DeepAI AI Chat
Log In Sign Up

StereoSpike: Depth Learning with a Spiking Neural Network

09/28/2021
by   Ulysse Rançon, et al.
CNRS
Université de Bordeaux
0

Depth estimation is an important computer vision task, useful in particular for navigation in autonomous vehicles, or for object manipulation in robotics. Here we solved it using an end-to-end neuromorphic approach, combining two event-based cameras and a Spiking Neural Network (SNN) with a slightly modified U-Net-like encoder-decoder architecture, that we named StereoSpike. More specifically, we used the Multi Vehicle Stereo Event Camera Dataset (MVSEC). It provides a depth ground-truth, which was used to train StereoSpike in a supervised manner, using surrogate gradient descent. We propose a novel readout paradigm to obtain a dense analog prediction – the depth of each pixel – from the spikes of the decoder. We demonstrate that this architecture generalizes very well, even better than its non-spiking counterparts, leading to state-of-the-art test accuracy. To the best of our knowledge, it is the first time that such a large-scale regression problem is solved by a fully spiking network. Finally, we show that low firing rates (<10 regularization, with a minimal cost in accuracy. This means that StereoSpike could be efficiently implemented on neuromorphic chips, opening the door for low power and real time embedded systems.

READ FULL TEXT
11/22/2022

MSS-DepthNet: Depth Prediction with Multi-Step Spiking Neural Network

Event cameras are considered to have great potential for computer vision...
12/13/2021

Improving Surrogate Gradient Learning in Spiking Neural Networks via Regularization and Normalization

Spiking neural networks (SNNs) are different from the classical networks...
02/13/2023

Optical Flow estimation with Event-based Cameras and Spiking Neural Networks

Event-based cameras are raising interest within the computer vision comm...
10/23/2021

ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks

With event-driven algorithms, especially the spiking neural networks (SN...
08/03/2022

LaneSNNs: Spiking Neural Networks for Lane Detection on the Loihi Neuromorphic Processor

Autonomous Driving (AD) related features represent important elements fo...
10/05/2022

Neuro-Planner: A 3D Visual Navigation Method for MAV with Depth Camera based on Neuromorphic Reinforcement Learning

Traditional visual navigation methods of micro aerial vehicle (MAV) usua...