86 lines
3.0 KiB
Python
86 lines
3.0 KiB
Python
|
|
#retval, corners = cv2.findChessboardCorners(image,patternSize, flags)
|
|
|
|
import cv2
|
|
import numpy as np
|
|
|
|
# Define the size of the chessboard
|
|
chessboard_size = (8,5)
|
|
|
|
# Define the object points of the chessboard
|
|
object_points = np.zeros((np.prod(chessboard_size), 3), dtype=np.float32)
|
|
object_points[:, :2] = np.mgrid[0:chessboard_size[0], 0:chessboard_size[1]].T.reshape(-1, 2)
|
|
|
|
# Create arrays to store the object points and image points from all the images
|
|
object_points_array = []
|
|
image_points_array1 = []
|
|
image_points_array2 = []
|
|
|
|
# Load the images
|
|
images = []
|
|
images.append(cv2.imread("/home/ros/Bureau/ca_ur5/1.jpg"))
|
|
# Add more images as needed
|
|
|
|
# Loop through each image and find the chessboard corners
|
|
for image in images:
|
|
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
|
|
|
|
# Find the chessboard corners
|
|
found, corners = cv2.findChessboardCorners(gray, chessboard_size, None)
|
|
|
|
# If the corners are found, add the object points and image points to the arrays
|
|
if found:
|
|
object_points_array.append(object_points)
|
|
image_points_array1.append(corners)
|
|
|
|
# Calibrate the camera using the object points and image points
|
|
ret, camera_matrix, distortion_coefficients, rotation_vectors, translation_vectors = cv2.calibrateCamera(
|
|
object_points_array, image_points_array1, gray.shape[::-1], None, None)
|
|
|
|
# Print the camera matrix and distortion coefficients
|
|
print("Camera matrix:")
|
|
print(camera_matrix)
|
|
print("Distortion coefficients:")
|
|
print(distortion_coefficients)
|
|
|
|
|
|
# Load the images
|
|
images = []
|
|
images.append(cv2.imread("/home/ros/Bureau/ca_ur5/2.jpg"))
|
|
# Add more images as needed
|
|
|
|
# Loop through each image and find the chessboard corners
|
|
for image in images:
|
|
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
|
|
|
|
# Find the chessboard corners
|
|
found, corners = cv2.findChessboardCorners(gray, chessboard_size, None)
|
|
|
|
# If the corners are found, add the object points and image points to the arrays
|
|
if found:
|
|
object_points_array.append(object_points)
|
|
image_points_array2.append(corners)
|
|
|
|
# Calibrate the camera using the object points and image points
|
|
ret, camera_matrix, distortion_coefficients, rotation_vectors, translation_vectors = cv2.calibrateCamera(
|
|
object_points_array, image_points_array2, gray.shape[::-1], None, None)
|
|
|
|
# Print the camera matrix and distortion coefficients
|
|
print("Camera matrix:")
|
|
print(camera_matrix)
|
|
print("Distortion coefficients:")
|
|
print(distortion_coefficients)
|
|
|
|
print("Stereo calib")
|
|
|
|
flags = 0
|
|
flags |= cv2.CALIB_FIX_INTRINSIC
|
|
# Here we fix the intrinsic camara matrixes so that only Rot, Trns, Emat and Fmat are calculated.
|
|
# Hence intrinsic parameters are the same
|
|
|
|
criteria_stereo= (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 30, 0.001)
|
|
|
|
|
|
# This step is performed to transformation between the two cameras and calculate Essential and Fundamenatl matrix
|
|
retS, new_mtxL, distL, new_mtxR, distR, Rot, Trns, Emat, Fmat = cv2.stereoCalibrate(object_points_array, image_points_array1, image_points_array2, new_mtxL, distL, new_mtxR, distR, imgL_gray.shape[::-1], criteria_stereo, flags)
|