Resource Characterisation of Personal-Scale Sensing Models on Edge Accelerators

Antonini, Mattia; Vu, Tran; Min, Chulhong; Montanari, A.; Mathur, Akhil; Kawsar, Fahim

doi:10.1145/3363347.3363363

Cited by 50 publications

(22 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, their report does not include hardware-accelerated edge devices, although their findings indicate that CNN inference benchmarks will be greatly benefited from SIMD (single instruction, multiple data) style hardware acceleration due to the parallel nature of the CNN architecture. The work of Antonini et al [8] is most similar to ours in that both Coral Dev Board and Jetson Nano are covered and analyzed comparatively. Additionally, their work included Intel Neural Compute Stick for performance comparison altogether.…”

Section: Related Worksupporting

confidence: 54%

See 1 more Smart Citation

Benchmarking Modern Edge Devices for AI Applications

Kang

2021

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

AI (artificial intelligence) has grown at an overwhelming speed for the last decade, to the extent that it has become one of the mainstream tools that drive the advancements in science and technology. Meanwhile, the paradigm of edge computing has emerged as one of the foremost areas in which applications using the AI technology are being most actively researched, due to its potential benefits and impact on today's widespread networked computing environments. In this paper, we evaluate two major entry-level offerings in the state-of-the-art edge device technology, which highlight increased computing power and specialized hardware support for AI applications. We perform a set of deep learning benchmarks on the devices to measure their performance. By comparing the performance with other GPU (graphics processing unit) accelerated systems in different platforms, we assess the computational capability of the modern edge devices featuring a significant amount of hardware parallelism.

show abstract

Section: Related Worksupporting

confidence: 54%

“…There is a sizable amount of benchmark reports on the edge devices [8]- [11]. However, some reports are already a bit outdated and others miss benchmarks on the latest offerings from the major edge device vendors.…”

Section: Introductionmentioning

confidence: 99%

Benchmarking Modern Edge Devices for AI Applications

Kang

2021

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…A more extensive comparison among the various COTS devices used for Deep Learning can be found in [26,27].…”

Section: Machine Learning Accelerators Overviewmentioning

confidence: 99%

CloudScout: A Deep Neural Network for On-Board Cloud Detection on Hyperspectral Images

et al. 2020

View full text Add to dashboard Cite

The increasing demand for high-resolution hyperspectral images from nano and microsatellites conflicts with the strict bandwidth constraints for downlink transmission. A possible approach to mitigate this problem consists in reducing the amount of data to transmit to ground through on-board processing of hyperspectral images. In this paper, we propose a custom Convolutional Neural Network (CNN) deployed for a nanosatellite payload to select images eligible for transmission to ground, called CloudScout. The latter is installed on the Hyperscout-2, in the frame of the Phisat-1 ESA mission, which exploits a hyperspectral camera to classify cloud-covered images and clear ones. The images transmitted to ground are those that present less than 70% of cloudiness in a frame. We train and test the network against an extracted dataset from the Sentinel-2 mission, which was appropriately pre-processed to emulate the Hyperscout-2 hyperspectral sensor. On the test set we achieve 92% of accuracy with 1% of False Positives (FP). The Phisat-1 mission will start in 2020 and will operate for about 6 months. It represents the first in-orbit demonstration of Deep Neural Network (DNN) for data processing on the edge. The innovation aspect of our work concerns not only cloud detection but in general low power, low latency, and embedded applications. Our work should enable a new era of edge applications and enhance remote sensing applications directly on-board satellite.

show abstract

“…There are various edge AI devices for deep learning inference, including Raspberry Pi, ASUS Tinkerboard, NVIDIA Jetson series, and Google Coral Dev Board [32][33][34]. NVIDIA's Jetson is the most widely used edge AI device for deep learning tasks among these platforms.…”

Section: Rvm and Cnnmentioning

confidence: 99%

Dual Image-Based CNN Ensemble Model for Waste Classification in Reverse Vending Machine

2021

View full text Add to dashboard Cite

A reverse vending machine motivates citizens to bring recyclable waste by rewarding them, which is a viable solution to increase the recycling rate. Reverse vending machines generally use near-infrared sensors, barcode sensors, or cameras to classify recycling resources. However, sensor-based reverse vending machines suffer from a high configuration cost and the limited scope of target objects, and conventional single image-based reverse vending machines usually make erroneous predictions about intentional fraud objects. This paper proposes a dual image-based convolutional neural network ensemble model to address these problems. For this purpose, we first created a prototype reverse vending machine and constructed an image dataset containing two cross-sections of objects, top and front view. Then, we chose convolutional neural network models widely used in image classification as the candidates for building an accurate and lightweight ensemble model. Considering the size and classification performance of candidates, we constructed the best-fit ensemble combination and evaluated its classification performance. The final ensemble model showed a classification accuracy higher than 95% for all target classes, including fraud objects. This result proves that our approach achieves better robustness against intentional fraud objects than single image-based models and thus can broaden the scope for target resources. The measurement results on lightweight embedded platforms also demonstrated that our model provides a short inference time that is enough to facilitate the real-time execution of reverse vending machines based on low-cost edge artificial intelligence devices.

show abstract

Resource Characterisation of Personal-Scale Sensing Models on Edge Accelerators

Cited by 50 publications

References 10 publications

Benchmarking Modern Edge Devices for AI Applications

Benchmarking Modern Edge Devices for AI Applications

CloudScout: A Deep Neural Network for On-Board Cloud Detection on Hyperspectral Images

Dual Image-Based CNN Ensemble Model for Waste Classification in Reverse Vending Machine

Contact Info

Product

Resources

About