Method and apparatus for iteratively establishing object position

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 sensor data from at least one image sensor, wherein the sensor data comprises a plurality of images, and each image comprises sensor position data;
• process the plurality of images using a detection module to detect features within each of the plurality of images;
• parse the plurality of images for images including a first feature;
• for each of a plurality of combinations of two images including the first feature, determine an estimated first feature position based on a triangulated position between the first feature in each of the two images and the sensor position data associated with each of the two images;
• establish a spread of estimated first feature positions for the plurality of combinations of two images;
• determine a best-fit line passing through the spread of estimated first feature positions;
• iteratively reduce a perpendicular error projection of each estimated first feature position relative to the best-fit line to obtain a reduced spread of estimated first feature positions;
• establish from the reduced spread of estimated first feature positions a resulting estimated first feature position;
• and
• position an image of the first feature within a map based on the established resulting estimated first feature position.

A method comprising:

• receiving sensor data from at least one image sensor, wherein the sensor data comprises a plurality of images, and each image comprises sensor position data;
• processing the plurality of images using a detection module to detect features within each of the plurality of images;
• parsing the plurality of images for images including a first feature;
• for each of a plurality of combinations of two images including the first feature, determining an estimated first feature position based on a triangulated position between the first feature in each of the two images and the sensor position data associated with each of the two images;
• establishing a spread of estimated first feature positions for the plurality of combinations of two images;
• determine a best-fit line passing through the spread of estimated first feature positions;
• iteratively reducing a perpendicular error projection of each estimated first feature position relative to the best-fit line to obtain a reduced spread of estimated first feature positions;
• establishing from the reduced spread of optimized estimated first feature positions a resulting estimated first feature position;
• and
• positioning an image of the first feature within a map based on the established resulting estimated first feature position.