图像拼接

功能函数代码：

import numpy as np
import cv2


class Stitcher:
    # 拼接函数
    def stitch(self, imageA,imageB, ratio=0.75, reprojThresh=4.0, showMatches=False):
        # 获取输入图片

        # 检测AB图像的SIFT关键特征点，并计算特征描述子
        (kpsA, featuresA) = self.detectAndDescribe(imageA)
        (kpsB, featuresB) = self.detectAndDescribe(imageB)

        # 匹配两张图片的所有特征点，返回匹配结果
        M = self.matchKeypoints(kpsA, kpsB, featuresA, featuresB, ratio, reprojThresh)

        # 如果返回结果为空，没有匹配成功的特征点，退出算法
        if M is None:
            return None

        # 否则提取匹配结果
        # H是3*3视角变换矩阵
        (matches, H, status) = M

        # 将图片A进行视角变换，result是变换后的图片
        result = cv2.warpPerspective(imageA, H, (imageA.shape[1] + imageB.shape[1], imageA.shape[0]))
        #self.cv_show('result', result)

        # 将图片B传入result图片最左端
        result[0:imageB.shape[0], 0:imageB.shape[1]] = imageB
        #self.cv_show('result', result)
        '''
        # 检测是否需要显示图片匹配
        if showMatches:
            # 生成匹配图片
            vis = self.drawMatches(imageA, imageB, kpsA, kpsB, matches, status)
            # 返回结果
            return (result, vis)
        # 返回匹配结果
        '''
        return result

    def detectAndDescribe(self, image):
        # 灰度图
        image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
        # 实例化SIFT（建立SIFT生成器）
        sift = cv2.SIFT_create()
        # 检测特征点
        (kps, features) = sift.detectAndCompute(image, None)
        # 将结果转换成Numpy数组
        kps = np.float32([kp.pt for kp in kps])

        # 返回特征点集，及对应的描述特征
        return (kps, features)

    def matchKeypoints(self, kpsA, kpsB, featuresA, featuresB, ratio, reprojThresh):
        # 建立暴力匹配器
        matcher = cv2.BFMatcher()

        # KNN检测来自A、B图的SIFT特征匹配，k=2
        rawMatches = matcher.knnMatch(featuresA, featuresB, 2)

        matches = []
        for m in rawMatches:
            # 当最近距离跟次近距离的比值小于ratio值时，保留此配对
            if len(m) == 2 and m[0].distance < m[1].distance * ratio:
                # 存储两个点在featuresA，featuresB中的索引值（B的索引值，A的索引值）
                matches.append((m[0].trainIdx, m[1].queryIdx))
        # 当筛选后的匹配对大于4，计算视角变换坐标值
        if len(matches) > 4:
            # 获取匹配对的点坐标
            pstA = np.float32([kpsA[i] for (_, i) in matches])
            pstB = np.float32([kpsB[i] for (i, _) in matches])
            # 计算视角变换矩阵（RANSAC过滤、迭代算法去计算矩阵H）
            (H, status) = cv2.findHomography(pstA, pstB, cv2.RANSAC, reprojThresh)
            # 返回结果
            return (matches, H, status)

    def drawMatches(self,imageA, imageB, kpsA, kpsB, matches, status):
        vis=cv2.drawMatches(imageA,  kpsA, imageB,kpsB, matches,None, status)
        return vis

调用代码：

from Stitcher import Stitcher
import cv2


def resize(pic,height):
    (h,w,s)=pic.shape
    bili=h/height
    image = cv2.resize(pic, (int(w/bili),height,))
    return image

imageA=cv2.imread(r'D:\pythonProject\NewProject\PIc\right.jpg')
imageB=cv2.imread(r'D:\pythonProject\NewProject\PIc\left.jpg')
imageA=resize(imageA,500)
imageB=resize(imageB,500)
stitcher=Stitcher()
#(result,vis)=stitcher.stitch(imageA=imageA,imageB=imageB,showMatches=True)
#cv2.imshow('ImageA',imageA)
#cv2.imshow('ImageB',imageB)
#cv2.waitKey(0)
#cv2.destroyAllWindows()
result=stitcher.stitch(imageA=imageA,imageB=imageB)
cv2.imshow('ImageA',imageA)
cv2.imshow('ImageB',imageB)
#cv2.imshow('vis',vis)
cv2.imshow('result',result)
cv2.waitKey(0)
cv2.destroyAllWindows()