https://github.com/alvgaona/2d-feature-matching
A sample app showcasing 2D feature matching with OpenCV
https://github.com/alvgaona/2d-feature-matching
cpp feature-matching opencv pixi rerun
Last synced: about 1 month ago
JSON representation
A sample app showcasing 2D feature matching with OpenCV
- Host: GitHub
- URL: https://github.com/alvgaona/2d-feature-matching
- Owner: alvgaona
- License: mit
- Created: 2024-11-24T23:35:18.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2024-11-25T00:23:37.000Z (11 months ago)
- Last Synced: 2025-03-28T00:44:20.062Z (7 months ago)
- Topics: cpp, feature-matching, opencv, pixi, rerun
- Language: C++
- Homepage:
- Size: 6.25 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 2D Feature Tracking
https://github.com/user-attachments/assets/17f30b1c-abcb-4456-a1d8-4987d51b6fe6
This project demonstrates 2D feature matching using a sequence of images from the KITTI
dataset. Multiple combinations of keypoint detectors (like FAST, BRISK, ORB, AKAZE,
SIFT) and descriptor extractors (like BRIEF, ORB, FREAK, AKAZE, SIFT) are evaluated
to find optimal pairings for feature tracking. The implementation processes a reduced
set of consecutive frames to analyze detection, description and matching performance
across different methods.
The project is integrated with Rerun.io, a visualization toolkit
that enables real-time inspection of the feature detection and matching process, making
it easier to debug and understand the behavior of different detector/descriptor combinations.
## Prerequisites
- https://pixi.sh
- https://rerun.io
## Usage
1. Install dependencies
```sh
pixi install
```
2. Build the app
```sh
pixi run build
```
3. Start the app
```sh
pixi run start
```