LightGlue: Local Feature Matching at Light Speed

classical_matching.py

#!/usr/bin/env python3

import numpy as np
import cv2 as cv
from matplotlib import pyplot as plt

MIN_MATCH_COUNT = 10
img1 = cv.imread('./sensor4_00230.jpeg')
img2 = cv.imread('./sensor3_00230.jpeg')

# Initiate SIFT detector
sift = cv.SIFT_create()
# find the keypoints and descriptors with SIFT
kp1, des1 = sift.detectAndCompute(img1,None)
kp2, des2 = sift.detectAndCompute(img2,None)
FLANN_INDEX_KDTREE = 1
index_params = dict(algorithm = FLANN_INDEX_KDTREE, trees = 5)
search_params = dict(checks = 50)
flann = cv.FlannBasedMatcher(index_params, search_params)
matches = flann.knnMatch(des1,des2,k=2)

# store all the good matches as per Lowe's ratio test.
good = []
for m,n in matches:
    if m.distance < 0.7*n.distance:
        good.append(m)

if len(good)>MIN_MATCH_COUNT:
 src_pts = np.float32([ kp1[m.queryIdx].pt for m in good ]).reshape(-1,1,2)
 dst_pts = np.float32([ kp2[m.trainIdx].pt for m in good ]).reshape(-1,1,2)
 M, mask = cv.findHomography(dst_pts, src_pts, cv.RANSAC,5.0)

 h,w,_ = img1.shape
 T = np.float32([[1, 0, 0], [0, 1, h/2], [0, 0, 1]])
 M = T @ M
 matchesMask = mask.ravel().tolist()

 dst = cv.warpPerspective(img2, M, (w*2, h*2))
 dst[h//2:h//2+h ,0:w,:] = img1
else:
 print( "Not enough matches are found - {}/{}".format(len(good), MIN_MATCH_COUNT) )
 matchesMask = None

plt.imshow(dst[...,::-1])
plt.show()