SURF匹配python实现

最新推荐文章于 2025-05-14 13:19:38 发布

原创最新推荐文章于 2025-05-14 13:19:38 发布 · 7.6k 阅读

15 ·

CC 4.0 BY-SA版权

文章标签：

#Python #SURF

python image 专栏收录该内容

7 篇文章

订阅专栏

本文介绍如何使用SIFT算法检测并计算图像特征，再通过FLANN算法进行特征匹配，实现两幅图像的匹配过程。使用的是OPENCV3.1.0及以下版本，针对middlebury上的示例图片进行实验。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

# -*- coding: utf-8 -*-
"""
Created on Thu Jun 20 16:25:27 2019
推荐使用OPENCV 3.1.0及以下版本
两幅png为middlebury上面的示例图片
@author: zhangzhicheng
"""

import numpy as np
import cv2
from matplotlib import pyplot as plt
leftImage = cv2.imread('E:\\stereovisioncoding\\SemiGlobalMathingImplementationmatlab\\image_left.png')
rightImage = cv2.imread('E:\\stereovisioncoding\\SemiGlobalMathingImplementationmatlab\\image_right.png')

#创造sift
sift = cv2.xfeatures2d.SIFT_create()
kp1, des1 = sift.detectAndCompute(leftImage, None)
kp2, des2 = sift.detectAndCompute(rightImage, None)#返回关键点信息和描述符

 
FLANN_INDEX_KDTREE = 0
indexParams = dict(algorithm=FLANN_INDEX_KDTREE, trees = 5)
searchParams = dict(checks = 50)#指定索引树要被遍历的次数

flann = cv2.FlannBasedMatcher(indexParams, searchParams)
matches = flann.knnMatch(des1, des2, k=2)
matchesMask = [[0,0] for i in range(len(matches))]
print("matches", matches[0])
for i, (m,n) in enumerate (matches):
    if m.distance < 0.07*n.distance:
        matchesMask[i] = [1,0]

drawParams = dict(matchColor = (0, 255, 0), singlePointColor=None,
                  matchesMask = matchesMask, flags = 2)#flag=2只画出匹配点，flag=0把所有的点都画出
resultImage = cv2.drawMatchesKnn(leftImage,kp1,rightImage,kp2,matches,None,**drawParams)
plt.imshow(resultImage)
plt.show()