相机必须校准才能与立体BM一起使用吗？

Question

在我的情况下，无论参数如何调整，OpenCV StereoBM深度贴图返回的数据都没有意义。在

我正在为一个涉及OpenCV的设计项目做研究，并使用立体视觉来生成深度图。我目前能够成功地加载我的两个网络相机和生成一个深度地图使用立体bm。然而，结果数据目前并不有用，正如下面的截图所示。所以我创建了一个小的python应用程序来帮助我优化StereoBM参数，但这没有帮助。在

我的问题是相机必须校准才能使用立体BM功能吗？在

如果没有，有什么方法可以帮助我改进结果（例如，提高分辨率、使用立体声BGM等）

编码

import cv2
import time
import numpy as np
from Tkinter import *

oldVal = 15
def oddVals(n):
        global oldVal
        n = int(n)
        if not n % 2:
                window_size.set(n+1 if n > oldVal else n-1)
                oldVal = window_size.get()

minDispValues = [16,32,48,64]
def minDispCallback(n):
        n = int(n)
        newvalue = min(minDispValues, key=lambda x:abs(x-float(n)))
        min_disp.set(newvalue)

# Display the sliders to control the stereo vision 
master = Tk()

master.title("StereoBM Settings");

min_disp = Scale(master, from_=16, to=64, command=minDispCallback, length=600, orient=HORIZONTAL, label="Minimum Disparities")
min_disp.pack()
min_disp.set(16)

window_size = Scale(master, from_=5, to=255, command=oddVals, length=600, orient=HORIZONTAL, label="Window Size")
window_size.pack()
window_size.set(15)

Disp12MaxDiff = Scale(master, from_=5, to=30, length=600, orient=HORIZONTAL, label="Max Difference")
Disp12MaxDiff.pack()
Disp12MaxDiff.set(0)

UniquenessRatio = Scale(master, from_=0, to=30, length=600, orient=HORIZONTAL, label="Uniqueness Ratio")
UniquenessRatio.pack()
UniquenessRatio.set(15)

SpeckleRange = Scale(master, from_=0, to=60, length=600, orient=HORIZONTAL, label="Speckle Range")
SpeckleRange.pack()
SpeckleRange.set(34)

SpeckleWindowSize = Scale(master, from_=60, to=150, length=600, orient=HORIZONTAL, label="Speckle Window Size")
SpeckleWindowSize.pack()
SpeckleWindowSize.set(100)

master.update()

vcLeft = cv2.VideoCapture(0) # Load video campture for the left camera
#vcLeft.set(cv2.cv.CV_CAP_PROP_FRAME_WIDTH,420);
#vcLeft.set(cv2.cv.CV_CAP_PROP_FRAME_HEIGHT,340);
vcLeft.set(3,640) # Set camera width
vcLeft.set(4,480) # Set camera height

vcRight = cv2.VideoCapture(1) # Load video capture for the right camera
#vcRight.set(cv2.cv.CV_CAP_PROP_FRAME_WIDTH,420);
#vcRight.set(cv2.cv.CV_CAP_PROP_FRAME_HEIGHT,340);

firstTime = time.time() # First time log

totalFramesPassed = 0 # Number of frames passed

if vcLeft.isOpened() and vcRight.isOpened():
        rvalLeft, frameLeft = vcLeft.read()
        rvalRight, frameRight = vcRight.read()

else:
        rvalLeft = False
        rvalRight = False

while rvalLeft and rvalRight: # If the cameras are opened

        rvalLeft, frameLeft = vcLeft.read()

        rvalRight, frameRight = vcRight.read()

        cv2.putText(frameLeft, "FPS : " + str(totalFramesPassed / (time.time() - firstTime)),(40, 40), cv2.FONT_HERSHEY_SIMPLEX, 0.8, 150, 2, 10)

        cv2.imshow("Left Camera", frameLeft)

        cv2.putText(frameRight, "FPS : " + str(totalFramesPassed / (time.time() - firstTime)),(40, 40), cv2.FONT_HERSHEY_SIMPLEX, 0.8, 150, 2, 10)

        cv2.imshow("Right Camera", frameRight)

        frameLeftNew = cv2.cvtColor(frameLeft, cv2.COLOR_BGR2GRAY)

        frameRightNew = cv2.cvtColor(frameRight, cv2.COLOR_BGR2GRAY)

