Python+opencv 影象拼接

摘要： 1. http://www.cnblogs.com/skyfsm/p/7411961.html ,給出了很好地拼接演算法實現 2.由於不是Python的,所以簡單做了一些翻譯轉成Python+opencv的實現 3.修改了原來的特徵點檢測演算法為ORB(由於sift和surf的專利...

1. ofollow,noindex" target="_blank">http://www.cnblogs.com/skyfsm/p/7411961.html ,給出了很好地拼接演算法實現

2.由於不是Python的,所以簡單做了一些翻譯轉成Python+opencv的實現

3.修改了原來的特徵點檢測演算法為ORB(由於sift和surf的專利問題)

4.結果

5.原始碼

import numpy as np
import cv2 as cv
from matplotlib import pyplot as plt
import matplotlib.gridspec as gridspec

GOOD_POINTS_LIMITED = 0.99
src = 'photoes\\homograph\\w1.jpg'
des = 'photoes\\homograph\\w2.jpg'

img1_3 = cv.imread(src,1)# 基準影象
img2_3 = cv.imread(des,1)# 拼接影象

orb = cv.ORB_create()
kp1, des1 = orb.detectAndCompute(img1_3,None)
kp2, des2 = orb.detectAndCompute(img2_3,None)

bf = cv.BFMatcher.create()

matches = bf.match(des1,des2)

matches = sorted(matches, key = lambda x:x.distance)

goodPoints =[]
for i in range(len(matches)-1):
if matches[i].distance < GOOD_POINTS_LIMITED * matches[i+1].distance:
goodPoints.append(matches[i])

# goodPoints = matches[:20] if len(matches) > 20else matches[:]
print(goodPoints)

img3 = cv.drawMatches(img1_3,kp1,img2_3,kp2,goodPoints, flags=2,outImg=None )

src_pts = np.float32([kp1[m.queryIdx].pt for m in goodPoints]).reshape(-1, 1, 2)
dst_pts = np.float32([kp2[m.trainIdx].pt for m in goodPoints]).reshape(-1, 1, 2)

M, mask = cv.findHomography( dst_pts,src_pts, cv.RHO)

# 獲取原影象的高和寬
h1,w1,p1 = img2_3.shape
h2,w2,p2 = img1_3.shape

h = np.maximum(h1,h2)
w = np.maximum(w1,w2)

_movedis = int(np.maximum(dst_pts[0][0][0],src_pts[0][0][0]))
imageTransform = cv.warpPerspective(img2_3,M,(w1+w2-_movedis,h))

M1 = np.float32([[1, 0, 0], [0, 1, 0]])
h_1,w_1,p = img1_3.shape
dst1 = cv.warpAffine(img1_3,M1,(w1+w2-_movedis, h))

dst = cv.add(dst1,imageTransform)
dst_no = np.copy(dst)

dst_target = np.maximum(dst1,imageTransform)

fig = plt.figure (tight_layout=True, figsize=(8, 18))
gs = gridspec.GridSpec (6, 2)
ax = fig.add_subplot (gs[0, 0])
ax.imshow(img1_3)
ax = fig.add_subplot (gs[0, 1])
ax.imshow(img2_3)
ax = fig.add_subplot (gs[1, :])
ax.imshow(img3)
ax = fig.add_subplot (gs[2, :])
ax.imshow(imageTransform)
ax = fig.add_subplot (gs[3, :])
ax.imshow(dst1)
ax = fig.add_subplot (gs[4, :])
ax.imshow(dst_no)
ax = fig.add_subplot (gs[5, :])
ax.imshow(dst_target)
ax.set_xlabel ('The smooth method is SO FAST !!!!')
plt.show()