三维测量与建模笔记 - 3 Python Opencv实现相机标定

import cv2
import numpy as np
import glob
import matplotlib.pyplot as plt

cv2.__version__
#参考链接
#https://docs.opencv.org/3.4/dc/dbb/tutorial_py_calibration.html


#相关参数
#设置寻找亚像素角点的参数，采用的停止准则是最大循环次数30和最大误差容限0.001
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 30, 0.001) # 阈值
#棋盘格每行每列方块角点个数
w = 9
h = 6
#棋盘格方块边长(mm)
side = 10

#世界坐标下的棋盘格角点坐标如(0,0,0), (1,0,0), (2,0,0) ....,(8,5,0)，去掉Z坐标，记为二维矩阵
objp = np.zeros((w*h,3), np.float32)
objp[:,:2] = np.mgrid[0:w,0:h].T.reshape(-1,2)
objp = objp*side  # 边长side(mm)

#保存图片中的角点
world_points = [] #世界坐标系
img_points = [] #相平面坐标系

#拍摄的棋盘格图像文件列表
images = glob.glob('./imgs/*.jpg')
print("Image Files:",images)


#读取所有图片,检测角点,拿到世界坐标和相平面坐标
i=0
for fname in images:

    img = cv2.imread(fname)
    # 获取画面中心点
    #获取图像的长宽
    h1, w1 = img.shape[0], img.shape[1]
    gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
    u, v = img.shape[:2]
    # 找到棋盘格角点
    ret, corners = cv2.findChessboardCorners(gray, (w,h),None)
    # 如果找到足够点对，将其存储起来
    if ret == True:
        print("i:", i)
        i = i+1
        # 在原角点的基础上寻找亚像素角点
        cv2.cornerSubPix(gray,corners,(11,11),(-1,-1),criteria)
        #追加进入世界三维点和平面二维点中
        world_points.append(objp)
        img_points.append(corners)
        # 将角点在图像上显示
        cv2.drawChessboardCorners(img, (w,h), corners, ret)
        cv2.namedWindow('findCorners', cv2.WINDOW_NORMAL)
        cv2.resizeWindow('findCorners', 640, 480)
        cv2.imshow('findCorners',img)
        cv2.waitKey(1000)
cv2.destroyAllWindows()

#进行标定
ret, mtx, dist, rvecs, tvecs = \
    cv2.calibrateCamera(world_points, img_points, gray.shape[::-1], None, None)
print("Error:", ret)
print("Instrinsic Matrix:\n",mtx)      # 内参数矩阵
print("Distortion Coeff:\n", dist   )   # 畸变系数   distortion cofficients = (k_1,k_2,p_1,p_2,k_3)
print("Rotation Vectors:\n",rvecs)   # 旋转向量  # 外参数
print("Translation Vectors:\n",tvecs  )  # 平移向量  # 外参数

#使用去畸变参数
img = cv2.imread('./imgs/6.jpg')
newcameramtx, roi = cv2.getOptimalNewCameraMatrix(mtx, dist, (u, v), 0, (u, v))
# 纠正畸变
dst1 = cv2.undistort(img, mtx, dist, None, newcameramtx)

mapx,mapy=cv2.initUndistortRectifyMap(mtx,dist,None,newcameramtx,(w1,h1),5)
dst2=cv2.remap(img,mapx,mapy,cv2.INTER_LINEAR)
# 裁剪图像，输出纠正畸变以后的图片
x, y, w1, h1 = roi
dst1 = dst1[y:y + h1, x:x + w1]

plt.figure(1, figsize=(8,6), dpi=100)
plt.imshow(img)

plt.figure(1, figsize=(8,6), dpi=100)
plt.imshow(dst1)

plt.figure(1, figsize=(8,6), dpi=100)
plt.imshow(dst2)