AIDE: Accelerating imageābased ecological surveys with interactive machine learning
Ecological surveys increasingly rely on largeāscale image datasets, typically terabytes of imagery for a single survey. The ability to collect this volume of data allows surveys of unprecedented scale, at the cost of expansive volumes of photoāinterpretation labour. We present Annotation Interface for Dataādriven Ecology (AIDE), an openāsource web framework designed to alleviate the task of image annotation for ecological surveys. AIDE employs an easyātoāuse and customisable labelling interface that supports multiple users, database storage and scalability to the cloud and/or multiple machines. Moreover, AIDE closely integrates users and machine learning models into a feedback loop, where userāprovided annotations are employed to reātrain the model, and the latter is applied over unlabelled images to e.g. identify wildlife. These predictions are then presented to the users in optimised order, according to a customisable active learning criterion. AIDE has a number of deep learning models builtāin, but also accepts custom model implementations. Annotation Interface for Dataādriven Ecology has the potential to greatly accelerate annotation tasks for a wide range of researches employing image data. AIDE is openāsource and can be downloaded for free at https://github.com/microsoft/aerial_wildlife_detection.
2041-210X.13489.pdf
Publisher's version
openaccess
CC BY
1.85 MB
Adobe PDF
1609460d0aba89a3e34af2ee3cfc72a1