Performs block-matching to estimate pixel-wise disparities between two images
This application allows one to performs block-matching to estimate pixel-wise disparities between two images. One must chose block-matching method and input masks (related to the left and right input image) of pixels for which the disparity should be investigated. Additionally, two criteria can be optionally used to disable disparity investigation for some pixel: a no-data value, and a threshold on the local variance. This allows one to speed-up computation by avoiding to investigate disparities that will not be reliable anyway. For efficiency reasons, if the optimal metric values image is desired, it will be concatenated to the output image (which will then have three bands : horizontal disparity, vertical disparity and metric value). One can split these images afterward.
This section describes in details the parameters available for this application. Table 4.104, page 664 presents a summary of these parameters and the parameters keys to be used in command-line and programming languages. Application key is BlockMatching.
Parameter key | Parameter type |
Parameter description |
io | Group |
Input and output data |
io.inleft | Input image |
Left input image |
io.inright | Input image |
Right input image |
io.out | Output image |
The output disparity map |
io.outmask | Output image |
The output mask corresponding to all criterions |
io.outmetric | Boolean |
Output optimal metric values as well |
mask | Group |
Image masking parameters |
mask.inleft | Input image |
Discard left pixels from mask image |
mask.inright | Input image |
Discard right pixels from mask image |
mask.nodata | Float |
Discard pixels with no-data value |
mask.variancet | Float |
Discard pixels with low local variance |
bm | Group |
Block matching parameters |
bm.metric | Choices |
Block-matching metric |
bm.metric ssd | Choice |
Sum of Squared Distances |
bm.metric ncc | Choice |
Normalized Cross-Correlation |
bm.metric lp | Choice |
Lp pseudo-norm |
bm.metric.lp.p | Float |
p value |
bm.radius | Int |
Radius of blocks |
bm.minhd | Int |
Minimum horizontal disparity |
bm.maxhd | Int |
Maximum horizontal disparity |
|
||
bm.minvd | Int |
Minimum vertical disparity |
bm.maxvd | Int |
Maximum vertical disparity |
bm.subpixel | Choices |
Sub-pixel interpolation |
bm.subpixel none | Choice |
None |
bm.subpixel parabolic | Choice |
Parabolic |
bm.subpixel triangular | Choice |
Triangular |
bm.subpixel dichotomy | Choice |
Dichotomy |
bm.step | Int |
Computation step |
bm.startx | Int |
X start index |
bm.starty | Int |
Y start index |
bm.medianfilter | Group |
Median filtering |
bm.medianfilter.radius | Int |
Radius |
bm.medianfilter.incoherence | Float |
Incoherence threshold |
bm.initdisp | Choices |
Initial disparities |
bm.initdisp none | Choice |
None |
bm.initdisp uniform | Choice |
Uniform initial disparity |
bm.initdisp maps | Choice |
Initial disparity maps |
bm.initdisp.uniform.hdisp | Int |
Horizontal initial disparity |
bm.initdisp.uniform.vdisp | Int |
Vertical initial disparity |
bm.initdisp.uniform.hrad | Int |
Horizontal exploration radius |
|
||
bm.initdisp.uniform.vrad | Int |
Vertical exploration radius |
bm.initdisp.maps.hmap | Input image |
Horizontal initial disparity map |
bm.initdisp.maps.vmap | Input image |
Vertical initial disparity map |
bm.initdisp.maps.hrad | Int |
Horizontal exploration radius |
bm.initdisp.maps.vrad | Int |
Vertical exploration radius |
ram | Int |
Available RAM (Mb) |
inxml | XML input parameters file |
Load otb application from xml file |
outxml | XML output parameters file |
Save otb application to xml file |
|
||
|
||
|
||
|
||
|
Input and output data This group of parameters allows setting the input and output images.
Image masking parameters This group of parameters allows determining the masking parameters to prevent disparities estimation for some pixels of the left image
Block matching parameters This group of parameters allow tuning the block-matching behaviour
Available choices are:
Available choices are:
Available choices are:
Available RAM (Mb) Available memory for processing (in MB)
Load otb application from xml file Load otb application from xml file
Save otb application to xml file Save otb application to xml file
To run this example in command-line, use the following:
To run this example from Python, use the following code snippet:
None
This application has been written by OTB-Team.
These additional ressources can be useful for further information: