An interdisciplinary team of CAS faculty recently received a $2.8 million, five-year grant from the National Science Foundation for research into computer modeling of group behavior. Margrit Betke from the Department of Computer Science will lead the project, and she will work with co-principal investigators Joyce Wong (Biomedical Engineering), Stan Sclaroff (chair, Computer Science), and Tom Kunz (Biology).
The goal of the project, titled “Intelligent Tracking Systems that Reason about Group Behavior,” is to build computational systems that have the ability to comprehend and judge the behavior of organisms as they interact as part of a group. One aspect of group behavior that the researchers will study is “movement vis a vis other members of a group.” They will record videos of wild bats in their natural environment, employ time-lapse microscopy to record the movement of cells, and capture human motion either in the Computer Science lab or outdoors. They will study the spatial organization of groups, in particular group-size choices and density patterns. They will also investigate leadership roles of individuals.
Previous research has focused on studying the behavior of a single type of organism, testing theories of behavior based predominately on simulations, without the appropriate analytical tools to automatically explore and quantify the vast number of visual data sets. An important innovative aspect of the proposed research is the systematic and comprehensive approach to reasoning about the motion of large groups of living organisms observed in video data—independent of whether they are represented by humans, animals, or cells.
Understanding the processes by which groups of animals and microorganisms behave is crucial to the effective conservation of populations and ecosystems and the management of cellular environments. The project will provide new tools to answer urgent economical and ethical questions, e.g., about the mortality of birds and bats in wind energy facilities. The project will advance knowledge across the fields of computer vision, artificial intelligence, behavioral ecology, and biomaterial engineering.