
.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/transform/plot_fundamental_matrix.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_auto_examples_transform_plot_fundamental_matrix.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_transform_plot_fundamental_matrix.py:


=============================
Fundamental matrix estimation
=============================

This example demonstrates how to robustly estimate
`epipolar geometry <https://en.wikipedia.org/wiki/Epipolar_geometry>`
(the geometry of stereo vision) between two views using sparse ORB feature
correspondences.

The `fundamental matrix <https://en.wikipedia.org/wiki/Fundamental_matrix_(computer_vision)>`_
relates corresponding points between a pair of
uncalibrated images. The matrix transforms homogeneous image points in one image
to epipolar lines in the other image.

Uncalibrated means that the intrinsic calibration (focal lengths, pixel skew,
principal point) of the two cameras is not known. The fundamental matrix thus
enables projective 3D reconstruction of the captured scene. If the calibration
is known, estimating the essential matrix enables metric 3D reconstruction of
the captured scene.

.. GENERATED FROM PYTHON SOURCE LINES 22-98



.. image-sg:: /auto_examples/transform/images/sphx_glr_plot_fundamental_matrix_001.png
   :alt: Inlier correspondences, Histogram of disparity errors
   :srcset: /auto_examples/transform/images/sphx_glr_plot_fundamental_matrix_001.png
   :class: sphx-glr-single-img


.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    Number of matches: 223
    Number of inliers: 162






|

.. code-block:: Python


    import numpy as np
    from skimage import data
    from skimage.color import rgb2gray
    from skimage.feature import match_descriptors, ORB, plot_matched_features
    from skimage.measure import ransac
    from skimage.transform import FundamentalMatrixTransform
    import matplotlib.pyplot as plt

    img_left, img_right, groundtruth_disp = data.stereo_motorcycle()
    img_left, img_right = map(rgb2gray, (img_left, img_right))

    # Find sparse feature correspondences between left and right image.

    descriptor_extractor = ORB()

    descriptor_extractor.detect_and_extract(img_left)
    keypoints_left = descriptor_extractor.keypoints
    descriptors_left = descriptor_extractor.descriptors

    descriptor_extractor.detect_and_extract(img_right)
    keypoints_right = descriptor_extractor.keypoints
    descriptors_right = descriptor_extractor.descriptors

    matches = match_descriptors(descriptors_left, descriptors_right, cross_check=True)

    print(f'Number of matches: {matches.shape[0]}')

    # Estimate the epipolar geometry between the left and right image.
    random_seed = 9
    rng = np.random.default_rng(random_seed)

    model, inliers = ransac(
        (keypoints_left[matches[:, 0]], keypoints_right[matches[:, 1]]),
        FundamentalMatrixTransform,
        min_samples=8,
        residual_threshold=1,
        max_trials=5000,
        rng=rng,
    )

    inlier_keypoints_left = keypoints_left[matches[inliers, 0]]
    inlier_keypoints_right = keypoints_right[matches[inliers, 1]]

    print(f'Number of inliers: {inliers.sum()}')

    # Compare estimated sparse disparities to the dense ground-truth disparities.

    disp = inlier_keypoints_left[:, 1] - inlier_keypoints_right[:, 1]
    disp_coords = np.round(inlier_keypoints_left).astype(np.int64)
    disp_idxs = np.ravel_multi_index(disp_coords.T, groundtruth_disp.shape)
    disp_error = np.abs(groundtruth_disp.ravel()[disp_idxs] - disp)
    disp_error = disp_error[np.isfinite(disp_error)]

    # Visualize the results.

    fig, ax = plt.subplots(nrows=2, ncols=1)

    plt.gray()

    plot_matched_features(
        img_left,
        img_right,
        keypoints0=keypoints_left,
        keypoints1=keypoints_right,
        matches=matches[inliers],
        ax=ax[0],
        only_matches=True,
    )
    ax[0].axis("off")
    ax[0].set_title("Inlier correspondences")

    ax[1].hist(disp_error)
    ax[1].set_title("Histogram of disparity errors")

    plt.show()


.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 1.984 seconds)


.. _sphx_glr_download_auto_examples_transform_plot_fundamental_matrix.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: plot_fundamental_matrix.ipynb <plot_fundamental_matrix.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: plot_fundamental_matrix.py <plot_fundamental_matrix.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: plot_fundamental_matrix.zip <plot_fundamental_matrix.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_
