Linear panorama stitcher5/6/2023 ![]() ![]() What SIFT descriptor basically does is it takes a 16x16 window around the detected interest point (Figure 2), and then partitioning it into a 4x4 grid of cells. However in this case, I will just be focusing on the descriptors itself.įigure 2 (shows a downscaled version). SIFT is actually an algorithm that detect interest points and describing them. If his paper is too much to read, you can refer here on a much quicker read of SIFT. Scale Invariant Feature Transform (SIFT) was published by David Lowe in 2004. I will dive right in to the SIFT descriptor which we can use on our interest points found by our Harris Corner Detector. Descriptors should be invariant to rotation, scaling and translation too. Describing our interest pointsĭescriptors are basically vector representations that mathematically characterise a region in the image. To summarise this first part of detecting our interest points from an image, corners are good representation of an interest point and can be found using Harris Corner Detector. In order for Harris Corner to be scale invariant, we will need an additional step of Automatic Scale Selection to find a scale that gives a local maximum of our corner score. However, it is not invariant to scaling of intensity and to scale. Harris Corner is invariant to rotation (since the eigenvalues of the H matrix remains the same even after rotation), translation and additive changes to intensity. It is important to understand SIFT in the later parts as we will be using SIFT descriptor to describe our interest points found.Įssentially, Harris Corner algorithm computes a corner score from the gradients of the image (using a second moment H matrix) and label values above a set threshold as corners, before taking the points of the local maxima (Non-Maximum Suppression). I personally find this article to be a good read on SIFT. There are also other methods such as the SIFT which uses the Difference of Gaussian (DoG) to detect interest points of different scales. ![]() Note that Harris Corner Detector is just one of the many algorithms that helps us find these interest points. We want to be able to find the same interest points even if an image has been rotated, scaled or translated.Ī local feature will enable our detection of interest points to be more robust to clutter and occlusion. We want to be able to reliably determine which interest point in an image match to the corresponding interest point in the other image. We want to be able to find features in an image that can ultimately tell us where to match between different images of the same scene (from nearby viewpoints).ī) Distinctiveness of the interest points There are several characteristics when we look for interest points in an image. Perform Homography to finish the stitching.Matching these descriptors of our interest points.This also means that I will most probably be skipping any mathematical concepts and calculations involved. In this article, I will be giving a very brief overview that is able to sufficiently (hopefully) build the intuition behind how image stitching works. There are 4 main parts behind how Panorama stitching works. Computer Vision: Intuition behind Panorama Stitching ![]()
0 Comments
Leave a Reply. |