标定针孔相机的代码为:
import cv2
import numpy as np
import glob
# 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_MAX_ITER | cv2.TERM_CRITERIA_EPS, 30, 0.001)
# 获取标定板角点的位置
objp = np.zeros((4 * 7, 3), np.float32)
objp[:, :2] = np.mgrid[0:7, 0:4].T.reshape(-1, 2) # 将世界坐标系建在标定板上,所有点的Z坐标全部为0,所以只需要赋值x和y
obj_points = [] # 存储3D点
img_points = [] # 存储2D点
images = glob.glob("F:\\adataset\\calibration\\pinhole\\bag1_300\\*.jpg")
#images = glob.glob("C:/Users/lenovo/Desktop/fishcali/last/8828/*.png")
#images = glob.glob("C:/Users/lenovo/Desktop/fishcali/calipictures/new8828-25/*.png")
i=0;
for fname in images:
#print("a")
img = cv2.imread(fname)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
size = gray.shape[::-1]
ret, corners = cv2.findChessboardCorners(gray, (7, 4), None)
#print(corners)
if ret:
obj_points.append(objp)
corners2 = cv2.cornerSubPix(gray, corners, (5, 5), (-1, -1), criteria) # 在原角点的基础上寻找亚像素角点
#print(corners2)
if [corners2]:
img_points.append(corners2)
else:
img_points.append(corners)
cv2.drawChessboardCorners(img, (7, 4), corners, ret) # 记住,OpenCV的绘制函数一般无返回值
i+=1;
cv2.imwrite('./pyresults/conimg'+str(i)+'.png', img)
cv2.waitKey(1500)
else:
print(str(fname))
print(len(img_points))
cv2.destroyAllWindows()
# 标定
ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(obj_points, img_points, size, None, None)
print("ret:", ret)
print("内参矩阵mtx:\n", mtx) # 内参数矩阵
print("畸变系数dist:\n", dist) # 畸变系数 distortion cofficients = (k_1,k_2,p_1,p_2,k_3)
print("旋转向量rvecs:\n", rvecs) # 旋转向量 # 外参数
print("平移向量tvecs:\n", tvecs ) # 平移向量 # 外参数
print("-----------------------------------------------------")
img = cv2.imread(images[2])
h, w = img.shape[:2]
print("调节视场大小后的相机内参为:\n")
newcameramtx, roi = cv2.getOptimalNewCameraMatrix(mtx,dist,(w,h),1,(w,h))#显示更大范围的图片(正常重映射之后会删掉一部分图像)
print (newcameramtx)
print("------------------使用undistort函数-------------------")
dst = cv2.undistort(img,mtx,dist,None,newcameramtx)
x,y,w,h = roi
dst1 = dst[y:y+h,x:x+w]
cv2.imwrite('./pyresults/calibresult3.png', dst1)
cv2.imshow("original", img)
cv2.imshow("undistorted", dst1)
print ("dst的大小为:", dst1.shape)
cv2.waitKey(0)
cv2.destroyAllWindows()
标定鱼目相机的代码为:
# -*- coding: utf-8 -*-
import yaml
import cv2
import numpy as np
import glob
CHECKERBOARD = (4, 7)
subpix_criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 30, 0.1)
calibration_flags = cv2.fisheye.CALIB_RECOMPUTE_EXTRINSIC + cv2.fisheye.CALIB_CHECK_COND + cv2.fisheye.CALIB_FIX_SKEW
objp = np.zeros((1, CHECKERBOARD[0] * CHECKERBOARD[1], 3), np.float32)
objp[0, :, :2] = np.mgrid[0:CHECKERBOARD[0], 0:CHECKERBOARD[1]].T.reshape(-1, 2)
_img_shape = None
objpoints = [] # 3d point in real world space
imgpoints = [] # 2d points in image plane.
#images = glob.glob('C:/Users/lenovo/Desktop/fishcali/last/8827/*.jpg')
images = glob.glob('D:\\adataset\\calibration\\newfisheye\\8830\\midleft1/*.jpg')
for fname in images:
img = cv2.imread(fname)
if _img_shape == None:
_img_shape = img.shape[:2]
else:
assert _img_shape == img.shape[:2], "All images must share the same size."
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Chess board corners
ret, corners = cv2.findChessboardCorners(gray, CHECKERBOARD,
cv2.CALIB_CB_ADAPTIVE_THRESH + cv2.CALIB_CB_FAST_CHECK + cv2.CALIB_CB_NORMALIZE_IMAGE)
# Image points (after refinin them)
if ret == True:
objpoints.append(objp)
cv2.cornerSubPix(gray, corners, (3, 3), (-1, -1), subpix_criteria)
imgpoints.append(corners)
N_OK = len(objpoints)
K = np.zeros((3, 3))
D = np.zeros((4, 1))
rvecs = [np.zeros((1, 1, 3), dtype=np.float64) for i in range(N_OK)]
tvecs = [np.zeros((1, 1, 3), dtype=np.float64) for i in range(N_OK)]
rms, _, _, _, _ = \
cv2.fisheye.calibrate(
objpoints,
imgpoints,
gray.shape[::-1],
K,
D,
rvecs,
tvecs,
calibration_flags,
(cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 30, 1e-6)
)
print("Found " + str(N_OK) + " valid images for calibration")
print("DIM=" + str(_img_shape[::-1]))
print("K=np.array(" + str(K.tolist()) + ")")
print("D=np.array(" + str(D.tolist()) + ")")
DIM = _img_shape[::-1]
balance = 1
dim2 = None
dim3 = None
img = cv2.imread(images[0])
dim1 = img.shape[:2][::-1] # dim1 is the dimension of input image to un-distort
assert dim1[0] / dim1[1] == DIM[0] / DIM[
1], "Image to undistort needs to have same aspect ratio as the ones used in calibration"
if not dim2:
dim2 = dim1
if not dim3:
dim3 = dim1
scaled_K = K * dim1[0] / DIM[0] # The values of K is to scale with image dimension.
scaled_K[2][2] = 1.0 # Except that K[2][2] is always 1.0
# This is how scaled_K, dim2 and balance are used to determine the final K used to un-distort image. OpenCV document failed to make this clear!
new_K = cv2.fisheye.estimateNewCameraMatrixForUndistortRectify(scaled_K, D, dim2, np.eye(3), balance=balance)#newK 是去畸变后的K
map1, map2 = cv2.fisheye.initUndistortRectifyMap(scaled_K, D, np.eye(3), new_K, dim3, cv2.CV_16SC2)
undistorted_img = cv2.remap(img, map1, map2, interpolation=cv2.INTER_LINEAR, borderMode=cv2.BORDER_CONSTANT)
data = {'dim1': dim1,
'dim2': dim2,
'dim3': dim3,
'K': np.asarray(K).tolist(),
'D': np.asarray(D).tolist(),
'new_K': np.asarray(new_K).tolist(),
'scaled_K': np.asarray(scaled_K).tolist(),
'balance': balance}
import json
with open("kannala_8828.json", "w") as f:
json.dump(data, f)
cv2.imshow("undistorted", undistorted_img)
img2 = cv2.imread(images[0])
cv2.imshow("none undistorted", img2)
cv2.waitKey(0)
cv2.destroyAllWindows()