OpenCV-Python断言错误：SAD算法-立体相机视差图计算

Question

I want to calculate Disparity map using SAD algorithm, and when I run the code I get the error Message: return stereo.compute(left_image, right_image).astype(np.float32) / 16.0 cv2.error: OpenCV(3.4.3) C:\\projects\\opencv-python\\opencv\\modules\\calib3d\\src\\stereosgbm.cpp:2156: error: (-215:Assertion failed) left.size() == right.size() && left.type() == right.type() && left.depth() == CV_8U in function 'cv::StereoSGBMImpl::compute'

My code is :

left_image = cv2.imread('left.jpg')
right_image = cv2.imread('right.jpg')

def calc_disparity(left_image, right_image):
    window_size = 3
    min_disp = 1
    num_disp = 16
    stereo = cv2.StereoSGBM_create(
        minDisparity=min_disp,
        numDisparities=num_disp,
        blockSize = 5,
        # SADWindowSize=window_size,
        uniquenessRatio=10,
        speckleWindowSize=100,
        speckleRange=32,
        disp12MaxDiff=1,
        P1=8*3*window_size**2,
        P2=32*3*window_size**2,
        # fullDP=False

    )
    return stereo.compute(left_image, right_image).astype(np.float32) / 16.0

Answer 1

Possible reasons of this assertion failure are:

• left and right image don't have the same size
• left and right image don't have the same type
• left image has wrong depth type (CV_8U is required)

Please ensure that your input images have the above conditions (same size and type).