Stakes of neuromorphic foveation: a promising future for embedded event cameras

Foveation can be defined as the organic action of directing the gaze towards a visual region of interest to acquire relevant information selectively. With the recent advent of event cameras, we believe that taking advantage of this visual neuroscience mechanism would greatly improve the efficiency of event data processing. Indeed, applying foveation to event data would allow to comprehend the visual scene while significantly reducing the amount of raw data to handle. In this respect, we demonstrate the stakes of neuromorphic foveation theoretically and empirically across several computer vision tasks, namely semantic segmentation and classification. We show that foveated event data have a significantly better trade-off between quantity and quality of the information conveyed than high- or low-resolution event data. Furthermore, this compromise extends even over fragmented datasets. Our code is publicly available online at: https://github.com/amygruel/FoveationStakes_DVS.

Automated summary

Foveation refers to the organic action of directing gaze towards a visual region of interest for selective acquisition of relevant information. The recent development of event cameras presents an opportunity to exploit this visual neuroscience mechanism and enhance the efficiency of event data processing. By applying foveation to event data, it is possible to comprehend visual scenes with significantly reduced raw data volume. This study demonstrates the significance of neuromorphic foveation in computer vision tasks such as semantic segmentation and classification, showing a superior trade-off between quantity and quality of information conveyed compared to high or low-resolution event data. The code for this study is publicly available at: https://github.com/amygruel/FoveationStakes_DVS.