pandora.cpp.img_tools_cpp
Functions
|
Find valid neighbors along directions |
|
Interpolation of the input image to resolve invalid (nodata) pixels. |
Module Contents
- pandora.cpp.img_tools_cpp.find_valid_neighbors(dirs, disp, valid, row, col, msk_pixel_invalid)[source]
Find valid neighbors along directions
- Parameters:
dirs (2D np.ndarray (row, col)) – directions in which the valid neighbors will be searched, around the (row, col) pixel. Ex: [[0,1],[1,0],[0,-1],[-1,0]] to search in the axis-aligned cross centered on the pixel.
disp (2D np.ndarray (row, col)) – disparity map
valid (2D np.ndarray (row, col)) – validity mask
row (int) – row current value
col (int) – col current value
msk_pixel_invalid (int) – value for the PANDORA_MSK_PIXEL_INVALID constant in pandora.constants
- Returns:
valid neighbors
- Return type:
2D np.ndarray
- pandora.cpp.img_tools_cpp.interpolate_nodata_sgm(img: numpy.ndarray, valid: numpy.ndarray, msk_pixel_invalid: int, msk_pixel_filled_nodata: int) Tuple[numpy.ndarray, numpy.ndarray][source]
Interpolation of the input image to resolve invalid (nodata) pixels. Interpolate invalid pixels by finding the nearest correct pixels in 8 different directions and use the median of their disparities.
HIRSCHMULLER, Heiko. Stereo processing by semiglobal matching and mutual information. IEEE Transactions on pattern analysis and machine intelligence, 2007, vol. 30, no 2, p. 328-341.
- Parameters:
img (2D np.ndarray (row, col)) – input image
valid (2D np.ndarray (row, col)) – validity mask
msk_pixel_invalid (int) – value for the PANDORA_MSK_PIXEL_INVALID constant in pandora.constants
msk_pixel_filled_nodata (int) – value for the PANDORA_MSK_PIXEL_FILLED_NODATA constant in pandora.constants
- Returns:
the interpolate input image, with the validity mask update :
If out & PANDORA_MSK_PIXEL_FILLED_NODATA != 0 : Invalid pixel : filled nodata pixel
- Return type:
tuple(2D np.array (row, col), 2D np.array (row, col))