使用Python和OpenCV实现图片拼接的方法

import cv2
import numpy as np
import sys

def cv_show(name, img):
    """显示图像辅助函数"""
    cv2.imshow(name, img)
    cv2.waitKey(0)

def detectAndDescribe(image):
    """检测图像特征点并计算描述符"""
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    descriptor = cv2.SIFT_create()
    # 检测SIFT特征点，并计算描述符
    (kps, des) = descriptor.detectAndCompute(gray, None)
    # 将关键点坐标转换为numpy数组
    kps_float = np.float32([kp.pt for kp in kps])
    return (kps, kps_float, des)

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

descriptor = cv2.SIFT_create()

(kps, des) = descriptor.detectAndCompute(gray, None)

kps_float = np.float32([kp.pt for kp in kps])

return (kps, kps_float, des)

# 读取待拼接图片
imageA = cv2.imread('imageA.jpg')
imageB = cv2.imread('imageB.jpg')

# 计算特征点和描述符
(kpsA, kps_floatA, desA) = detectAndDescribe(imageA)
(kpsB, kps_floatB, desB) = detectAndDescribe(imageB)

# 建立暴力匹配器
matcher = cv2.BFMatcher()
rawMatcher = matcher.knnMatch(desB, desA, 2)

# 筛选优质匹配点
good = []
matches = []
for m in rawMatcher:
    # 当最近距离跟次近距离的比值小于0.65时，保留此匹配对
    if len(m) == 2 and m[0].distance < 0.65 * m[1].distance:
        good.append(m)
        matches.append((m[0].queryIdx, m[0].trainIdx))

# 绘制匹配结果
vis = cv2.drawMatchesKnn(imageB, kpsB, imageA, kpsA, good, None, 
                        flags=cv2.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
cv_show("keypoint matches", vis)

if len(matches) > 4:
    # 获取匹配点的坐标
    ptsB = np.float32([kps_floatB[i] for (i, _) in matches])
    ptsA = np.float32([kps_floatA[i] for (_, i) in matches])
    
    # 使用RANSAC算法计算单应性矩阵
    (H, mask) = cv2.findHomography(ptsB, ptsA, cv2.RANSAC, 10)
else:
    print("图片未找到4个以上的匹配点")
    sys.exit()

# 对imageB应用透 视变换
result = cv2.warpPerspective(imageB, H, 
                            (imageB.shape[1] + imageA.shape[1], imageB.shape[0]))

# 将imageA放置在结果图像的左侧
result[0:imageA.shape[0], 0:imageA.shape[1]] = imageA
cv_show('result', result)