https://github.com/qidian213/sgm-gpu
sgm gpu实现，每个像素点可以使用不同组的p1,p2参数
https://github.com/qidian213/sgm-gpu
sgm-gpu sgm-nets
Last synced: 8 months ago
JSON representation
sgm gpu实现，每个像素点可以使用不同组的p1,p2参数
- Host: GitHub
- URL: https://github.com/qidian213/sgm-gpu
- Owner: Qidian213
- License: gpl-3.0
- Created: 2019-02-28T09:49:16.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2024-11-14T11:14:35.000Z (about 1 year ago)
- Last Synced: 2025-04-01T10:12:45.520Z (9 months ago)
- Topics: sgm-gpu, sgm-nets
- Language: C++
- Homepage:
- Size: 1.23 MB
- Stars: 8
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Semi-Global Matching on the GPU
This is the implementation of [Embedded real-time stereo estimation via Semi-Global Matching on the GPU](http://www.sciencedirect.com/science/article/pii/S1877050916306561), [D. Hernandez-Juarez](http://www.cvc.uab.es/people/dhernandez/) et al, ICCS 2016. Then rebuild to provide p1 p2 for every pixel points with a pointer.
Results for example image (left and right Images):
Results for example image (Output):
## How to compile and test
Simply use CMake and target the output directory as "build". In command line this would be (from the project root folder):
```
mkdir build
cd build
cmake ..
make
```
## How to use it
Type: `./sgm`
## Related Publications
[Embedded real-time stereo estimation via Semi-Global Matching on the GPU](http://www.sciencedirect.com/science/article/pii/S1877050916306561)
[D. Hernandez-Juarez](http://www.cvc.uab.es/people/dhernandez/), A. Chacón, A. Espinosa, D. Vázquez, J. C. Moure, and A. M. López
ICCS2016 – International Conference on Computational Science 2016
## Requirements
- OpenCV
- CUDA
- CMake
## Limitations
- Maximum disparity has to be 128
- PATH_AGGREGATION parameter must be set to 4 or 8
- Image width and height must be a divisible by 4