041-asift-a-new-framework-for-fully-affine-invariant-image-comparison

https://github.com/szu-advtech-2023/041-asift-a-new-framework-for-fully-affine-invariant-image-comparison

Science Score: 18.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (4.2%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: SZU-AdvTech-2023
  • Language: Cuda
  • Default Branch: main
  • Size: 3.27 MB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed over 2 years ago
Metadata Files
Citation

https://github.com/SZU-AdvTech-2023/041-ASIFT-A-New-Framework-for-Fully-Affine-Invariant-Image-Comparison/blob/main/

## Usage

### Command Syntax
```shell
ASIFT_CUDA [detectOption] [image1] [image2] [resultPath]
```


### Options
- `-origin` : Use original ASIFT.
- `-openmp` : Use original ASIFT with OpenMP for parallel processing.
- `-cudasift` : Replace SIFT in original ASIFT with CUDA-SIFT.
- `-openmp_cudasift` : Use CUDA-SIFT with OpenMP. (Image may be split due to insufficient GPU memory)
- `-rtg` : Run image rotate, tilt, and Gaussian blur on GPU.
- `-rtg_cudasift` : Run image processing on GPU using CUDA-SIFT.
- `-openmp_rtg_cudasift` : Image processing on GPU, using CUDA-SIFT and OpenMP. (Image may be split due to insufficient GPU memory)
- `-npp_cudasift` : Image processing on GPU using Nvidia 2D Image and Signal Performance Primitives with CUDA-SIFT.

### Parameters
- `[detectOption]` : Detection option as per above.
- `[image1]` : Path to the first image.
- `[image2]` : Path to the second image.
- `[resultPath]` : Path for saving the output.

### Example
```shell
ASIFT_CUDA -openmp_cudasift ./image1.jpg ./image2.jpg ./results/
```

Owner

  • Name: SZU-AdvTech-2023
  • Login: SZU-AdvTech-2023
  • Kind: organization

Citation (citation.txt)

@article{REPO041,
    author = "Morel, Jean-Michel and Yu, Guoshen",
    journal = "SIAM journal on imaging sciences",
    number = "2",
    pages = "438--469",
    title = "{ASIFT: A New Framework for Fully Affine Invariant Image Comparison}",
    volume = "2",
    year = "2009"
}

GitHub Events

Total
Last Year