Abstract
This paper presents a proof of concept for classifying migratory birds from residential birds in Near-Field using an alternative method, by examining the nature of their flight paths, patterns, and trajectories. Multiple videos containing natural and artificial databases of flying birds were used to extract their flight trajectories. For them to fly over a long distance, migratory birds, Canadian Geese, for example, have much higher physical strength and lower body weight compared to residential birds. Therefore, due to their nature and physical limitations, migratory birds fly in folk, usually with considerably more predictable and periodic (due to their flapping motion) fight paths without drastic changes in their heading. Whereas residential birds, on the other hand, fly or sometimes glide in shorter distances and sections from point A to point B, so they can change their heading and acceleration very quickly or even in mid-air. Four (4) trajectories characteristics and observed from the bird's flight paths: turning angle, periodicity (frequency), and object pace (velocity and acceleration). Hereafter, principal component analyses were applied to reduce the number of these trajectory features from 4 to 2 parameters. Support vector machine (SVM) with Quadratic transformation kernel was then used for binary classification. Sample test results show that the prediction was <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\geq$</tex> 90% accurate. Note that classification accuracy can be improved with more true-to-life training data to cover more cases.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.