Description

The current models retrieving data from event-based cameras reconstruct pixel images on which image processing algorithms can be applied. Thus, the asynchronous and event-driven nature is ultimately poorly considered. A model based on spiking neural networks would follow the dynamics of the inputs and would lead to innovative algorithms that surpass current processing chains.

Skills required

AI, neural networks, image processing Python programming

Bibliography

• Bergoin R, Torcini A, Deco G, Quoy M, Zamora-López G (2025) Emergence and maintenance of modularity in neural networks with Hebbian and anti-Hebbian inhibitory STDP. PLOS Computational Biology 21(4): e1012973. https://doi.org/10.1371/journal.pcbi.1012973.
• Cuadrado, J., Rançon, U., Cottereau, B. R., Barranco, F., & Masquelier, T. (2023). Optical flow estimation from event-based cameras and spiking neural networks. Frontiers in Neuroscience, 17, 1160034.
• Nazari, S., Amiri, M. An accurate and fast learning approach in the biologically spiking neural network. Sci Rep 15, 6585 (2025). https://doi.org/10.1038/s41598-025-90113-0
° Rançon, U., Cuadrado-Anibarro, J., Cottereau, B. R., & Masquelier, T. (2022). Stereospike: Depth learning with a spiking neural network. IEEE Access, 10, 127428-127439.
• Simon Chane, Camille, Ernst Niebur, Ryad Benosman, and Sio-Hoi Ieng (2024) An event-based implementation of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Cognitive and Developmental Systems, 1 13. https://doi.org/10.1109/TCDS.2024.3480153.
• Vicente-Sola, A., Manna, D.L., Kirkland, P., Di Caterina, G., Bihl, T.J. (2025) Spiking Neural Networks for event-based action recognition: A new task to understand their advantage, Neurocomputing 611, https://doi.org/10.1016/j.neucom.2024.128657

Keywords

Neural networks, Even based camera