New camera technology is allowing avian ecologists to perform detailed studies of avian behavior, nesting strategies and predation in areas where it was previously impossible to gather data. Unfortunately, studies have shown mechanical triggers and a variety of sensors to be inadequate in capturing footage of small predators (e.g., snakes, rodents) or events in dense vegetation. Because of this, continuous camera recording is currently the most robust solution for avian monitoring, especially in ground nesting species. However, continuous video footage results in a data deluge, as monitoring enough nests to make biologically significant inferences results in massive amounts of data which is unclassifiable by humans alone. This project will develop a citizen science project which combines volunteer computing, where people volunteer their computers to automatically analyze video with computer vision strategies, and crowd sourcing, where people volunteer their brain power by streaming the videos and reporting observations, to analyze over a hundred thousand of hours of avian nesting video.
This collaborative proposal will address the data deluge in avian research, where data acquisition rates are greatly outpacing the ability to process that data, by gathering, storing, and analyzing nest video at unprecedented scales for evaluating hypotheses about avian reproductive ecology and predator-prey interactions. The team will develop computer vision techniques based on the scale-invariant feature transform (SIFT) and speeded up robust features (SURF) algorithms and their variants capable of identifying events involving animals with cryptic coloration in uncontrolled outdoor settings for this analysis. In addition,they will use the nesting video to develop a large human annotated archival video resource for ecologists and computer vision researchers alike, generated using crowd sourced volunteer observations validated against each other and further refined by a scientific web portal for expert analysis of the volunteered responses. An enduring citizen science project combining crowd sourcing and volunteer computing to perform the analysis of the video and use it to foster public interest and involvement from K-12 classrooms, stimulating online education in STEM disciplines is also planned.
