Description
Hummingbirds are well equipped for hovering flight, and past studies have used image analysis to analyze the kinematics of their flapping motion [1], [2].
These studies had the benefit of using multiple cameras to pinpoint motion.
In this project, video taken with a single camera view is analyzed through segmentation with the future goal of using this information for kinematic analysis of tail oscillation.
While past studies have used techniques such as normalized cuts [3] and mean shift [4] for image segmentation, here the movement between consecutive frames is primarily utilized because the backlighting of some videos does not allow for segmentation of single frames.
References
[1] B. W. Tobalske and et. al., “Three-dimensional kinematics of hummingbird flight,” Journal of Experimental Biology, vol. 210, no. 13, pp. 2368-2382, 2007.
[2] D. L. Altshuler, “Wingbeat kinematics and motor control of yaw turns in Anna’s hummingbirds,” Journal of Experimental Biology, vol. 215, no. 23, pp. 4070-4084, 2012.
[3] J. Shi and J. Malik, “Normalized Cuts and Image Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888-905, 2000.
[4] D. Comaniciu, “Mean shift: A robust approach toward feature space analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 603- 619, 2002.
MATLAB code for image correlation from time encoded Polaris SP data
Reviews
There are no reviews yet.