        num_disp = 112 - min_disp.get()

        stereo = cv2.StereoBM_create(numDisparities = num_disp, blockSize = window_size.get())

        stereo.setMinDisparity(min_disp.get())

        stereo.setNumDisparities(num_disp)

        stereo.setBlockSize(window_size.get())

        stereo.setDisp12MaxDiff(Disp12MaxDiff.get())

        stereo.setUniquenessRatio(UniquenessRatio.get())

        stereo.setSpeckleRange(SpeckleRange.get())

        stereo.setSpeckleWindowSize(SpeckleWindowSize.get())

        disparity = stereo.compute(frameLeftNew, frameRightNew).astype(np.float32) / 16.0

        disp_map = (disparity - min_disp.get())/num_disp

        cv2.imshow("Disparity", disp_map)

        master.update() # Update the slider options

        key = cv2.waitKey(20)

        totalFramesPassed = totalFramesPassed + 1 # One frame passed, increment

        if key == 27:

                break


vcLeft.release()

vcRight.release()

Answer 1

我发现我们需要修正这一对才能使用StereoBM函数。此外，我发现，虽然它是更资源密集型，立体GBM功能给了我更多的最佳结果。在

如果将来有人需要校准他们的相机，您可以使用以下代码来帮助您：

# Imports
import cv2
import numpy as np

# Constants
leftCameraNumber = 2 # Number for left camera
rightCameraNumber = 1 # Number for right camera

numberOfChessRows = 6
numberOfChessColumns = 8
chessSquareSize = 30 # Length of square in millimeters

numberOfChessColumns = numberOfChessColumns - 1 # Update to reflect how many corners are inside the chess board
numberOfChessRows = numberOfChessRows - 1

objp = np.zeros((numberOfChessColumns*numberOfChessRows,3), np.float32)
objp[:,:2] = np.mgrid[0:numberOfChessRows,0:numberOfChessColumns].T.reshape(-1,2)*chessSquareSize

objectPoints = []
leftImagePoints = []
rightImagePoints = []

parameterCriteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 30, 0.001)

# Code
print("Press \"n\" when you're done caputing checkerboards.")

vcLeft = cv2.VideoCapture(leftCameraNumber) # Load video campture for the left camera
vcLeft.set(cv2.CAP_PROP_FRAME_WIDTH,640*3/2);
vcLeft.set(cv2.CAP_PROP_FRAME_HEIGHT,480*3/2);

vcRight = cv2.VideoCapture(rightCameraNumber) # Load video capture for the right camera
vcRight.set(cv2.CAP_PROP_FRAME_WIDTH,640*3/2);
vcRight.set(cv2.CAP_PROP_FRAME_HEIGHT,480*3/2);

if vcLeft.isOpened() and vcRight.isOpened():
    rvalLeft, frameLeft = vcLeft.read()
    rvalRight, frameRight = vcRight.read()

else:
    rvalLeft = False
    rvalRight = False

# Number of succesful recognitions
checkerboardRecognitions = 0

while rvalLeft and rvalRight: # If the cameras are opened

    vcLeft.grab();

    vcRight.grab();

    rvalLeft, frameLeft = vcLeft.retrieve()

    rvalRight, frameRight = vcRight.retrieve()

    frameLeftNew = cv2.cvtColor(frameLeft, cv2.COLOR_BGR2GRAY)

    frameRightNew = cv2.cvtColor(frameRight, cv2.COLOR_BGR2GRAY)

    foundPatternLeft, cornersLeft = cv2.findChessboardCorners(frameLeftNew, (numberOfChessRows, numberOfChessColumns), None, cv2.CALIB_CB_ADAPTIVE_THRESH + cv2.CALIB_CB_NORMALIZE_IMAGE + cv2.CALIB_CB_FAST_CHECK)

    foundPatternRight, cornersRight = cv2.findChessboardCorners(frameRightNew, (numberOfChessRows, numberOfChessColumns), None, cv2.CALIB_CB_ADAPTIVE_THRESH + cv2.CALIB_CB_NORMALIZE_IMAGE + cv2.CALIB_CB_FAST_CHECK)


    if foundPatternLeft and foundPatternRight: # If found corners in this frame

        # Process the images and display the count of checkboards in our array
        checkerboardRecognitions = checkerboardRecognitions + 1
        print("Checker board recognitions: " + str(checkerboardRecognitions))

