Neural network identification of people hidden from view with a single-pixel, single-photon detector

Caramazza, Piergiorgio; Boccolini, Alessandro; Buschek, Daniel; Hullin, Matthias B.; Higham, Catherine; Henderson, Robert K.; Murray-Smith, Roderick; Faccio, Daniele

doi:10.1038/s41598-018-30390-0

Cited by 87 publications

(55 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The choice of the most suitable approaches depends primarily on the complexity of the computational model, as well as the computational budget available (i.e., the expected processing time, data storage limitations, and the desired quality of the information extracted). Supervised machine learning (including deep learning) approaches are particularly well suited for applications where a sufficient quantity of ground truth data or reference data is available (85)(86)(87)(88). Such methods rely on a twostage process, which consists of the training stage and the test stage.…”

Section: Computational Methods In the Photon-starved Regimementioning

confidence: 99%

Quantum-inspired computational imaging

Altmann

McLaughlin

Padgett

et al. 2018

Science

Self Cite

172

View full text Add to dashboard Cite

Computational imaging combines measurement and computational methods with the aim of forming images even when the measurement conditions are weak, few in number, or highly indirect. The recent surge in quantum-inspired imaging sensors, together with a new wave of algorithms allowing on-chip, scalable and robust data processing, has induced an increase of activity with notable results in the domain of low-light flux imaging and sensing. We provide an overview of the major challenges encountered in low-illumination (e.g., ultrafast) imaging and how these problems have recently been addressed for imaging applications in extreme conditions. These methods provide examples of the future imaging solutions to be developed, for which the best results are expected to arise from an efficient codesign of the sensors and data analysis tools.

show abstract

Section: Computational Methods In the Photon-starved Regimementioning

confidence: 99%

Quantum-inspired computational imaging

Altmann

McLaughlin

Padgett

et al. 2018

Science

Self Cite

172

View full text Add to dashboard Cite

show abstract

“…The return signal from each voxel is simulated and the voxel shapes/number are then varied in a loop until the difference between the simulated and measured signals is minimised. Caramazza et al, have also demonstrated that is possible to use a deep learning approach to correctly retrieve both position information and the identity of a person hidden behind an obstacle [94]. The method relies on the use of a 32x32 SPAD array camera that is used as an array of 1024 independent, single pixel SPADs.…”

Section: Gated Detection Continuous Illumination and Deep Learningmentioning

confidence: 99%

A trillion frames per second: the techniques and applications of light-in-flight photography

Faccio

Velten

2018

Rep. Prog. Phys.

Self Cite

View full text Add to dashboard Cite

Cameras capable of capturing videos at a trillion frames per second allow to freeze light in motion, a very counterintuitive capability when related to our everyday experience in which light appears to travel instantaneously. By combining this capability with computational imaging techniques, new imaging opportunities emerge such as 3D imaging of scenes that are hidden behind a corner, the study of relativistic distortion effects, imaging through diffusive media and imaging of ultrafast optical processes such as laser ablation, supercontinuum and plasma generation. We provide an overview of the main techniques that have been developed for ultra-high speed photography with a particular focus on 'light-in-flight' imaging, i.e. applications where the key element is the imaging of light itself at frame rates that allow to freeze its motion and therefore extract information that would otherwise be blurred out and lost.

show abstract

“…Over the past several years, single-photon sensitive detectors have been used to observe laser propagation in air [27,28], to detect objects hidden from the line-of-sight [29][30][31][32][33], and to image in the presence of scattering media [34][35][36][37][38][39][40]. In particular, progress is being made in the development and implementation of SPAD detectors in the form of dense pixel arrays [41][42][43][44].…”

mentioning

confidence: 99%

Long-range depth imaging using a single-photon detector array and non-local data fusion

Chan

Halimi

Zhu

et al. 2019

Sci Rep

View full text Add to dashboard Cite

The ability to measure and record high-resolution depth images at long stand-off distances is important for a wide range of applications, including connected and automotive vehicles, defense and security, and agriculture and mining. In LIDAR (light detection and ranging) applications, single-photon sensitive detection is an emerging approach, offering high sensitivity to light and picosecond temporal resolution, and consequently excellent surface-to-surface resolution. The use of large format CMOS (complementary metal-oxide semiconductor) single-photon detector arrays provides high spatial resolution and allows the timing information to be acquired simultaneously across many pixels. In this work, we combine state-of-the-art single-photon detector array technology with non-local data fusion to generate high resolution three-dimensional depth information of long-range targets. The system is based on a visible pulsed illumination system at a wavelength of 670 nm and a 240 × 320 array sensor, achieving sub-centimeter precision in all three spatial dimensions at a distance of 150 meters. The non-local data fusion combines information from an optical image with sparse sampling of the single-photon array data, providing accurate depth information at low signature regions of the target.

show abstract

Neural network identification of people hidden from view with a single-pixel, single-photon detector

Cited by 87 publications

References 22 publications

Quantum-inspired computational imaging

Quantum-inspired computational imaging

A trillion frames per second: the techniques and applications of light-in-flight photography

Long-range depth imaging using a single-photon detector array and non-local data fusion

Contact Info

Product

Resources

About