import numpy as np
import cv2
 
class Stitcher:
 
    #拼接函數(shù)
    def stitch(self, images, ratio=0.75, reprojThresh=4.0,showMatches=False):
        #獲取輸入圖片
        (imageB, imageA) = images
        #檢測(cè)A、B圖片的SIFT關(guān)鍵特征點(diǎn)，并計(jì)算特征描述子
        (kpsA, featuresA) = self.detectAndDescribe(imageA)
        (kpsB, featuresB) = self.detectAndDescribe(imageB)
 
        # 匹配兩張圖片的所有特征點(diǎn)，返回匹配結(jié)果
        M = self.matchKeypoints(kpsA, kpsB, featuresA, featuresB, ratio, reprojThresh)
 
        # 如果返回結(jié)果為空，沒(méi)有匹配成功的特征點(diǎn)，退出算法
        if M is None:
            return None
 
        # 否則，提取匹配結(jié)果
        # H是3x3視角變換矩陣      
        (matches, H, status) = M
        # 將圖片A進(jìn)行視角變換，result是變換后圖片
        result = cv2.warpPerspective(imageA, H, (imageA.shape[1] + imageB.shape[1], imageA.shape[0]))
        self.cv_show('result', result)
        # 將圖片B傳入result圖片最左端
        result[0:imageB.shape[0], 0:imageB.shape[1]] = imageB
        self.cv_show('result', result)
        # 檢測(cè)是否需要顯示圖片匹配
        if showMatches:
            # 生成匹配圖片
            vis = self.drawMatches(imageA, imageB, kpsA, kpsB, matches, status)
            # 返回結(jié)果
            return (result, vis)
 
        # 返回匹配結(jié)果
        return result
    def cv_show(self,name,img):
        cv2.imshow(name, img)
        cv2.waitKey(0)
        cv2.destroyAllWindows()
 
    def detectAndDescribe(self, image):
        # 將彩色圖片轉(zhuǎn)換成灰度圖
        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
 
        # 建立SIFT生成器
        descriptor = cv2.xfeatures2d.SIFT_create()
        # 檢測(cè)SIFT特征點(diǎn)，并計(jì)算描述子
        (kps, features) = descriptor.detectAndCompute(image, None)
 
        # 將結(jié)果轉(zhuǎn)換成NumPy數(shù)組
        kps = np.float32([kp.pt for kp in kps])
 
        # 返回特征點(diǎn)集，及對(duì)應(yīng)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()
  
        # 使用KNN檢測(cè)來(lái)自A、B圖的SIFT特征匹配對(duì)，K=2
        rawMatches = matcher.knnMatch(featuresA, featuresB, 2)
 
        matches = []
        for m in rawMatches:
            # 當(dāng)最近距離跟次近距離的比值小于ratio值時(shí)，保留此匹配對(duì)
            if len(m) == 2 and m[0].distance < m[1].distance * ratio:
            # 存儲(chǔ)兩個(gè)點(diǎn)在featuresA, featuresB中的索引值
                matches.append((m[0].trainIdx, m[0].queryIdx))
 
        # 當(dāng)篩選后的匹配對(duì)大于4時(shí)，計(jì)算視角變換矩陣
        if len(matches) > 4:
            # 獲取匹配對(duì)的點(diǎn)坐標(biāo)
            ptsA = np.float32([kpsA[i] for (_, i) in matches])
            ptsB = np.float32([kpsB[i] for (i, _) in matches])
 
            # 計(jì)算視角變換矩陣
            (H, status) = cv2.findHomography(ptsA, ptsB, cv2.RANSAC, reprojThresh)
 
            # 返回結(jié)果
            return (matches, H, status)
 
        # 如果匹配對(duì)小于4時(shí)，返回None
        return None
 
    def drawMatches(self, imageA, imageB, kpsA, kpsB, matches, status):
        # 初始化可視化圖片，將A、B圖左右連接到一起
        (hA, wA) = imageA.shape[:2]
        (hB, wB) = imageB.shape[:2]
        vis = np.zeros((max(hA, hB), wA + wB, 3), dtype="uint8")
        vis[0:hA, 0:wA] = imageA
        vis[0:hB, wA:] = imageB
 
        # 聯(lián)合遍歷，畫出匹配對(duì)
        for ((trainIdx, queryIdx), s) in zip(matches, status):
            # 當(dāng)點(diǎn)對(duì)匹配成功時(shí)，畫到可視化圖上
            if s == 1:
                # 畫出匹配對(duì)
                ptA = (int(kpsA[queryIdx][0]), int(kpsA[queryIdx][1]))
                ptB = (int(kpsB[trainIdx][0]) + wA, int(kpsB[trainIdx][1]))
                cv2.line(vis, ptA, ptB, (0, 255, 0), 1)
 
        # 返回可視化結(jié)果
        return vis

from Stitcher import Stitcher
import cv2
 
# 讀取拼接圖片
imageA = cv2.imread("left_01.jpg")
imageB = cv2.imread("right_01.jpg")
 
# 把圖片拼接成全景圖
stitcher = Stitcher()
(result, vis) = stitcher.stitch([imageA, imageB], showMatches=True)
 
# 顯示所有圖片
cv2.imshow("Image A", imageA)
cv2.imshow("Image B", imageB)
cv2.imshow("Keypoint Matches", vis)
cv2.imshow("Result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()

pip install --user opencv-contrib-python==3.3.0.10