Meek, P. | bioRxiv Science

bioRxiv2020

U-Infuse: Democratization of Customizable AI for Object Detection

O_LIImage data is one of the primary sources of ecological data used in biodiversity conservation and management worldwide. However, classifying and interpreting large numbers of images is time and resource expensive, particularly in the context of camera trapping. Deep learning models have been used to achieve this task but are often not suited to specific applications due to their inability to generalise to new environments and inconsistent performance. Models need to be developed for specific species cohorts and environments, but the technical skills required to achieve this are a key barrier to the accessibility of this technology to ecologists. There is a strong need to democratise access to deep learning technologies by providing an easy to use software application allowing non-technical users to custom train custom object detectors. C_LIO_LIU-Infuse addresses this issue by putting the power of AI into the hands of ecologists. U-Infuse provides ecologists with the ability to train customised models using publicly available images and/or their own camera trap images, without the constraints of annotating and pre-processing large numbers of images, or specific technical expertise. U-Infuse is a free and open-source software solution that supports both multiclass and single class training and inference, allowing ecologists to access state of the art AI on their own device, customised to their application without sharing IP or sensitive data. C_LIO_LIU-Infuse provides ecological practitioners with the ability to (i) easily achieve camera trap object detection within a user-friendly GUI, generating a species distribution report, and other useful statistics, (ii) custom train deep learning models using publicly available and custom training data, (iii) achieve supervised auto-annotation of images for further training, with the benefit of editing annotations to ensure quality datasets. C_LIO_LIBroad adoption of U-Infuse by ecological practitioners will improve camera trap image analysis and processing by allowing significantly more image data to be processed with minimal expenditure of time and resources. Ease of training and reliance on transfer learning means domain-specific models can be trained rapidly, and frequently updated without the need for computer science expertise, or data sharing, protecting intellectual property and privacy. C_LI

ecology↗

bioRxiv2020

Location Invariant Animal Recognition UsingMixed Source Datasets and Deep Learning

O_LIA time-consuming challenge faced by camera trap practitioners all over the world is the extraction of meaningful data from images to inform ecological management. The primary methods of image processing used by practitioners includes manual analysis and citizen science. An increasingly popular alternative is automated image classification software. However, most automated solutions are not sufficiently robust to be deployed on a large scale. Key challenges include limited access to images for each species and lack of location invariance when transferring models between sites. This prevents optimal use of ecological data and results in significant expenditure of time and resources to annotate and retrain deep learning models. C_LIO_LIIn this study, we aimed to (a) assess the value of publicly available non-iconic FlickR images in the training of deep learning models for camera trap object detection, (b) develop an out-of-the-box location invariant automated camera trap image processing solution for ecologist using deep transfer learning and (c) explore the use of small subsets of camera trap images in optimisation of a FlickR trained deep learning model for high precision ecological object detection. C_LIO_LIWe collected and annotated a dataset of images of "pigs" (Sus scrofa and Phacochoerus africanus) from the consumer image sharing website FlickR. These images were used to achieve transfer learning using a RetinaNet model in the task of object detection. We compared the performance of this model to the performance of models trained on combinations of camera trap images obtained from five different projects, each characterised by 5 different geographical regions. Furthermore, we explored optimisation of the FlickR model via infusion of small subsets of camera trap images to increase robustness in difficult images. C_LIO_LIIn most cases, the mean Average Precision (mAP) of the FlickR trained model when tested on out of sample camera trap sites (67.21-91.92%) was significantly higher than the mAP achieved by models trained on only one geographical location (4.42-90.8%) and rivalled the mAP of models trained on mixed camera trap datasets (68.96-92.75%). The infusion of camera trap images into the FlickR training further improved AP by 5.10-22.32% to 83.60-97.02%. C_LIO_LIEcology researchers can use FlickR images in the training of automated deep learning solutions for camera trap image processing to significantly reduce time and resource expenditure by allowing the development of location invariant, highly robust out-of-the-box solutions. This would allow AI technologies to be deployed on a large scale in ecological applications. C_LI

ecology↗