Automated location invariant animal detection in camera trap images using publicly available data sources. Issue 9 (10th March 2021)

• Record Type: Journal Article
• Authors: Shepley, Andrew; Falzon, Greg; Meek, Paul; Kwan, Paul
• Is Part Of: Ecology and evolution. Volume 11:Issue 9(2021)
• Page Start: 4494
• Page End: 4506
• Publication Date: 2021-03-10
• Subjects: animal identification -- artificial intelligence -- camera trap images -- camera trapping -- deep convolutional neural networks -- deep learning -- infusion -- location invariance -- wildlife ecology -- wildlife monitoring; Ecology -- Periodicals; Evolution -- Periodicals; 577.05
• DOI: 10.1002/ece3.7344
• Languages: English
• ISSNs: 2045-7758

Abstract

Abstract: A time‐consuming challenge faced by camera trap practitioners is the extraction of meaningful data from images to inform ecological management. An increasingly popular solution is automated image classification software. However, most solutions are not sufficiently robust to be deployed on a large scale due to lack of location invariance when transferring models between sites. This prevents optimal use of ecological data resulting in significant expenditure of time and resources to annotate and retrain deep learning models. We present a method ecologists can use to develop optimized location invariant camera trap object detectors by (a) evaluating publicly available image datasets characterized by high intradataset variability in training deep learning models for camera trap object detection and (b) using small subsets of camera trap images to optimize models for high accuracy domain‐specific applications. We collected and annotated three datasets of images of striped hyena, rhinoceros, and pigs, from the image‐sharing websites FlickR and iNaturalist (FiN), to train three object detection models. We compared the performance of these models to that of three models trained on the Wildlife Conservation Society and Camera CATalogue datasets, when tested on out‐of‐sample Snapshot Serengeti datasets. We then increased FiN model robustness by infusing small subsets of camera trap images into training. In all experiments, the mean Average Precision (mAP) of the FiN trained models was significantly higher (82.33%–88.59%) than that achieved by the models trained only on camera trap datasets (38.5%–66.74%). Infusion further improved mAP by 1.78%–32.08%. Ecologists can use FiN images for training deep learning object detection solutions for camera trap image processing to develop location invariant, robust, out‐of‐the‐box software. Models can be further optimized by infusion of 5%–10% camera trap images into training data. This would allow AI technologies to be deployed on a large scale in ecological applications. Datasets and code related to this study are open source and available on this repository: https://doi.org/10.5061/dryad.1c59zw3tx . Abstract : Achieve location invariant camera trap object detectors by using publicly available image data. Optimize object detectors for domain‐specific application using infusion of small subsets of camera trap images.