Papers
3
Total Citations
26
H-Index
2
About
Amélie Gruel is at the forefront of neuromorphic computing and embedded computer vision, pioneering methods to make visual intelligence as efficient as biological systems. Her research centers on bridging the gap between event-based sensors—like Dynamic Vision Sensors (DVS), which mimic the retina by capturing only pixel-level brightness changes—and Spiking Neural Networks (SNNs), the brain-inspired computing paradigm that processes sparse, asynchronous data with minimal energy. Gruel’s key contributions include developing novel downscaling techniques for event data, enabling high-performance vision on resource-constrained embedded platforms. Her 2022 paper on event data downscaling for embedded computer vision has garnered 13 citations, while her 2023 comparative study of DVS spatial downscaling methods using SNNs has attracted 11 citations, underscoring the community’s interest in efficient neuromorphic pipelines. Most recently, her 2024 work on neuromorphic event-based line detection on the SpiNNaker hardware demonstrates real-world deployment of SNNs for robotic perception. By tackling the fundamental challenge of processing sparse, asynchronous data with biologically plausible networks, Gruel is shaping a future where vision systems are as frugal and responsive as the human eye.
Research Focus
Key Achievements
Top Papers
- 1Event Data Downscaling for Embedded Computer Vision13 citations · 2022
- 2
- 3Neuromorphic Event-based Line Detection on SpiNNaker2 citations · 2024