StereoSpike: Depth Learning With a Spiking Neural Network

StereoSpike: Depth Learning With a Spiking Neural Network

Depth estimation is an important computer vision task, useful in particular for navigation in autonomous vehicles, or for object manipulation in robotics. Here, we propose to solve it using StereoSpike, an end-to-end neuromorphic approach, combining two event-based cameras and a Spiking Neural Netwo...

Celý popis

Podrobná bibliografie
Hlavní autoři: Ulysse Rancon, Javier Cuadrado-Anibarro, Benoit R. Cottereau, Timothee Masquelier
Médium: Článek
Jazyk:English
Vydáno: IEEE 2022-01-01
Edice:IEEE Access
Témata:
Computer vision
bio-inspired learning
deep neural architectures
neuromorphic computing
spiking neural networks
stereo depth regression
On-line přístup:https://ieeexplore.ieee.org/document/9969606/

Internet

https://ieeexplore.ieee.org/document/9969606/

Podobné jednotky