Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Continuous-surface 3D reconstruction from kilometer-range single-photon LiDAR using score-based priors.

Scientific reports·2026

Same author

Strategic Amyotrophic Lateral Sclerosis Australia-Systems Genomics Consortium (SALSA-SGC): cohort profile.

BMJ open·2026

Same author

Compensating for photon counting losses in a TCSPC SPAD array enables quantitative time-resolved fluorescence anisotropy imaging.

Methods and applications in fluorescence·2026

Same author

Tumour-to-tumour metastasis: head and neck squamous cell carcinoma to enchondroma.

Skeletal radiology·2026

Same author

Human activity recognition at a kilometer range using single-photon LiDAR.

Optics express·2026

Same author

Acute postoperative complications after scleral fixation of Akreos AO60 intraocular lens.

Journal of surgical case reports·2026

Same journal

Denoising algorithm of Φ-OTDR systems based on adaptive fractional wavelet transform denoising.

Optics express·2026

Same journal

Millisecond photon-to-photon latency and high-speed volumetric projection system for optogenetics.

Optics express·2026

Same journal

Polarization-encoded coaxial structured light for high-precision 3D surface profilometry.

Optics express·2026

Same journal

Discrete freeform optical design based on collaborative optimization of point cloud and local normals.

Optics express·2026

Same journal

Ultrafast ghost imaging with 25 GHz speckle switching and wavelength-division multiplexing.

Optics express·2026

Same journal

Atomic vapor cells fabricated by femtosecond laser welding of standard-optical-quality glass.

Optics express·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 12, 2025

Single Molecule Fluorescence Microscopy on Planar Supported Bilayers

Single Molecule Fluorescence Microscopy on Planar Supported Bilayers

Published on: October 31, 2015

High-speed object detection with a single-photon time-of-flight image sensor.

Germán Mora-Martín, Alex Turpin, Alice Ruget

|November 23, 2021

Summary

This summary is machine-generated.

Convolutional neural networks (CNNs) enhance 3D time-of-flight (ToF) imaging for object detection. Using SPAD cameras with CNNs improves depth map resolution and processing speed for real-time applications.

More Related Videos

A Protocol for Real-time 3D Single Particle Tracking

A Protocol for Real-time 3D Single Particle Tracking

Published on: January 3, 2018

Single-Molecule Tracking Microscopy - A Tool for Determining the Diffusive States of Cytosolic Molecules

Single-Molecule Tracking Microscopy - A Tool for Determining the Diffusive States of Cytosolic Molecules

Published on: September 5, 2019

Related Experiment Videos

Last Updated: Oct 12, 2025

Single Molecule Fluorescence Microscopy on Planar Supported Bilayers

Single Molecule Fluorescence Microscopy on Planar Supported Bilayers

Published on: October 31, 2015

A Protocol for Real-time 3D Single Particle Tracking

A Protocol for Real-time 3D Single Particle Tracking

Published on: January 3, 2018

Single-Molecule Tracking Microscopy - A Tool for Determining the Diffusive States of Cytosolic Molecules

Single-Molecule Tracking Microscopy - A Tool for Determining the Diffusive States of Cytosolic Molecules

Published on: September 5, 2019

Area of Science:

Computer Vision
Photonics
Machine Learning

Background:

3D time-of-flight (ToF) imaging, utilizing single-photon avalanche diodes (SPADs), offers accurate depth data for applications like robotics and augmented reality.
Current SPAD array limitations in lateral resolution hinder detailed object detection from depth maps.
High-speed 3D capture is achievable with SPAD arrays and integrated processing, but resolution remains a challenge.

Purpose of the Study:

To demonstrate the effectiveness of convolutional neural networks (CNNs) in overcoming resolution limitations in SPAD-based 3D ToF imaging for object detection.
To evaluate the performance of CNNs using full histogram data versus point clouds for object detection.
To assess the real-time processing capabilities and latency of the proposed system.

Main Methods:

Development of a portable SPAD camera system capturing 16-bin photon timing histograms with 64x32 spatial resolution.
Application of convolutional neural networks (CNNs) to process histogram data for object detection.
Comparison of CNN performance using full histogram data, point clouds, and combined data inputs.

Main Results:

CNNs significantly improve object detection performance by utilizing full histogram data from SPAD cameras.
High-speed 3D capture achieved with exposure times as low as 2 ms (500 FPS) and low signal-to-background ratios (0.05).
GPU-accelerated processing achieves sub-millisecond frame times, resulting in overall system latency in the millisecond range.

Conclusions:

CNNs effectively address the lateral resolution limitations of SPAD-based 3D ToF imaging for object detection.
Processing full histogram data or a combination of point cloud and intensity data with CNNs yields high performance.
The low latency and high-speed capabilities make this approach suitable for safety-critical computer vision applications requiring faster-than-human reaction times.