Markerless-based augmented reality

As commented before, camera pose estimation can be derived from images to find the correspondences between known points in the environment and their camera projections. In this section, we will see how to extract features from the images to derive the camera pose. Based on these features and their matching, we will see how to finally derive camera pose estimation, which is then used to overlay and integrate digital information.

Feature detection

A feature can be described as a small patch in the image, which is invariant (as much as possible) to image scaling, rotation, and illumination. This way, the same feature can be detected from different images of the same scene with different perspectives...