Calc Disparity Image

You are viewing an old version of the documentation. You can switch to the documentation of the latest version by clicking the top-right corner of the page.

Contents of this Step are under maintenance. If you need more information about this Step with urgency, please contact us at docs@mech-mind.net.

Function

This Step obtains a disparity image using the input rectified stereo images.

Usage Scenario

This Step is for developers and is used to debug in the passive stereo camera mode. Regular users do not need to use this Step in general application scenarios.

Input and Output

  • Input:

    1. Rectified left image of the stereo camera mode output.

    2. Rectified right image of the stereo camera mode output.

    3. The mapping matrix from camera disparity values to depth values (should be a 4 x 4 matrix).

    4. Scaling parameters for input validation (since this Step requires the original, unscaled image, if any of the scaling parameters are not 1, the Step will not run).

    5. Edge-enhanced left image (optional).

    6. Depth map for reference (optional). A passive stereo camera can leverage depth values from active stereo mode to compensate for point cloud defects. The user can input the depth map to this port.

  • Output:

    1. The output disparity image. Note: this disparity image can not be used as the depth map input to another Step before data conversion.

    2. The confidence mask (8U) for the output disparity image. Regions with large depth discontinuities will be presented with low confidences.

We Value Your Privacy

We use cookies to provide you with the best possible experience on our website. By continuing to use the site, you acknowledge that you agree to the use of cookies. If you decline, a single cookie will be used to ensure you're not tracked or remembered when you visit this website.