https://github.com/decadenza/directstereorectification

"Rectifying Homographies for Stereo Vision: Analytical Solution for Minimal Distortion": algorithm to compute the optimal rectifying homographies that minimise perspective distortion.
https://github.com/decadenza/directstereorectification

opencv python stereo-algorithms stereo-calibration stereo-rectification stereo-vision

Last synced: 6 days ago
JSON representation

"Rectifying Homographies for Stereo Vision: Analytical Solution for Minimal Distortion": algorithm to compute the optimal rectifying homographies that minimise perspective distortion.

• Host: GitHub
• URL: https://github.com/decadenza/directstereorectification
• Owner: decadenza
• License: gpl-3.0
• Created: 2020-04-30T17:11:56.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2022-11-07T12:54:11.000Z (about 2 years ago)
• Last Synced: 2024-11-01T21:42:26.377Z (13 days ago)
• Topics: opencv, python, stereo-algorithms, stereo-calibration, stereo-rectification, stereo-vision
• Language: Python
• Homepage:
• Size: 565 KB
• Stars: 27
• Watchers: 2
• Forks: 5
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Direct Stereo Rectification

Here you can find the algorithm for stereo rectification. This algorithm computes the rectifying homographies that minimize perspective distortion.

Our method does not use optimisation libraries and provides a closed-form solution.

It is an improvement of the approach originally introduced by Charles Loop and Zhengyou Zhang in _“Computing rectifying homographies for stereo vision”_ (1999), DOI: 10.1109/CVPR.1999.786928.

Video presentation [YouTube link](https://youtu.be/oTkYWsB3KTk).

Full details in our **paper**:

**Lafiosca, P., Ceccaroni, M. (2022). Rectifying Homographies for Stereo Vision: Analytical Solution for Minimal Distortion. In: Arai, K. (eds) Intelligent Computing. SAI 2022. Lecture Notes in Networks and Systems, vol 507. Springer, Cham. https://doi.org/10.1007/978-3-031-10464-0_33**

Pre-print available [here](https://arxiv.org/abs/2203.00123).

Please, if you find this useful, **cite** as:

```

@inproceedings{LafioscaDirectStereoRectification,

    author  = {Lafiosca, Pasquale and Ceccaroni, Marta},

    title   = {Rectifying Homographies for Stereo Vision: Analytical Solution for Minimal Distortion},

    year    = {2022},

    journal = {Lecture Notes in Networks and Systems},

    booktitle = {Intelligent Computing},

    isbn    = {978-3-031-10464-0},

    volume  = {507},

    pages   = {484--503},

    doi     = {10.1007/978-3-031-10464-0_33},

    url     = {https://doi.org/10.1007/978-3-031-10464-0_33},

    publisher = {Springer International Publishing}

}

```

## Dependencies

- Python 3 (tested with version 3.8.2)

- NumPy (tested with version 1.18.2)

Install as:

```

pip3 install numpy

```

OpenCV is required for the example only. You can install it with:

```

pip3 install opencv-contrib-python

```

## Usage

Try it with:

```

python3 example.py

```

Refer to comments in [example.py](example.py) and [rectification.py](rectification.py).

## Disclamer

The code is provided "as is" wihout any warranty. For details see [LICENSE](LICENSE) file.