Data

Tools

Indexes

Applications

Experiments

Open Source Science

semantic_kitti_stats

:chart_with_downwards_trend: Get some nice plots with statistics about the Semantic KITTI dataset

https://github.com/ltriess/semantic_kitti_stats

Science Score: 44.0%

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
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (12.9%) to scientific vocabulary

Keywords

analysis kitti-dataset lidar plots semantic-segmentation statistics
Last synced: 6 months ago · JSON representation ·

Repository

:chart_with_downwards_trend: Get some nice plots with statistics about the Semantic KITTI dataset

Basic Info
  • Host: GitHub
  • Owner: ltriess
  • License: mit
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 89.8 KB
Statistics
  • Stars: 25
  • Watchers: 2
  • Forks: 10
  • Open Issues: 1
  • Releases: 0
Topics
analysis kitti-dataset lidar plots semantic-segmentation statistics
Created over 6 years ago · Last pushed over 3 years ago
Metadata Files
Readme License Citation

README.md

Semantic KITTI Dataset Statistics

License: MIT

This repository holds a script that allows an analysis of the Semantic KITTI Dataset [1,2]. The main focus is on distance and label analysis. For all statistics a csv file and a plot are generated.

Some Examples: * see which label has how many points over the distance

teaser1

  • see how many points belong to a specific label in each sequence

teaser2

  • ... and many more, such as the analysis per sequence or labels over azimuth and elevation angle

Contents

Getting Started

These instructions will get you a copy of the project up and running on your local machine.

Installing

$ git clone https://github.com/ltriess/semantic_kitti_stats.git $ cd semantic_kitti_stats $ pip install requirements.txt

Get the Data

Download the data and unzip it in the same folder. * for the labels: Semantic KITTI * for the point clouds: KITTI Odometry

Running the code

The main script is analyse.py which can be called according to

``` Usage: analyse_sequence.py [OPTIONS] PATH

Options: --mode [compute|fromdata] If compute is selected, PATH must be the path to the dataset. All statistics will be calculated from the data. If fromdata is selected, PATH must be a a folder in which csv files with the computed statistics are located. --save_dir PATH Path where to save the generated graphs. If not provided, show on display. --help Show this message and exit. ```

The script first iterates over all trainval sequences and generates separate statistics for each sequence. Finally, all the sequence statistics are combined and a total analysis as well as a sequence overview is generated. There are two modes in which the script dan be called:

  • compute: PATH must point to the root directory of the dataset which contains the folders dataset/sequences/{00..10}/{velodyne/labels} according to how the dataset is extracted after the download. All statistics will be computed from the dataset and then plots will be generated. If savedir_ is set to a valid path, all the statistics will be saved to csv files for later usage.
  • fromdata_: PATH must point to the folder in which all the generated csv files are located. This is useful when the statistics are available, but a redo of the plots is needed.

In both modes, if savedir_ is set, the plots are saved as png files to the specified location. If it is not set, the plots will be displayed on the screen.

License

This project is licensed under the MIT License - see the LICENSE file for details

References

[1] J. Behley and M. Garbade and A. Milioto and J. Quenzel and S. Behnke and C. Stachniss and J. Gall, "SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences", ICCV 2019

[2] A. Geiger and P. Lenz and C. Stiller and R. Urtasun, Vision meets Robotics: The KITTI Dataset, IJRR 2013

Owner

  • Name: Larissa Triess
  • Login: ltriess
  • Kind: user
  • Company: @mercedes-benz @intervall-io

Seeing through the eyes of a self-driving car

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Triess"
  given-names: "Larissa"
  orcid: "https://orcid.org/0000-0003-0037-8460"
title: "Scripts for SemanticKITTI dataset statistics"
date-released: 2019-08-23
url: "https://github.com/ltriess/semantic_kitti_stats"

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 2
  • Average time to close issues: N/A
  • Average time to close pull requests: 1 minute
  • Total issue authors: 0
  • Total pull request authors: 2
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 1
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • dependabot[bot] (1)
  • ltriess (1)
Top Labels
Issue Labels
Pull Request Labels
dependencies (1)

Dependencies

requirements.txt pypi
  • Click ==7.0
  • matplotlib ==3.1.1
  • numpy ==1.16.4