Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/PetervanLunteren/EcoAssist
Simplify camera trap image analysis with ML species recognition models based around the MegaDetector model
https://github.com/PetervanLunteren/EcoAssist
animals annotation-tool cameratraps classifier-model conservation deploy ecology linux machine-learning macos megadetector object-detection python windows yolov5
Last synced: about 1 month ago
JSON representation
Simplify camera trap image analysis with ML species recognition models based around the MegaDetector model
- Host: GitHub
- URL: https://github.com/PetervanLunteren/EcoAssist
- Owner: PetervanLunteren
- License: mit
- Created: 2022-01-29T13:43:22.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-04-13T23:08:59.000Z (5 months ago)
- Last Synced: 2024-04-14T07:12:21.913Z (5 months ago)
- Topics: animals, annotation-tool, cameratraps, classifier-model, conservation, deploy, ecology, linux, machine-learning, macos, megadetector, object-detection, python, windows, yolov5
- Language: Python
- Homepage:
- Size: 62.8 MB
- Stars: 91
- Watchers: 7
- Forks: 12
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- Funding: .github/FUNDING.yml
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Citation: citation.cff
Awesome Lists containing this project
- awesome-yolo-object-detection - PetervanLunteren/EcoAssist - code platform to train and deploy YOLOv5 object detection models. (Applications)
- open-sustainable-technology - EcoAssist - An open-source application designed to streamline the work of ecologists dealing with camera trap images. (Biosphere / Terrestrial Wildlife)
README
![]()
[![status](https://joss.theoj.org/papers/dabe3753aae2692d9908166a7ce80e6e/status.svg)](https://joss.theoj.org/papers/dabe3753aae2692d9908166a7ce80e6e)
[![Project Status: Active The project has reached a stable, usable state and is being actively developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active)
![GitHub](https://img.shields.io/github/license/PetervanLunteren/EcoAssist)
![GitHub last commit](https://img.shields.io/github/last-commit/PetervanLunteren/EcoAssist)---
[![](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86)](https://github.com/sponsors/PetervanLunteren)
Official website: https://addaxdatascience.com/ecoassist/EcoAssist is an application designed to streamline the work of ecologists dealing with camera trap images. Itβs an AI platform that allows you to analyse images with machine learning models for automatic detection, offering ecologists a way to save time and focus on conservation efforts.
![]()
![]()
![]()
![]()
## Cite
Please use the following citations if you used EcoAssist in your research.EcoAssist
[Link to paper](https://joss.theoj.org/papers/10.21105/joss.05581)
```BibTeX
@article{van_Lunteren_EcoAssist_2023,
author = {van Lunteren, Peter},
doi = {10.21105/joss.05581},
journal = {Journal of Open Source Software},
month = aug,
number = {88},
pages = {5581},
title = {{EcoAssist: A no-code platform to train and deploy custom YOLOv5 object detection models}},
url = {https://joss.theoj.org/papers/10.21105/joss.05581},
volume = {8},
year = {2023}
}
```MegaDetector
[Link to paper](https://arxiv.org/abs/1907.06772)
```BibTeX
@article{Beery_Efficient_2019,
title = {Efficient Pipeline for Camera Trap Image Review},
author = {Beery, Sara and Morris, Dan and Yang, Siyu},
journal = {arXiv preprint arXiv:1907.06772},
year = {2019}
}
```## Contribute
Interested in contributing to this project? There are always things to do. Do you feel comfortable handling one of the tasks below? [Let me know](mailto:[email protected])! And I will guide you in the right direction. Thanks!
- [ ] **Improve installation** - At the moment users still have to install dependeceies and use CLI. Perferably, we would like to package EcoAssist as a standalone folder with all dependencies.
- [ ] **Camtrap DP format** - Add a postprocess option to export results to camtrap DP format: https://camtrap-dp.tdwg.org/.
- [ ] **Improve human-in-loop** - At the moment the human-in-the-loop feature works with two separate windows. Perferably, we would like to merge these two.
- [ ] **Sequence smoothing** - There is no option to smoothen results based on sequences, yet. Dan Morris has already created [the code to do so](https://github.com/agentmorris/MegaDetector/blob/main/api/batch_processing/data_preparation/manage_local_batch.py#L1302). This needs to be implemented into the existing workflow.
- [ ] **Sequence ID** - Add column for unique sequence_id in CSV export.## Uninstall
All files are located in one folder, called `EcoAssist_files`. You can uninstall EcoAssist by simply deleting this folder. Please be aware that it's hidden, so you'll probably have to adjust your settings before you can see it (find out how to: [macOS](https://www.sonarworks.com/support/sonarworks/360003040160-Troubleshooting/360003204140-FAQ/5005750481554-How-to-show-hidden-files-Mac-and-Windows-), [Windows](https://support.microsoft.com/en-us/windows/view-hidden-files-and-folders-in-windows-97fbc472-c603-9d90-91d0-1166d1d9f4b5#WindowsVersion=Windows_11), [Linux](https://askubuntu.com/questions/232649/how-to-show-or-hide-a-hidden-file)). If you're planning on updating EcoAssist, there is no need to uninstall it first. It will do that automatically.Location on Windows
```r
# All users
βββ πProgram Files
βββ πEcoAssist_files# Single user
βββ πUsers
βββ π
βββ πEcoAssist_files
```Location on macOS
```r
βββ πApplications
βββ π.EcoAssist_files
```Location on Linux
```r
βββ πhome
βββ π
βββ π.EcoAssist_files
```