标题：Gaussian process dynamic modeling of bat flapping flight
作者：Bender, Matthew ;Yang, Xu ;Chen, Hui ;Kurdila, Andrew ;Muller, Rolf
作者机构：[Bender, Matthew ;Kurdila, Andrew ;Muller, Rolf ] Department of Mechanical Engineering, Virginia Tech, Blacksburg; VA, United States;[Muller, Rolf ] S 更多
会议名称：24th IEEE International Conference on Image Processing, ICIP 2017
会议日期：17 September 2017 through 20 September 2017
来源：Proceedings - International Conference on Image Processing, ICIP
关键词：Dimensionality Reduction; Gaussian Process Dynamic Models; Manifold Estimation; Motion Capture
摘要：The flapping flight of bats can serve as an inspiration for flapping-wing air vehicles. Obtaining an understanding of bat flight requires detailed, occlusion-free kinematics data that can only be collected using large numbers of cameras. Here, we have explored the use of low-cost cameras with low frame rates that result in nonlinear, large-baseline motions in image space. To create a better model for predicting the motion of features under these circumstances, we have applied Gaussian Process Dynamic Modeling (GPDM) to manually digitized flight data in order to learn a lower dimensional manifold near which the motion evolves. The primary contribution of this work is the first nonlinear dimensionality reduction for the representation of bat flight. © 2017 IEEE.