摘要：為了解決這個(gè)問(wèn)題，算法使用和可以通過(guò)參數(shù)來(lái)設(shè)定所以好的匹配提供的正確的估計(jì)被稱為，剩下的被稱為返回一個(gè)掩模，這個(gè)掩模確定了和點(diǎn)

Feature Matching + Homography to find Objects

聯(lián)合使用特征提取和 calib3d 模塊中的 findHomography 在復(fù)雜圖像中查找已知對(duì)象.

之前在一張雜亂的圖像中找到了一個(gè)對(duì)象（的某些部分）的位置.這些信息足以幫助我們?cè)谀繕?biāo)圖像中準(zhǔn)確的找到（查詢圖像）對(duì)象.為了達(dá)到這個(gè)目的可以使用 calib3d 模塊中的cv2.findHomography()函數(shù).如果將這兩幅圖像中的特征點(diǎn)集傳給這個(gè)函數(shù)，他就會(huì)找到這個(gè)對(duì)象的透視圖變換.然后就可以使用函數(shù) cv2.perspectiveTransform() 找到這個(gè)對(duì)象了.至少要 4 個(gè)正確的點(diǎn)才能找到這種變換.在匹配過(guò)程可能會(huì)有一些錯(cuò)誤，而這些錯(cuò)誤會(huì)影響最終結(jié)果。為了解決這個(gè)問(wèn)題，算法使用 RANSAC 和 LEAST_MEDIAN(可以通過(guò)參數(shù)來(lái)設(shè)定).所以好的匹配提供的正確的估計(jì)被稱為 inliers，剩下的被稱為outliers.cv2.findHomography() 返回一個(gè)掩模，這個(gè)掩模確定了 inlier 和outlier 點(diǎn).

import numpy as np
import cv2
import matplotlib.pyplot as plt

MIN_MATCH_COUNT = 10

img1 = cv2.imread("img.jpg",0)          # queryImage
img2 = cv2.imread("img1.jpg",0) # trainImage

# Initiate SIFT detector
sift = cv2.xfeatures2d.SIFT_create()


# find the keypoints and descriptors with SIFT
kp1, des1 = sift.detectAndCompute(img1,None)
kp2, des2 = sift.detectAndCompute(img2,None)

FLANN_INDEX_KDTREE = 0
index_params = dict(algorithm = FLANN_INDEX_KDTREE, trees = 5)
search_params = dict(checks = 50)

flann = cv2.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 = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC,5.0)
    matchesMask = mask.ravel().tolist()

    h,w = img1.shape
    pts = np.float32([ [0,0],[0,h-1],[w-1,h-1],[w-1,0] ]).reshape(-1,1,2)
    dst = cv2.perspectiveTransform(pts,M)

    img2 = cv2.polylines(img2,[np.int32(dst)],True,255,3, cv2.LINE_AA)

else:
    print("Not enough matches are found - %d/%d" % (len(good),MIN_MATCH_COUNT))
    matchesMask = None

# Finally we draw our inliers (if successfully found the object) or matching keypoints (if failed).

draw_params = dict(matchColor = (0,255,0), # draw matches in green color
                   singlePointColor = None,
                   matchesMask = matchesMask, # draw only inliers
                   flags = 2)

img3 = cv2.drawMatches(img1,kp1,img2,kp2,good,None,**draw_params)

plt.imshow(img3, "gray"),plt.show()