Abstract
Neuromorphic event-based image sensors capture only the dynamic motion in a scene, which is then transferred to computation units for motion recognition. This approach, however, leads to time latency and can be power consuming. Here we report computational event-driven vision sensors that capture and directly convert dynamic motion into programmable, sparse and informative spiking signals. The sensors can be used to form a spiking neural network for motion recognition. Each individual vision sensor consists of two parallel photodiodes with opposite polarities and has a temporal resolution of 5 μs. In response to changes in light intensity, the sensors generate spiking signals with different amplitudes and polarities by electrically programming their individual photoresponsivity. The non-volatile and multilevel photoresponsivity of the vision sensors can emulate synaptic weights and can be used to create an in-sensor spiking neural network. Our computational event-driven vision sensor approach eliminates redundant data during the sensing process, as well as the need for data transfer between sensors and computation units.
This is a preview of subscription content, access via your institution
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$29.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Buy this article
- Purchase on Springer Link
- Instant access to full article PDF
Prices may be subject to local taxes which are calculated during checkout
Similar content being viewed by others
Data availability
The data that support the plots within this paper and other findings of this study are available from the corresponding authors upon reasonable request. Source data are provided with this paper.
Code availability
The codes used for simulation and data plotting are available from the corresponding authors upon reasonable request.
References
Lichtsteiner, P. & Delbruck, T. A 64x64 AER logarithmic temporal derivative silicon retina. In Research in Microelectronics and Electronics, 2005 PhD, Vol. 2 202–205 (IEEE, 2005).
Lichtsteiner, P., Posch, C. & Delbruck, T. A 128 × 128 120 dB 15 μs latency asynchronous temporal contrast vision sensor. IEEE J. Solid-State Circuits 43, 566–576 (2008).
Posch, C., Serrano-Gotarredona, T., Linares-Barranco, B. & Delbruck, T. Retinomorphic event-based vision sensors: bioinspired cameras with spiking output. Proc. IEEE 102, 1470–1484 (2014).
Furber, S. B. et al. Overview of the SpiNNaker system architecture. IEEE Trans. Comput. 62, 2454–2467 (2013).
Akopyan, F. et al. TrueNorth: design and tool flow of a 65 mW 1 million neuron programmable neurosynaptic chip. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 34, 1537–1557 (2015).
Davies, M. et al. Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 38, 82–99 (2018).
Bichler, O. et al. Visual pattern extraction using energy-efficient ‘2-PCM synapse’ neuromorphic architecture. IEEE Trans. Electron Devices 59, 2206–2214 (2012).
Bichler, O., Querlioz, D., Thorpe, S. J., Bourgoin, J.-P. & Gamrat, C. Extraction of temporally correlated features from dynamic vision sensors with spike-timing-dependent plasticity. Neural Netw. 32, 339–348 (2012).
Gallego, G. et al. Event-based vision: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44, 154–180 (2022).
Chen, G. et al. Event-based neuromorphic vision for autonomous driving: a paradigm shift for bio-inspired visual sensing and perception. IEEE Signal Process. Mag. 37, 34–49 (2020).
Drazen, D., Lichtsteiner, P., Häfliger, P., Delbrück, T. & Jensen, A. Toward real-time particle tracking using an event-based dynamic vision sensor. Exp. Fluids 51, 1465–1469 (2011).
Bing, Z., Meschede, C., Chen, G., Knoll, A. & Huang, K. Indirect and direct training of spiking neural networks for end-to-end control of a lane-keeping vehicle. Neural Netw. 121, 21–36 (2020).
Zhou, F. & Chai, Y. Near-sensor and in-sensor computing. Nat. Electron. 3, 664–671 (2020).
Chai, Y. In-sensor computing for machine vision. Nature 579, 32–33 (2020).
Wan, T. et al. In-sensor computing: materials, devices, and integration technologies. Adv. Mater. 35, e2203830 (2023).
Wu, P. et al. Next-generation machine vision systems incorporating two-dimensional materials: progress and perspectives. InfoMat 4, e12275 (2022).
Zhou, F. et al. Optoelectronic resistive random access memory for neuromorphic vision sensors. Nat. Nanotechnol. 14, 776–782 (2019).
Liao, F. et al. Bioinspired in-sensor visual adaptation for accurate perception. Nat. Electron. 5, 1–8 (2022).
Zhang, Z. et al. All-in-one two-dimensional retinomorphic hardware device for motion detection and recognition. Nat. Nanotechnol. 17, 27–32 (2022).
Subbulakshmi Radhakrishnan, S., Dodda, A. & Das, S. An all-in-one bioinspired neural network. ACS Nano 16, 20100–20115 (2022).
Dodda, A., Trainor, N., Redwing, J. M. & Das, S. All-in-one, bio-inspired, and low-power crypto engines for near-sensor security based on two-dimensional memtransistors. Nat. Commun. 13, 3587 (2022).
Wang, S. et al. Networking retinomorphic sensor with memristive crossbar for brain-inspired visual perception. Natl Sci. Rev. 8, nwaa172 (2021).
Jang, H. et al. An atomically thin optoelectronic machine vision processor. Adv. Mater. 32, e2002431 (2020).
Mennel, L. et al. Ultrafast machine vision with 2D material neural network image sensors. Nature 579, 62–66 (2020).
Jang, H. et al. In-sensor optoelectronic computing using electrostatically doped silicon. Nat. Electron. 5, 519–525 (2022).
Cui, B. et al. Ferroelectric photosensor network: an advanced hardware solution to real-time machine vision. Nat. Commun. 13, 1707 (2022).
Wang, C.-Y. et al. Gate-tunable van der Waals heterostructure for reconfigurable neural network vision sensor. Sci. Adv. 6, eaba6173 (2020).
