learn how to use preconfigured Stitcher configurations to stitch images using different camera models.
Code
C++
This tutorial's code is shown in the lines below. You can download it from here.
Note: The C++ version includes additional options such as image division (–d3) and more detailed error handling, which are not present in the Python example.
This tutorial's code is shown in the lines below. You can download it from here.
Note: The C++ version includes additional options such as image division (–d3) and more detailed error handling, which are not present in the Python example.
#!/usr/bin/env python
'''
Stitching sample
================
Show how to use Stitcher API from python in a simple way to stitch panoramas
A new instance of stitcher is created and the cv::Stitcher::stitch will do all the hard work.
cv::Stitcher::create can create stitcher in one of the predefined configurations (argument mode). See cv::Stitcher::Mode for details. These configurations will setup multiple stitcher properties to operate in one of predefined scenarios. After you create stitcher in one of predefined configurations you can adjust stitching by setting any of the stitcher properties.
If you have cuda device cv::Stitcher can be configured to offload certain operations to GPU. If you prefer this configuration set try_use_gpu to true. OpenCL acceleration will be used transparently based on global OpenCV settings regardless of this flag.
Stitching might fail for several reasons, you should always check if everything went good and resulting pano is stored in pano. See cv::Stitcher::Status documentation for possible error codes.
Camera models
There are currently 2 camera models implemented in stitching pipeline.
Homography model is useful for creating photo panoramas captured by camera, while affine-based model can be used to stitch scans and object captured by specialized devices.
Note
Certain detailed settings of cv::Stitcher might not make sense. Especially you should not mix classes implementing affine model and classes implementing Homography model, as they work with different transformations.
Try it out
If you enabled building samples you can found binary under build/bin/cpp-example-stitching. This example is a console application, run it without arguments to see help. opencv_extra provides some sample data for testing all available configurations.
to try panorama mode run:
./cpp-example-stitching --mode panorama <path to opencv_extra>/testdata/stitching/boat*
to try scans mode run (dataset from home-grade scanner):
./cpp-example-stitching --mode scans <path to opencv_extra>/testdata/stitching/newspaper*
or (dataset from professional book scanner):
./cpp-example-stitching --mode scans <path to opencv_extra>/testdata/stitching/budapest*
Note
Examples above expects POSIX platform, on windows you have to provide all files names explicitly (e.g. boat1.jpgboat2.jpg...) as windows command line does not support * expansion.
Stitching detailed (python opencv >4.0.1)
If you want to study internals of the stitching pipeline or you want to experiment with detailed configuration you can use stitching_detailed source code available in C++ or python
stitching_detailed program uses command line to get stitching parameter. Many parameters exists. Above examples shows some command line parameters possible :
Pairwise images are matched using an homography –matcher homography and estimator used for transformation estimation too –estimator homography
Confidence for feature matching step is 0.3 : –match_conf 0.3. You can decrease this value if you have some difficulties to match images
Threshold for two images are from the same panorama confidence is 0. : –conf_thresh 0.3 You can decr␂ease this value if you have some difficulties to match images
Bundle adjustment cost function is ray –ba ray
Refinement mask for bundle adjustment is xxxxx ( –ba_refine_mask xxxxx) where 'x' means refine respective parameter and '_' means don't. Refine one, and has the following format: fx,skew,ppx,aspect,ppy
Save matches graph represented in DOT language to test.txt ( –save_graph test.txt) : Labels description: Nm is number of matches, Ni is number of inliers, C is confidence
Perform wave effect correction is no (–wave_correct no)
Warp surface type is fisheye (–warp fisheye)
Blending method is multiband (–blend multiband)
Exposure compensation method is not used (–expos_comp no)
Seam estimation estimator is Minimum graph cut-based seam (–seam gc_colorgrad)