pysdic.display_optical_flow#

display_optical_flow(image, flow_x, flow_y, region=None, display_region=None, alpha=0.5, channel=0, norm_cmap='inferno', comp_cmap='bwr', norm_vmin=None, norm_vmax=None, comp_vmin=None, comp_vmax=None)[source]#

Display the optical flow overlaid on the given image using Matplotlib.

Parameters:

  • image (ArrayLike) – The background image with shape \((H, W)\) or \((H, W, C)\).

  • flow_x (ArrayLike) – The x-component of the optical flow (horizontal displacement) in pixels with shape \((H, W)\).

  • flow_y (ArrayLike) – The y-component of the optical flow (vertical displacement) in pixels with shape \((H, W)\).

  • region (Optional[Tuple[Integral, Integral, Integral, Integral]], optional) – A tuple specifying the region of interest in the format (x, y, width, height). If None, the entire image is displayed. Default is None.

  • display_region (Optional[Tuple[Integral, Integral, Integral, Integral]], optional) – A tuple specifying the region of the flow to display in the format (x, y, width, height). If None, the entire flow is displayed. Default is None.

  • alpha (Real, optional) – The alpha blending value for overlaying the optical flow on the image. Default is 0.5.

  • channel (Integral, optional) – The channel of the image to display if it is multi-channel. Default is 0.

  • norm_cmap (str, optional) – The colormap for the flow magnitude. Default is ‘inferno’.

  • comp_cmap (str, optional) – The colormap for the flow components. Default is ‘bwr’.

  • norm_vmin (Optional[Real], optional) – Minimum value for flow magnitude colormap normalization. Default is None.

  • norm_vmax (Optional[Real], optional) – Maximum value for flow magnitude colormap normalization. Default is None.

  • comp_vmin (Optional[Real], optional) – Minimum value for flow component colormap normalization. Default is None.

  • comp_vmax (Optional[Real], optional) – Maximum value for flow component colormap normalization. Default is None.

Returns:

Displays the optical flow overlay on the image.

Return type:

None

Raises:

  • TypeError – If the input image, flow components are not of type numpy.ndarray If the specified channel is not an integer. If the region or flow_region coordinates and size are not integers.

  • ValueError – If the input image and flow components do not have compatible shapes. If the specified channel is out of bounds. If the input image is not a 2D or 3D array or not unsigned integer type. If the region or flow_region is out of image bounds.

See also

compute_optical_flow()

Compute the optical flow between two images using the DIS method of OpenCV.

Examples

Create two example images and compute the optical flow between them.

../_images/lena_texture.png

Lena texture image used for the example.#

 1import numpy
 2import cv2
 3from pysdic import compute_optical_flow, display_optical_flow
 4from pysdic import get_lena_texture
 5
 6# Create two example images
 7image1 = get_lena_texture() # numpy array of shape (474, 474)
 8
 9# cv2 distortion to create a second image
10image2 = cv2.undistort(image1, cameraMatrix=numpy.array([[300, 0, 237], [0, 300, 237], [0, 0, 1]]), distCoeffs=numpy.array([-0.2, 0.1, 0, 0]))
11
12# Compute optical flow
13flow_x, flow_y = compute_optical_flow(image1, image2)
14
15# Select a region of interest (optional)
16display_region = (10, 10, image1.shape[1]-20, image1.shape[0]-20) # (x, y, width, height)
17
18# Display the optical flow
19display_optical_flow(image1, flow_x, flow_y, display_region=display_region)
On this page

This Page