Chai, Y. Silicon photodiodes that multiply. Nat. Electron. 5, 483–484 (2022).
Seung, H. et al. Integration of synaptic phototransistors and quantum dot light-emitting diodes for visualization and recognition of UV patterns. Sci. Adv. 8, eabq3101 (2022).
Zhou, Y. et al. A 2T2R1C vision cell with 140 dB dynamic range and event-driven characteristics for in-sensor spiking neural network. In International Electron Devices Meeting 31–34 (IEEE, 2022).
Koppens, F. H. L. et al. Photodetectors based on graphene, other two-dimensional materials and hybrid systems. Nat. Nanotechnol. 9, 780–793 (2014).
Chen, P. et al. Approaching the intrinsic exciton physics limit in two-dimensional semiconductor diodes. Nature 599, 404–410 (2021).
Zhou, Y. et al. A reconfigurable two-WSe2-transistor synaptic cell for reinforcement learning. Adv. Mater. 34, 2107754 (2022).
Pan, C. et al. Reconfigurable logic and neuromorphic circuits based on electrically tunable two-dimensional homojunctions. Nat. Electron. 3, 383–390 (2020).
Chen, H. et al. Logic gates based on neuristors made from two-dimensional materials. Nat. Electron. 4, 399–404 (2021).
Zhou, C. et al. Carrier type control of WSe2 field-effect transistors by thickness modulation and MoO3 layer doping. Adv. Funct. Mater. 26, 4223–4230 (2016).
Das, S. & Appenzeller, J. WSe2 field effect transistors with enhanced ambipolar characteristics. Appl. Phys. Lett. 103, 103501 (2013).
Suh, D. C. et al. Improved thermal stability of Al2O3/HfO2/Al2O3 high-k gate dielectric stack on GaAs. Appl. Phys. Lett. 96, 142112 (2010).
Lee, D. U., Lee, H. J., Kim, E. K., You, H.-W. & Cho, W.-J. Low operation voltage and high thermal stability of a WSi2 nanocrystal memory device using an Al2O3/HfO2/Al2O3 tunnel layer. Appl. Phys. Lett. 100, 072901 (2012).
Molas, G. et al. Reliability of charge trapping memories with high-k control dielectrics. Microelectron. Eng. 86, 1796–1803 (2009).
Wu, J. Y., Chen, Y. T., Lin, M. H. & Wu, T. B. Ultrathin HfON trapping layer for charge-trap memory made by atomic layer deposition. IEEE Electron Device Lett. 31, 993–995 (2010).
Groenendijk, D. J. et al. Photovoltaic and photothermoelectric effect in a double-gated WSe2 device. Nano Lett. 14, 5846–5852 (2014).
Li, D. et al. Two-dimensional non-volatile programmable p–n junctions. Nat. Nanotechnol. 12, 901–906 (2017).
Buscema, M. et al. Photocurrent generation with two-dimensional van der Waals semiconductors. Chem. Soc. Rev. 44, 3691–3718 (2015).
Baugher, B. W. H., Churchill, H. O. H., Yang, Y. & Jarillo-Herrero, P. Optoelectronic devices based on electrically tunable p–n diodes in a monolayer dichalcogenide. Nat. Nanotechnol. 9, 262–267 (2014).
Prezioso, M. et al. Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature 521, 61–64 (2015).
Yao, P. et al. Fully hardware-implemented memristor convolutional neural network. Nature 577, 641–646 (2020).
Acknowledgements
This work is supported by the Research Grant Council of Hong Kong (CRS_PolyU502/22), the Shenzhen Science and Technology Innovation Commission (SGDX2020110309540000), the Innovation Technology Fund (ITS/047/20) and The Hong Kong Polytechnic University (1-ZE1T, 9BFT and WZ4X). Y.H. acknowledges the support from the National Natural Science Foundation of China (62374093, 92164204) and the National Key Research and Development Program of China (SQ2023YFB4500038).
Author information
Authors and Affiliations
Contributions
Y.C. conceived the concept. Y.H. and Y.C. supervised the project. Y.Z. designed the devices and circuits. Y.Z., Z.C. and H.Y. fabricated the devices. J.Y. performed the Raman and Atomic Force Microscope characterizations. Y.Z. performed the device and circuit measurement. J.F. and Y.H. designed and performed the neural network simulations. Y.Z., Y.W., F.Z., S.M., L.X. and X.M. analysed the data. Y.Z. and Y.C. wrote the paper. All the authors discussed the results and implications, and reviewed the paper.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Peer review
Peer review information
Nature Electronics thanks Du Xiang and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Supplementary Information
Supplementary Notes I–XVI, Figs. 1–33, Table 1 and References.
Supplementary Video 1
The complete generated spikes in real time.
Supplementary Video 2
The details of the three types of motions.
Source data
Source Data Fig. 2
Raw data used to plot Fig. 2 in CSV format.
Source Data Fig. 3
Raw data used to plot Fig. 3 in CSV format.
Source Data Fig. 4
Raw data used to plot Fig. 4 in CSV format.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhou, Y., Fu, J., Chen, Z. et al. Computational event-driven vision sensors for in-sensor spiking neural networks. Nat Electron 6, 870–878 (2023). https://doi.org/10.1038/s41928-023-01055-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41928-023-01055-2
This article is cited by
-
Non-volatile rippled-assisted optoelectronic array for all-day motion detection and recognition
Nature Communications (2024)
-
Bio-inspired “Self-denoising” capability of 2D materials incorporated optoelectronic synaptic array
npj 2D Materials and Applications (2024)
-
Extending in-sensor computing from static images to dynamic motions
Nature Electronics (2023)