DeepLidar
Geographic Generalization in Airborne RGB Deep Learning Tree Detection.
https://github.com/weecology/DeepLidar
Last synced: over 1 year ago
JSON representation
Acceptance Criteria
- Revelant topics? false
- External users? true
- Open source license? false
- Active? false
- Fork? false
Repository metadata
LIDAR and RGB Deep Learning Model for Individual Tree Segmentation
- Host: GitHub
- URL: https://github.com/weecology/DeepLidar
- Owner: weecology
- Archived: true
- Created: 2018-11-13T21:47:48.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2024-01-09T12:53:23.000Z (over 1 year ago)
- Last Synced: 2024-01-21T05:04:24.455Z (over 1 year ago)
- Language: Python
- Size: 202 MB
- Stars: 48
- Watchers: 10
- Forks: 15
- Open Issues: 0
- Releases: 0
-
Metadata Files:
- Readme: README.md
README.md
Geographic Generalization in Airborne RGB Deep Learning Tree Detection
Ben. G. Weinstein, Sergio Marconi, Stephanie Bohlman, Alina Zare, Ethan White
Summary
DeepLidar is a keras retinanet implementation for predicting individual tree crowns in RGB imagery.
How can I train new data?
DeepLidar uses a semi-supervised framework for model training. For generating lidar-derived training data see (). I recommend using a conda environments to manage python dependencies.
- Create conda environment and install dependencies
conda env create --name DeepForest -f=generic_environment.yml
Clone the fork of the retinanet repo and install in local environment
conda activate DeepForest
git clone https://github.com/bw4sz/keras-retinanet
cd keras-retinanet
pip install .
- Update config paths
All paths are hard coded into _config.yml
- Train new model with new hand annotations
python train.py --retrain
How can I use pre-built models to predict new images.
Check out a demo ipython notebook: https://github.com/weecology/DeepLidar/tree/master/demo
Where are the data?
The Neon Trees Benchmark dataset is soon to be published. All are welcome to use it. Currently under curation (in progress): https://github.com/weecology/NeonTreeEvaluation/
For a static version of the dataset that reflects annotations at the time of submission, see dropbox link here
Published articles
Our first article was published in Remote Sensing and can be found here.
This codebase is constantly evolving and improving. To access the code at the time of publication, see Releases.
The results of the full model can be found on our comet page.
Owner metadata
- Name: Weecology
- Login: weecology
- Email:
- Kind: organization
- Description:
- Website: http://weecology.org
- Location:
- Twitter:
- Company:
- Icon url: https://avatars.githubusercontent.com/u/1156696?v=4
- Repositories: 93
- Last ynced at: 2023-03-11T03:45:49.249Z
- Profile URL: https://github.com/weecology
GitHub Events
Total
- Create event: 16
- Release event: 6
- Issues event: 21
- Watch event: 54
- Delete event: 9
- Issue comment event: 10
- Push event: 944
- Public event: 1
- Fork event: 15
Last Year
- Fork event: 5
- Watch event: 6
Committers metadata
Last synced: over 1 year ago
Total Commits: 1,029
Total Committers: 2
Avg Commits per committer: 514.5
Development Distribution Score (DDS): 0.002
Commits in past year: 2
Committers in past year: 1
Avg Commits per committer in past year: 2.0
Development Distribution Score (DDS) in past year: 0.0
| Name | Commits | |
|---|---|---|
| bw4sz | b****0@g****m | 1027 |
| Ethan White | e****n@w****g | 2 |
Committer domains:
Issue and Pull Request metadata
Last synced: over 1 year ago
Total issues: 12
Total pull requests: 2
Average time to close issues: about 1 year
Average time to close pull requests: less than a minute
Total issue authors: 3
Total pull request authors: 1
Average comments per issue: 0.83
Average comments per pull request: 0.0
Merged pull request: 2
Bot issues: 0
Bot pull requests: 0
Past year issues: 0
Past year pull requests: 2
Past year average time to close issues: N/A
Past year average time to close pull requests: less than a minute
Past year issue authors: 0
Past year pull request authors: 1
Past year average comments per issue: 0
Past year average comments per pull request: 0.0
Past year merged pull request: 2
Past year bot issues: 0
Past year bot pull requests: 0
Top Issue Authors
- bw4sz (10)
- MarconiS (1)
- Rotaka92 (1)
Top Pull Request Authors
- ethanwhite (2)
Top Issue Labels
Top Pull Request Labels
Dependencies
- blas 1.0
- blosc 1.14.4
- bokeh 1.0.2
- bzip2 1.0.6
- ca-certificates 2018.03.07
- certifi 2018.11.29
- click 7.0
- cloudpickle 0.6.1
- cytoolz 0.9.0.1
- dask 1.0.0
- dask-core 1.0.0
- dbus 1.13.2
- distributed 1.25.0
- expat 2.2.6
- freetype 2.9.1
- gettext 0.19.8.1
- glib 2.56.2
- hdf5 1.10.2
- heapdict 1.0.0
- icu 58.2
- intel-openmp 2019.0
- jinja2 2.10
- jpeg 9b
- libcxx 4.0.1
- libcxxabi 4.0.1
- libedit 3.1.20170329
- libffi 3.2.1
- libgfortran 3.0.1
- libiconv 1.15
- libpng 1.6.35
- libtiff 4.0.9
- locket 0.2.0
- lzo 2.10
- markupsafe 1.1.0
- mkl 2018.0.3
- mkl_fft 1.0.6
- mkl_random 1.0.1
- msgpack-python 0.5.6
- ncurses 6.1
- numexpr 2.6.8
- numpy 1.15.3
- numpy-base 1.15.3
- olefile 0.46
- openssl 1.1.1
- packaging 18.0
- pandas 0.23.4
- partd 0.3.9
- pcre 8.42
- pillow 5.3.0
- pip 10.0.1
- psutil 5.4.8
- pyopengl 3.1.1a1
- pyparsing 2.3.0
- pyqt 5.9.2
- pyqtgraph 0.10.0
- pytables 3.4.4
- python 3.6.7
- python-dateutil 2.7.5
- pytz 2018.7
- pyyaml 3.13
- qt 5.9.6
- readline 7.0
- setuptools 40.2.0
- sip 4.19.13
- six 1.12.0
- snappy 1.1.7
- sortedcontainers 2.1.0
- sqlite 3.25.2
- tblib 1.3.2
- tk 8.6.8
- toolz 0.9.0
- tornado 5.1.1
- wheel 0.31.1
- xz 5.2.4
- yaml 0.1.7
- zict 0.1.3
- zlib 1.2.11
Score: 4.564348191467836