Deep Learning Object Detection Methods for Ecological Camera Trap Data

TL;DR

This paper evaluates deep learning object detection methods, specifically Faster R-CNN and YOLO v2.0, for automating the analysis of ecological camera trap images to identify and quantify animal species, demonstrating promising accuracy improvements.

Contribution

It compares the performance of two deep learning classifiers on ecological data, highlighting transfer learning's effectiveness for real-world camera trap image analysis.

Findings

Faster R-CNN achieved 93.0% accuracy on one dataset.

YOLO v2.0 achieved 76.7% accuracy on the same datasets.

Transfer learning enables effective application to ecological data.

Abstract

Deep learning methods for computer vision tasks show promise for automating the data analysis of camera trap images. Ecological camera traps are a common approach for monitoring an ecosystem's animal population, as they provide continual insight into an environment without being intrusive. However, the analysis of camera trap images is expensive, labour intensive, and time consuming. Recent advances in the field of deep learning for object detection show promise towards automating the analysis of camera trap images. Here, we demonstrate their capabilities by training and comparing two deep learning object detection classifiers, Faster R-CNN and YOLO v2.0, to identify, quantify, and localize animal species within camera trap images using the Reconyx Camera Trap and the self-labeled Gold Standard Snapshot Serengeti data sets. When trained on large labeled datasets, object recognition methods have shown success. We demonstrate their use, in the context of realistically sized ecological data sets, by testing if object detection methods are applicable for ecological research scenarios when utilizing transfer learning. Faster R-CNN outperformed YOLO v2.0 with average accuracies of 93.0\% and 76.7\% on the two data sets, respectively. Our findings show promising steps towards the automation of the labourious task of labeling camera trap images, which can be used to improve our understanding of the population dynamics of ecosystems across the planet.