Figures
The spatial pooling regions of the foveated object detector
A large number of species from primates to shrimps do not see the visual world with uniform spatial detail. An area with heightened sensitivity to spatial detail, known as the fovea in mammals is oriented through eye and head movements to scrutinize regions of interest in the visual environment. Akbas and Eckstein showed using a computer vision object detection model, that the foveated version of the model can attain similar search performance to its non-foveated version while bringing significant computational savings. The image shows the spatial pooling regions of the foveated model.
Image Credit: Emre Akbas
Citation: (2017) PLoS Computational Biology Issue Image | Vol. 13(10) October 2017. PLoS Comput Biol 13(10): ev13.i10. https://doi.org/10.1371/image.pcbi.v13.i10
Published: October 31, 2017
Copyright: © 2017 Emre Akbas, Miguel Eckstein. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
A large number of species from primates to shrimps do not see the visual world with uniform spatial detail. An area with heightened sensitivity to spatial detail, known as the fovea in mammals is oriented through eye and head movements to scrutinize regions of interest in the visual environment. Akbas and Eckstein showed using a computer vision object detection model, that the foveated version of the model can attain similar search performance to its non-foveated version while bringing significant computational savings. The image shows the spatial pooling regions of the foveated model.
Image Credit: Emre Akbas