FlyDVS: An Event-Driven Wireless Ultra-Low Power Visual Sensor Node

Mauro, Alfio Di; Scherer, Moritz; Mas, Jordi Fornt; Bougenot, Basile; Magno, Michele; Benini, Luca

doi:10.23919/date51398.2021.9474260

Cited by 6 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Events, i.e., active DVS pixels, can be directly transferred from the event camera to the Kraken TCDM, where they are accessible to the EHWPE and the cluster domain for processing. Such an on-chip integrated interface reduces the event acquisition power consumption by more than one order of magnitude, compared to what is shown in [7], improving the overall energy efficiency. Moreover, Kraken also implements hardware power management strategies, e.g., power gating, that allows the on/off switching of unused system parts to reduce the overall power consumption.…”

Section: B Academic Platform Krakenmentioning

confidence: 96%

“…Another drawback that limits the success of today's eventbased cameras and neuromorphic computing, especially for embedded low-power systems, is that the promised low power, low latency, and energy efficiency are diminished and often compromised by the interface's high power consumption, often due to non-standard communication protocol. Although nowadays data is mainly acquired using a high-power Field Programmable Gate Array (FPGA) and a USB interface [7], novel embedded processors are being developed, providing the research community with reference platforms and resources contained to address this issue. Large-scale, neuromorphic processors like Intel Loihi [8] can simulate hundreds of thousands or even millions of spiking neurons in real-time.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Embedded neuromorphic attention model leveraging a novel low-power heterogeneous platform

Gruel¹,

Mauro²,

Hunziker³

et al. 2023

2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)

Self Cite

View full text Add to dashboard Cite

Neuromorphic computing has been identified as an ideal candidate to exploit the potential of event-based cameras, a promising sensor for embedded computer vision. However, state-of-the-art neuromorphic models try to maximize the model performance on large platforms rather than a trade-off between memory requirements and performance. We present the first deployment of an embedded neuromorphic algorithm on Kraken, a low-power RISC-V-based SoC prototype including a neuromorphic spiking neural network (SNN) accelerator. In addition, the model employed in this paper was designed to achieve visual attention detection on event data while minimizing the neuronal populations' size and the inference latency. Experimental results show that it is possible to achieve saliency detection in event data with a delay of 32ms, maintains classification accuracy of 84.51% and consumes only 3.85mJ per second of processed input data, achieving all of this while processing input data 10 times faster than real-time. This trade-off between decision latency, power consumption, accuracy, and run time significantly outperforms those achieved by previous implementations on CPU and neuromorphic hardware.

show abstract

Section: B Academic Platform Krakenmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Embedded neuromorphic attention model leveraging a novel low-power heterogeneous platform

Gruel¹,

Mauro²,

Hunziker³

et al. 2023

2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…A key advantage introduced by event sensors is the proportionality between the primary sensor input and the number of output events generated by it [2]. To efficiently exploit the inherently sparse nature of such data streams, the energy to information proportionality needs to be preserved across the whole processing pipeline.…”

Section: Introductionmentioning

confidence: 99%

SNE: an Energy-Proportional Digital Accelerator for Sparse Event-Based Convolutions

Mauro

Prasad

Huang

et al. 2022

2022 Design, Automation &Amp; Test in Europe Conference &Amp; Exhibition (DATE)

Self Cite

View full text Add to dashboard Cite

Event-based sensors are drawing increasing attention due to their high temporal resolution, low power consumption, and low bandwidth. To efficiently extract semantically meaningful information from sparse data streams produced by such sensors, we present a 4.5TOP/s/W digital accelerator capable of performing 4-bits-quantized event-based convolutional neural networks (eCNN). Compared to standard convolutional engines, our accelerator performs a number of operations proportional to the number of events contained into the input data stream, ultimately achieving a high energy-to-information processing proportionality. On the IBM-DVS-Gesture dataset, we report 80uJ/inf to 261uJ/inf, respectively, when the input activity is 1.2% and 4.9%. Our accelerator consumes 0.221pJ/SOP, to the best of our knowledge it is the lowest energy/OP reported on a digital neuromorphic engine.

show abstract

Event-Based Vision on FPGAs - a Survey

Kryjak

2024

2024 27th Euromicro Conference on Digital System Design (DSD)

View full text Add to dashboard Cite

FlyDVS: An Event-Driven Wireless Ultra-Low Power Visual Sensor Node

Cited by 6 publications

References 10 publications

Embedded neuromorphic attention model leveraging a novel low-power heterogeneous platform

Embedded neuromorphic attention model leveraging a novel low-power heterogeneous platform

SNE: an Energy-Proportional Digital Accelerator for Sparse Event-Based Convolutions

Event-Based Vision on FPGAs - a Survey

Contact Info

Product

Resources

About