An Automated Acoustic System to Monitor and Classify Birds

To minimize the number of birdstrikes, a common method uses microphone arrays to monitor and identify dangerous birds near the airport or critical locations in the airspace. However, it was recognized that the range of existing ground-based acoustic monitoring devices is limited to a few hundred meters. Moreover, the identification performance in low signal-to-noise environments such as airports is not very satisfactory. Intelligent Automation Inc. (IAI), University of Missouri at Columbia (UM), Detect Inc., and a group of engineers at National Institute of Standards and Technology (NIST), propose a novel system to improve bird monitoring and recognition in noisy environments. First, a circular microphone array with many concentric rings is proposed that will provide very directional and long range (a few thousand meters) acquisition of bird sounds, and can simultaneously pick up and track sound from different directions. The cost of the dish will be a few thousand dollars. The beamforming algorithm for the circular array has been developed and evaluated. Second, an efficient bird recognition algorithm is proposed which uses Hidden Markov Model (HHM) and Gaussian Mixture Models (GMM). The overall system is suitable for real-time monitoring and recognition for a large number of birds. Fusion with radar will be performed too.