Heartbeat of a Nest

Collaborators: Shaun Ahmadain, Zainul Charbiwala, John Hicks, Mohammad Rahimi, Deborah Estrin, Stefano
Soatto, Sharon Coe, Michael P. Hamiltonnest box cycle

We present a scalable end-to-end system for vision-based monitoring of natural environments, and illustrate its use for the analysis of avian nesting cycles. Our system enables automated analysis of thousands of images, where manual processing would be infeasible. We automate the analysis of raw imaging data using statistics that are tailored to the task of interest. These "features" are a representation to be fed to classiers that exploit spatial and temporal consistencies. Our testbed can detect birds with an accuracy of 82%, count eggs with an accuracy of 84%, and detect the inception of the nesting stage within a day. Our results demonstrate the challenges and potential bene ts of using imagers as biological sensors. An exploration of system performance under varying image resolution and frame rate suggest that an in situ adaptive vision system is technically feasible.

General overview: [Presentation] presented and CENS 5th Annual Research Review

Key Publications:

  • T. Ko. S. Ahmadian, J. Hicks, M. Rahimi, D. Estrin, S. Soatto, S. Coe, and M. P. Hamilton. Heartbeat of a Nest: Using imagers as biological sensors. To appear in Transactions of Sensor Networks, Vol. 6, No. 3, August 2010.
  • T. Ko, Z. M. Charbiwala, S. Ahmadian, M. Rahimi, M. B. Srivastava, S. Soatto and D. Estrin. Exploring Tradeoffs in Accuracy, Energy and Latency of Scale Invariant Feature Transform in Wireless Camera Networks. In International Conference for Distributed Smart Cameras. September 2007. [PDF] poster: [PDF]