leomariga/pyRANSAC-3D
Python library for fitting 3D primitive shapes to point clouds with RANSAC. Detect planes, spheres, cylinders, cuboids, circles, and lines.
What it solves
It provides a way to fit primitive geometric shapes (like planes, cylinders, and spheres) to 3D point clouds, which is often difficult due to noise and outliers in the data. This is essential for tasks like 3D reconstruction, object tracking, and SLAM (Simultaneous Localization and Mapping).
How it works
The library implements the Random Sample Consensus (RANSAC) method. It takes NumPy-compatible arrays of 3D points and iteratively samples subsets of the data to find the mathematical model that best fits the most points (inliers), effectively ignoring noise.
Who it’s for
It is designed for developers and researchers working with LiDAR or depth-sensor data who need to segment geometric shapes from noisy point clouds in Python.
Highlights
- Supports a wide variety of shapes: planes, cylinders, cones, cuboids, spheres, lines, circles, and points.
- Lightweight implementation based on NumPy.
- Compatible with Open3D for visualization.
- Provides a simple API for fitting shapes with a defined threshold for inliers.
相關
- 專案
- 專案
- 專案
- 專案
- 專案