Real-time video stabilization without phantom movements for micro aerial vehicles

Abstract

In recent times, micro aerial vehicles (MAVs) are becoming popular for several applications as rescue, surveillance, mapping, etc. Undesired motion between consecutive frames is a problem in a video recorded by MAVs. There are different approaches, applied in video post-processing, to solve this issue. However, there are only few algorithms able to be applied in real time. An additional and critical problem is the presence of false movements in the stabilized video. In this paper, we present a new approach of video stabilization which can be used in real time without generating false movements. Our proposal uses a combination of a low-pass filter and control action information to estimate the motion intention.

Real-Time Model-Based Video Stabilization for Microaerial Vehicles

“…This phenomenon was presented in a previous article [1]. The phantom movements correspond mainly to false displacement generated by video stabilization algorithm in the scale and/or translation parameters due to the compensation of the eliminated high frequency movements in the motion smoothing process.…”

“…An alternative option is [1], where we propose estimating the motion intention of the motion parameters instead of the feature points.…”

“…In the same paper [1], we presented a proposal based on a low pass filter and the use of the control action as logical gate with hysteresis.…”

Obstacle Avoidance Based-Visual Navigation for Micro Aerial Vehicles

“…Previous works [43][44][45][46] have made experimental tests with handheld devices and onboard cameras, and the results showed undesired movements and parasitic vibrations that are significant on the plane perpendicular to the roll axis. The distortion can be modeled by a projective transformation; in our case, we use the affine model, which is a particular case of this [47].…”

Motion intention optimization for multirotor robust video stabilization

“…In [1] [2] [3], we present video stabilization algorithms based on Low-pass and Kalman Filters that can compensate the effects of the undesired movements in real time for micro aerial vehicles. However, we have not considered the problem of video freeze.…”