使用ORB算法检测特征点，并通过BFMatcher进行特征点匹配。然后，根据Lowe's ratio test选择好的匹配点，并使用findHomography计算单应性矩阵。最后，使用warpPerspective将图像进行透视变换，然后将第二张图像粘贴到变换后的图像上。

import cv2
import numpy as npdef find_homography_and_blend(image1, image2, output_path):# 读取两张图片img1 = cv2.imread(image1)img2 = cv2.imread(image2)# 转换为灰度图像gray1 = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)gray2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)# 使用ORB算法检测特征点orb = cv2.ORB_create()keypoints1, descriptors1 = orb.detectAndCompute(gray1, None)keypoints2, descriptors2 = orb.detectAndCompute(gray2, None)# 使用BFMatcher进行特征点匹配bf = cv2.BFMatcher()matches = bf.knnMatch(descriptors1, descriptors2, k=2)# 根据Lowe's ratio test选择好的匹配点good_matches = []for m, n in matches:if m.distance < 0.75 * n.distance:good_matches.append(m)# 获取匹配点的坐标src_pts = np.float32([keypoints1[m.queryIdx].pt for m in good_matches]).reshape(-1, 1, 2)dst_pts = np.float32([keypoints2[m.trainIdx].pt for m in good_matches]).reshape(-1, 1, 2)# 使用findHomography计算单应性矩阵homography, _ = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 5.0)# 使用warpPerspective将图像进行透视变换result = cv2.warpPerspective(img1, homography, (img1.shape[1] + img2.shape[1], img1.shape[0]))# 将第二张图像粘贴到变换后的图像上result[0:img2.shape[0], 0:img2.shape[1]] = img2# 保存融合后的图像cv2.imwrite(output_path, result)# 设置两张图片的路径和融合后的输出路径
image_path1 = "path/to/image1.jpg"
image_path2 = "path/to/image2.jpg"
output_path = "path/to/output.jpg"# 调用融合函数
find_homography_and_blend(image_path1, image_path2, output_path)