Question

import cv2
import numpy as np

MIN_MATCH_COUNT = 30

#Initiate Sift detector for brute force matching
detector = cv2.xfeatures2d.SIFT_create()

#FLANN Parameters(finds nearest neighbors)
FLANN_INDEX_KDITREE=0
flannParam = dict(algorithm = FLANN_INDEX_KDITREE, tree=5)
flann = cv2.FlannBasedMatcher(flannParam, {})

#Initialize train image
img1 = cv2.imread("2.jpg")
img2 = cv2.imread("1.jpg")
trainImg = [img1,img2]
trainKP, trainDesc = detector.detectAndCompute(trainImg,None)

如何将多个图片提供给detectAndCompute()方法？

将此视为错误：

trainKP，trainDesc = detector.detectAndCompute（trainImg，None）

TypeError：image不是numpy数组，也不是标量

Answer 1

似乎你无法将图像列表传递给detectAndCompute。它需要像这样使用

kp1, des1 = detector.detectAndCompute(img1,None)
kp2, des2 = detector.detectAndCompute(img1,None)

或使用for循环

trainImg = [img1,img2]

for img in trainImg:
    kp, desc = detector.detectAndCompute(img, None)
    # Process kp and desc

此外，如果你正在寻找一个教程，这是一个非常好的用于python中的基本功能匹配 http://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_feature2d/py_matcher/py_matcher.html

OpenCv SIFT蛮力与多个图像匹配

1 个答案: