a. The first depth of this algorithm is input two images which are supposed to stitch.
b. Use in-built function knnMatch() to find the matching points
c. Determine which points is good match, if it is a good match, save it to the array
d. Use the good match points to compute the homography. Reason: Using the homography matrix so that we can perspective the image.
e. Use in-built function Warp perseptive to find the warp image. Reason: Makes two image looks like it from the same view.
f. Stitch two images into one, combine two image together.
Fig 1. Match points
Fig 2. Stitch image