Stereo-based visual odometry method and system

A visual odometry system for estimating pose from a sequence of images, comprising:

• means for obtaining a sequence of stereo images;
• a processor and a memory for performing the steps of:
• (a) detecting at least three feature points in both the left image and right image of a first pair of stereo images at a first point in time;
• (b) matching the at least three feature points in the left image to the at least three feature points in the right image to obtain at least three two-dimensional feature correspondences;
• (c) calculating the three-dimensional coordinates of the at least three two-dimensional feature correspondences to obtain at least three three-dimensional reference feature points;
• (d) tracking the at least three feature points in one of the left image and right image of a second pair of stereo images at a second point in time different from the first point in time to obtain at least three two-dimensional reference feature points;
• and
• (e) calculating a pose based on the at least three three-dimensional reference feature points and its corresponding two-dimensional reference feature points in the stereo images;
• and
• a display for displaying the calculated pose.

A non-transitory computer-readable medium carrying one or more sequences of instructions for estimating pose from a sequence of images, wherein execution of the one of more sequences of instructions by one or more processors causes the one or more processors to perform the steps of:

• (a) detecting at least three feature points in both the left image and right image of a first pair of stereo images at a first point in time;
• (b) matching the at least three feature points in the left image to the at least three feature points in the right image to obtain at least three two-dimensional feature correspondences;
• (c) calculating the three-dimensional coordinates of the at least three two-dimensional feature correspondences to obtain at least three three-dimensional reference feature points;
• (d) tracking the at least three feature points in one of the left image and right image of a second pair of stereo images at a second point in time different from the first point in time to obtain at least three two-dimensional reference feature points;
• and
• (e) calculating a pose based on the at least three three-dimensional reference feature points and its corresponding two-dimensional reference feature points in the stereo images.

A method for obtaining a pose of an object from a sequence of images, comprising the steps of:

• (a) detecting at least one feature point in both the left image and right image of a first pair of stereo images at a first point in time;
• (b) matching the at least one feature point in the left image to the at least one feature point in the right image to obtain at least one two-dimensional feature correspondence;
• (c) calculating the three-dimensional coordinates of the at least one two-dimensional feature correspondence to obtain at least one three-dimensional reference feature point;
• (d) tracking the at least one feature point in one of the left image and right image of a second pair of stereo images at a second point in time different from the first point in time to obtain at least one two-dimensional reference feature point;
• and
• (e) calculating a pose based on the at least one three-dimensional reference feature point and its corresponding two-dimensional reference feature point in the stereo images.