https://github.com/ansonhex/kdtree-obstacle-detection

https://github.com/ansonhex/kdtree-obstacle-detection

Last synced: 17 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/ansonhex/kdtree-obstacle-detection
• Owner: ansonhex
• Created: 2024-07-31T20:30:53.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-08-04T22:44:42.000Z (5 months ago)
• Last Synced: 2024-08-05T00:52:46.300Z (5 months ago)
• Language: Python
• Size: 23.1 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# KDTree Obstacle Detectcion

![detecion workflow](assets/workflow.gif)

This is an exploration using KDTree for obstacle detection with PCD (Point Cloud DAta) using Python. It includes a simple implementation of a KDTree class along with various preprocessing techniques and comparisons with other search methods.

## Requirement

* Python Version: `3.11.*`

* Install dependencies from `requreiments.txt`

```sh

pip install -r requirements.txt

```

## Explored

* Simple KDTree class implementation

* Obstacle detection using KDTree

* Preprocessing techniques:

  * Grid voxel filter

  * Plane segmentation

* Basic workflow of obstacle detection

* Comparison with Grid-based nearest search

## Reference

* Inspired by [ikd-Tree](https://github.com/hku-mars/ikd-Tree)

* LiDAR PCD Data & Preprocessing  Techniques from [Lidar-Obstacle-Detection](https://github.com/olpotkin/Lidar-Obstacle-Detection)

```

@article{cai2021ikd,

  title={ikd-Tree: An Incremental KD Tree for Robotic Applications},

  author={Cai, Yixi and Xu, Wei and Zhang, Fu},

  journal={arXiv preprint arXiv:2102.10808},

  year={2021}

}

```

## LICENSE