TDC-less Direct Time-of-Flight Imaging Using Spiking Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: MacLean, Jack, Stewart, Brian, Gyongy, Istvan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929240202543104
author MacLean, Jack
Stewart, Brian
Gyongy, Istvan
author_facet MacLean, Jack
Stewart, Brian
Gyongy, Istvan
contents 3D depth sensors using single-photon avalanche diodes (SPADs) are becoming increasingly common in applications such as autonomous navigation and object detection. Recent designs implement on-chip histogramming time-to-digital converters (TDCs) to compress the photon timestamps and reduce the bottleneck in the read-out and processing of large volumes of photon data. However, the use of full histogramming with large SPAD arrays poses significant challenges due to the associated demands in silicon area and power consumption. We propose a TDC-less dToF sensor which uses Spiking Neural Networks (SNN) to process the SPAD events directly. The proposed SNN is trained and tested on synthetic SPAD events, and while it offers five times lower precision in depth prediction than a classic centre-of-mass (CoM) algorithm (applied to histograms of the events), it achieves similar Mean Absolute Error (MAE) with faster processing speeds and significantly lower power consumption is anticipated.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10793
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TDC-less Direct Time-of-Flight Imaging Using Spiking Neural Networks
MacLean, Jack
Stewart, Brian
Gyongy, Istvan
Image and Video Processing
Signal Processing
3D depth sensors using single-photon avalanche diodes (SPADs) are becoming increasingly common in applications such as autonomous navigation and object detection. Recent designs implement on-chip histogramming time-to-digital converters (TDCs) to compress the photon timestamps and reduce the bottleneck in the read-out and processing of large volumes of photon data. However, the use of full histogramming with large SPAD arrays poses significant challenges due to the associated demands in silicon area and power consumption. We propose a TDC-less dToF sensor which uses Spiking Neural Networks (SNN) to process the SPAD events directly. The proposed SNN is trained and tested on synthetic SPAD events, and while it offers five times lower precision in depth prediction than a classic centre-of-mass (CoM) algorithm (applied to histograms of the events), it achieves similar Mean Absolute Error (MAE) with faster processing speeds and significantly lower power consumption is anticipated.
title TDC-less Direct Time-of-Flight Imaging Using Spiking Neural Networks
topic Image and Video Processing
Signal Processing
url https://arxiv.org/abs/2401.10793