Abstract
Aerial imagery surveys are commonly used in marine mammal research to determine population size, distribution and habitat use. Analysis of aerial photos involves hours of manually identifying individuals present in each image and converting raw counts into useable biological statistics. Our research proposes the use of deep learning algorithms to increase the efficiency of the marine mammal research workflow. To test the feasibility of this proposal, the existing YOLOv4 convolutional neural network model was trained to detect belugas, kayaks and motorized boats in oblique drone imagery, collected from a stationary tethered system. Automated computer-based object detection achieved the following precision and recall, respectively, for each class: beluga = 74%/72%; boat = 97%/99%; and kayak = 96%/96%. We then tested the performance of computer vision tracking of belugas and occupied watercraft in drone videos using the DeepSORT tracking algorithm, which achieved a multiple-object tracking accuracy (MOTA) ranging from 37% to 88% and multiple object tracking precision (MOTP) between 63% and 86%. Results from this research indicate that deep learning technology can detect and track features more consistently than human annotators, allowing for larger datasets to be processed within a fraction of the time while avoiding discrepancies introduced by labeling fatigue or multiple human annotators.
Highlights
Marine wildlife population statistics provide information on the success of these species under human influence and are used to develop conservation strategies for individual species and populations
Considering each class individually, it is apparent that the model is the least accurate at detecting belugas, which accounts for the majority of the false positives and false negatives (Table 2)
False positive occurrence is related to belugas generating water disturbances while they are near the water surface (Figure 4)
Summary
Marine wildlife population statistics provide information on the success of these species under human influence and are used to develop conservation strategies for individual species and populations. An increasing threat for Arctic marine wildlife is noise pollution generated by shipping traffic and resource exploration, which can mask communication between individuals and increase mammal stress levels, leading to a lowered immune response and reproductive success (Rolland et al 2012; Erbe et al 2016). Another rapidly increasing source of anthropogenic influence on marine wildlife is ecotourism (Giampiccoli et al 2020), the impacts of these activities are dependent on the species and population in question. The range in response to anthropogenic activities based on species and population highlights the importance of researching the influence of human activities on wildlife at a group or population scale
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
