude and orientation;
• and
• generating a translation vector from clusters of pairwise vectors, wherein the translation vector represents a shift of the second image sensor data to correspond to a ground truth data.