Question

我正在使用SIFT + RANSAC检测图像中的特征以及对象或徽标的位置。

在我遵循Opencv教程时，我需要提供一张查询图像和一张培训图像。

但是我想用一张火车图像给出3个不同的查询图像。

有可能吗？

我尝试了以下代码：

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

MIN_MATCH_COUNT = 10

img1 = cv.imread('/home/jcl-vb/Desktop/Dataset/Balea_dm_Logo0.jpg',0)# Query Image 1
img2 = cv.imread('/home/jcl-vb/Desktop/Dataset/Balea_dm_Logo1.jpg',0)# Query Image 2
img3 = cv.imread('/home/jcl-vb/Desktop/Dataset/Balea_dm_Logo2.jpg',0)# Query Image 3 

img4 = cv.imread('/home/jcl-vb/downloads/Balea/6. img_0045-e1488488847800.jpg',0) # train Image

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

# find the keypoints and descriptors with SIFT
kp1, des1 = sift.detectAndCompute(img1,None)
kp2, des2 = sift.detectAndCompute(img2,None)
kp3, des3 = sift.detectAndCompute(img3,None)

kp4, des4 = sift.detectAndCompute(img4,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)
matches1 = flann.knnMatch(des1,des4,k=2)
matches2 = flann.knnMatch(des2,des4,k=2)
matches3 = flann.knnMatch(des3,des4,k=2)

那我实际上不知道，我该怎么走？

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([ kp4[m.trainIdx].pt for m in good ]).reshape(-1,1,2)
    M, mask = cv.findHomography(src_pts, dst_pts, cv.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 = cv.perspectiveTransform(pts,M)
    img4 = cv.polylines(img4,[np.int32(dst)],True,255,3, cv.LINE_AA)
else:
    print( "Not enough matches are found - {}/{}".format(len(good), MIN_MATCH_COUNT) )
    matchesMask1 = None


draw_params = dict(matchColor = (0,255,0), # draw matches in green color
                   singlePointColor = None,
                   matchesMask = matchesMask,
                   flags = 2)
print(draw_params)
img3 = cv.drawMatches(img1,kp1,img4,kp4,good,None,**draw_params)
plt.figure(figsize=(10,10))
plt.imshow(img3)
plt.show()

实际结果：一张查询图片和一张img4中的火车图片

预期结果：一张火车的三个不同查询图像img4中的图像。

如何编写一些代码以使用一个火车图像获取多个查询图像的输出？

0 个答案: