This repo contains the tools for training, running, and evaluating detectors and classifiers for images collected from motion-triggered camera traps. The core functionality provided is:
- Data parsing from frequently-used camera trap metadata formats into a common format
- Training and evaluation of detectors, particularly our “MegaDetector”, which does a pretty good job finding terrestrial animals in a variety of ecosystems
- Training and evaluation of species-level classifiers for specific data sets
- A Web-based demo that runs our models via a REST API that hosts them on a Web endpoint
- Miscellaneous useful tools for manipulating camera trap data
- Research experiments we’re doing around camera trap data (i.e., some directories are highly experimental and you should take them with a grain of salt)
Classifiers and detectors are trained using TensorFlow.
This repo is maintained by folks in the Microsoft AI for Earth program who like looking at pictures of animals. I mean, we want to use machine learning to support conservation too, but we also really like looking at pictures of animals.
You can read more about what we do to support camera trap researchers in our recent blog post.
This repo does not directly host camera trap data, but we work with our collaborators to make data and annotations available whenever possible on lila.science.
This repo does not extensively host models, though we will release models when they are at a level of generality that they might be useful to other people.
Speaking of models that might be useful to other people, we have trained a one-class animal detector trained on several hundred thousand bounding boxes from a variety of ecosystems. Lots more information – including download links – on the MegaDetector page.
Here’s a “teaser” image of what detector output looks like:
Image credit University of Washington.
For questions about this repo, contact [email protected].
This repo is organized into the following folders...
Code for hosting our models as an API, either for synchronous operation (e.g. for real-time inference or for our Web-based demo) or as a batch process (for large biodiversity surveys).
Code for training species classifiers on new data sets, generally trained on crops generated via an existing detector. We’ll release some classifiers soon, but more importantly, here’s a tutorial on training your own classifier using our detector and our training pipeline.
Oh, and here’s another “teaser image” of what you get at the end of training a classifier:
Code for:
- Converting frequently-used metadata formats to COCO Camera Traps format
- Creating, visualizing, and editing COCO Camera Traps .json databases
- Generating tfrecords
Source for the Web-based demo of our MegaDetector model (we’ll release the demo soon!).
Code for training and evaluating detectors.
Ongoing research projects that use this repository in one way or another; as of the time I’m editing this README, there are projects in this folder around active learning and the use of simulated environments for training data augmentation.
Random things that don’t fit in any other directory. Currently contains a single file, a not-super-useful but super-duper-satisfying and mostly-successful attempt to use OCR to pull metadata out of image pixels in a fairly generic way, to handle those pesky cases when image metadata is lost.
We use conda to manage our Python package dependencies. Conda is a package and environment management system. You can install a lightweight distribution of conda (Miniconda) for your OS via installers at https://docs.conda.io/en/latest/miniconda.html. Installing packages with conda may be slower as it optimizes package version compatibility.
Some Azure SDKs are only available on PyPI; we install them using pip as a part of the conda installation step.
The required Python packages for running utility and visualization scripts in this repo are listed in environment.yml. Scripts in some folders including api,detection and classification may require additional setup. In particular, the detection/run_tf_detector*.py scripts should use environment-detector.yml to set up the environment.
In your shell, navigate to the root directory of this repo and issue the following command to create a virtual environment via conda called cameratraps (specified in the environment file) and install the required packages:
conda env create --file environment.yml
If you run into an error while creating the environment, try updating conda to version 4.5.11 or above. Check the version of conda using conda --version.
To enter the conda virtual environment at your current shell, issue conda activate cameratraps. You should see (cameratraps) prepended to the command line prompt. Invoking python or jupyter notebook will now be using the interpreter and packages available in this virtual env.
To exit the virtual env, issue conda deactivate cameratraps.
If you need to use additional packages, add them to the environment file and run
conda env update --file environment.ymlIn some scripts, we also assume that you have the AI for Earth utilities repo (ai4eutils) cloned and its path appended to PYTHONPATH. You can append a path to PYTHONPATH for the current shell session by executing
export PYTHONPATH="$PYTHONPATH:/absolute/path/to/repo/ai4eutils"Adding this line to your ~/.bashrc modifies PYTHONPATH permanently.
Image credit USDA, from the NACTI data set.
This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit cla.microsoft.com.
When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.
This repository is licensed with the MIT license.