RESUMO
Evidence suggests that wintering populations of long-tailed ducks along the Atlantic and Pacific coasts are in decline, but little is known about wintering populations on Lake Michigan. Researchers seek answers to basic questions regarding habitat use and migration patterns (temporal and spatial) of long-tailed ducks that winter on Lake Michigan, by using surgically implanted satellite transmitters. The processes of locating the birds, capturing and implanting satellite transmitters, and interpreting the results were challenging, and efforts relied on dedicated researchers, veterinarians, resource managers, and many volunteers.
Assuntos
Patos , Pesquisadores , Médicos Veterinários , Voluntários , Animais , Animais Selvagens , Temperatura Baixa , Great Lakes Region , Estações do Ano , Estados Unidos , United States Government Agencies , WisconsinRESUMO
Deep learning shows promise for automating detection and classification of wildlife from digital aerial imagery to support cost-efficient remote sensing solutions for wildlife population monitoring. To support in-flight orthorectification and machine learning processing to detect and classify wildlife from imagery in near real-time, we evaluated deep learning methods that address hardware limitations and the need for processing efficiencies to support the envisioned in-flight workflow. We developed an annotated dataset for a suite of marine birds from high-resolution digital aerial imagery collected over open water environments to train the models. The proposed 3-stage workflow for automated, in-flight data processing includes: 1) image filtering based on the probability of any bird occurrence, 2) bird instance detection, and 3) bird instance classification. For image filtering, we compared the performance of a binary classifier with Mask Region-based Convolutional Neural Network (Mask R-CNN) as a means of sub-setting large volumes of imagery based on the probability of at least one bird occurrence in an image. On both the validation and test datasets, the binary classifier achieved higher performance than Mask R-CNN for predicting bird occurrence at the image-level. We recommend the binary classifier over Mask R-CNN for workflow first-stage filtering. For bird instance detection, we leveraged Mask R-CNN as our detection framework and proposed an iterative refinement method to bootstrap our predicted detections from loose ground-truth annotations. We also discuss future work to address the taxonomic classification phase of the envisioned workflow.