Motion intention optimization for multirotor robust video stabilization

Abstract:

In this paper we present an optimization algorithm for simultaneously detecting video freeze and obtaining the minimum number of the frame required in motion intention estimation for real time robust video stabilization on multirotor unmanned aerial vehicles. A combination of a filter and a threshold is used to the video freeze detection, and for optimizing the algorithm, we find the minimum number of frames for motion intention estimation without decrease the performance.

Año de publicación:

2017

Keywords:

• Motion smoothing
• RANSAC
• Geometric transform
• Warping
• Video stabilization
• Feature points
• filter

Fuente:

scopus