Abstract
The growing use of cameras embedded in autonomous robotic platforms and worn by people is increasing the importance of accurate global motion estimation (GME). However, existing GME methods may degrade considerably under illumination variations. In this paper, we address this problem by proposing a biologically-inspired GME method that achieves high estimation accuracy in the presence of illumination variations. We mimic the early layers of the human visual cortex with the spatio-temporal Gabor motion energy by adopting the pioneering model of Adelson and Bergen and we provide the closed-form expressions that enable the study and adaptation of this model to different application needs. Moreover, we propose a normalisation scheme for motion energy to tackle temporal illumination variations. Finally, we provide an overall GME scheme which, to the best of our knowledge, achieves the highest accuracy on the Pose, Illumination, and Expression (PIE) database.
Highlights
G LOBAL motion estimation (GME) is an increasingly important task because of the growing use of cameras embedded in autonomous platforms or worn by people
We provide closed-form expressions that can be used to study the Adelson and Bergen’s model [14] and we propose an illumination normalisation scheme that renders the output of Gabor filtering robust against the brightness value of dynamic elements as well as temporal illumination variations
We show that this scheme achieves high accuracy even in the presence of challenging illumination variations, outperforming state-ofthe-art global motion estimation (GME) methods
Summary
G LOBAL motion estimation (GME) is an increasingly important task because of the growing use of cameras embedded in autonomous platforms or worn by people. We provide closed-form expressions that can be used to study the Adelson and Bergen’s model [14] and we propose an illumination normalisation scheme that renders the output of Gabor filtering robust against the brightness value of dynamic elements as well as temporal illumination variations. We propose an overall GME scheme, which, to the best of our knowledge, is the first biologically-inspired GME approach that is validated on real sequences with challenging illumination variations.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
