Collectives™ on Stack Overflow

Find centralized, trusted content and collaborate around the technologies you use most.

Teams

Q&A for work

Connect and share knowledge within a single location that is structured and easy to search.

How to apply `DisparityWLSFilter` to live stereo camera data using precomputed disparity map in OpenCV-Python

I am trying to post-filter my stereo cameras using cv2.ximgproc.createDisparityWLSFilter after block matching and rectification.

I have been following this tutorial and have implemented the suggestions in this answer and this answer in my code (snippet, below). However, I already have an instance of cv2.StereoBM_create , performed rectification, and computed the disparity.

    stereo = cv2.StereoBM_create()
    wls_filter = cv2.ximgproc.createDisparityWLSFilter(stereo)
    disparity = stereo.compute(Left_rect, Right_rect)
    disparity = disparity.astype(np.float32)
    # Scaling down the disparity values and normalizing them
    disparity = (disparity / 16.0 - minDisparity) / numDisparities
    # Normalize and apply a color map
    disparityImg = cv2.normalize(src=disparity, dst=None, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX,
                                 dtype=cv2.CV_8UC1)
    disparityImg = cv2.applyColorMap(disparityImg, cv2.COLORMAP_JET)
    # Applying WLS filter to remove noise
    left_image = Left_rect
    right_image = Right_rect
    left_matcher = stereo
    right_matcher = cv2.ximgproc.createRightMatcher(left_matcher)
    left_disp = left_matcher.compute(left_image, right_image)
    right_disp = right_matcher.compute(right_image, left_image)
    # Now create DisparityWLSFilter
    wls_filter = cv2.ximgproc.createDisparityWLSFilter(left_matcher)
    filtered_disp = wls_filter.filter(left_disp, left_image, disparity_map_right=right_disp)
    # Displaying the disparity map
    cv2.imshow("disparity map", disparityImg)
    cv2.imshow("filtered disparity map", filtered_disp)
The parameters for the stereoBM and wls filter are set using a GUI (see image below).
The above tutorial/code is written for two static left and right images. However, I need to apply it stereo webcams, as applied in this project.
When I run the code above, I get a blank disparity map image. Without the WLSFilter code the disparity map image shows is displayed.
I have tried feeding it my disparity map with left_matcher = disparity, but that obviously doesn't work as I need the left/right disparities separate.
I'm sure this is an easy fix/silly mistake I'm making, I just can't see it! Can anyone spot where I'm going wrong, please?
        
Thanks for contributing an answer to Stack Overflow!
Please be sure to answer the question. Provide details and share your research!
But avoid …
Asking for help, clarification, or responding to other answers.
Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.