Low-Complexity Global Motion Estimation for Aerial Vehicles

Nirmala Ramakrishnan, Alok Prakash, Thambipillai Srikanthan; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 85-93

Abstract


Global motion estimation (GME) algorithms are typically employed on aerial videos captured by on-board UAV cameras to compensate for the artificial motion induced in these video frames due to camera motion. However, existing methods for GME have high computational complexity and are therefore not suitable for on-board processing in UAVs with limited computing capabilities. In this paper, we propose a novel low complexity technique for GME that exploits the characteristics of aerial videos to only employ the minimum, yet, well-distributed features based on the scene complexity. Experiments performed on a mobile SoC platform, similar to the ones used in UAVs, confirm that the proposed technique achieves a speedup in execution time of over 40% without compromising the accuracy of the GME step when compared to a conventional method.

Related Material


[pdf]
[bibtex]
@InProceedings{Ramakrishnan_2017_CVPR_Workshops,
author = {Ramakrishnan, Nirmala and Prakash, Alok and Srikanthan, Thambipillai},
title = {Low-Complexity Global Motion Estimation for Aerial Vehicles },
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}
}