        objectPoints.append(objp)

        exactCornersLeft = cv2.cornerSubPix(frameLeftNew, cornersLeft, (11, 11), (-1, -1), parameterCriteria);
        leftImagePoints.append(exactCornersLeft)

        exactCornersRight = cv2.cornerSubPix(frameRightNew, cornersRight, (11, 11), (-1, -1), parameterCriteria);
        rightImagePoints.append(exactCornersRight)

        frameLeft = cv2.drawChessboardCorners(frameLeft, (numberOfChessRows, numberOfChessColumns), (exactCornersLeft), True);

        frameRight = cv2.drawChessboardCorners(frameRight, (numberOfChessRows, numberOfChessColumns), (exactCornersRight), True);


    # Display current webcams regardless if board was found or not
    cv2.imshow("Left Camera", frameLeft)

    cv2.imshow("Right Camera", frameRight)


    key = cv2.waitKey(250) # Give the frame some time

    if key == ord('n'):

        break

cameraMatrixLeft = np.zeros( (3,3) )
cameraMatrixRight = np.zeros( (3,3) )
distortionLeft = np.zeros( (8,1) )
distortionRight = np.zeros( (8,1) )
height, width = frameLeft.shape[:2]

rms, leftMatrix, leftDistortion, rightMatrix, rightDistortion, R, T, E, F = cv2.stereoCalibrate(objectPoints, leftImagePoints, rightImagePoints,  cameraMatrixLeft, distortionLeft, cameraMatrixRight, distortionRight, (width, height),parameterCriteria, flags=0)

arr1 = np.arange(8).reshape(2, 4)
arr2 = np.arange(10).reshape(2, 5)
np.savez('camera_calibration.npz', leftMatrix=leftMatrix, leftDistortion=leftDistortion, rightMatrix=rightMatrix, rightDistortion=rightDistortion, R=R, T=T, E=E, F=F)
print("Calibration Settings Saved to File!")

print("RMS:")
print(rms)
print("Left Matrix:")
print(leftMatrix)
print("Left Distortion:")
print(leftDistortion)
print("Right Matrix:")
print(rightMatrix)
print("Right Distortion:")
print(rightDistortion)
print("R:")
print(R)
print("T:")
print(T)
print("E:")
print(E)
print("F:")
print(F)


leftRectTransform, rightRectTransform, leftProjMatrix, rightProjMatrix, _, _, _ = cv2.stereoRectify(leftMatrix, leftDistortion, rightMatrix, rightDistortion,  (width, height), R, T, alpha=-1);
leftMapX, leftMapY = cv2.initUndistortRectifyMap(leftMatrix, leftDistortion, leftRectTransform, leftProjMatrix, (width, height), cv2.CV_32FC1);
rightMapX, rightMapY = cv2.initUndistortRectifyMap(rightMatrix, rightDistortion, rightRectTransform, rightProjMatrix, (width, height), cv2.CV_32FC1);

minimumDisparities = 0
maximumDisparities = 128

stereo = cv2.StereoSGBM_create(minimumDisparities, maximumDisparities, 18)

while True: # If the cameras are opened
    vcLeft.grab();

    vcRight.grab();

    rvalLeft, frameLeft = vcLeft.retrieve()

    rvalRight, frameRight = vcRight.retrieve()

    frameLeftNew = cv2.cvtColor(frameLeft, cv2.COLOR_BGR2GRAY)

    frameRightNew = cv2.cvtColor(frameRight, cv2.COLOR_BGR2GRAY)

    leftRectified = cv2.remap(frameLeftNew, leftMapX, leftMapY, cv2.INTER_LINEAR);

    rightRectified = cv2.remap(frameRightNew, rightMapX, rightMapY, cv2.INTER_LINEAR);

    disparity = stereo.compute(leftRectified, rightRectified)

    cv2.filterSpeckles(disparity, 0, 6000, maximumDisparities);

    cv2.imshow("Normalized Disparity", (disparity/16.0 - minimumDisparities)/maximumDisparities);

    cv2.imshow("Left Camera", leftRectified)

    cv2.imshow("Right Camera", rightRectified)


    key = cv2.waitKey(10) # Give the frame some time

    if key == 27:

        break

print("Finished!")