Analysis, camera, and image files for: ecoEye, embedded vision camera for biodiversity monitoring

We need comprehensive information to manage and protect biodiversity in the face of global environmental challenges, and artificial intelligence is needed to generate that information from vast amounts of biodiversity data. Currently, vision-based monitoring methods are heterogenous; they poorly cover spatial and temporal dimensions, overly depend on humans, and are not reactive enough for adaptive management.
To mitigate these issues, we present a portable, modular, affordable, and low-power device with embedded vision for biodiversity monitoring of a wide range of terrestrial taxa. Our camera uses interchangeable lenses to resolve barely visible and remote targets, as well as customisable algorithms for blob detection, region-of-interest classification, and object detection to identify them. We showcase our system in six use cases from the ethology, landscape ecology, agronomy, pollination ecology, conservation biology, and phenology disciplines.
Using the same devices with different ..., Please refer to the paper's Materials & Methods section and its Supplementary Information., , # ZIP contents and CSV data description

[https://doi.org/10.5061/dryad.1ns1rn90j](https://doi.org/10.5061/dryad.1ns1rn90j)

## Description of the data and file structure

Each ZIP file corresponds to and is named after one of the use cases described in the manuscript (A to F). It contains:

* “analysis” subfolder: the CSV files and R scripts (\"A-F - analysis[...].R\" and \"A-F - precision and recall[...].R\") needed to reproduce the results and figures in R. The scripts only require to manually input the path to the folder where the ZIP was extracted. CSV files are described below.
* “camera” subfolder: micropython scripts (\"main.py\", \"ecofunctions.py\", etc.) and optionally TensorFlow model (\"model.tflite\") and labels file (\"labels.txt\") to replicate the camera operation. These files should be placed at the root of the SD card of the ecoEye camera.
* “samples” subfolder: 10 representative images obtained during the field deployments

### Files and variables

#### File: README.md

**Descri...