A Cost-Effective Person-Following System for Assistive Unmanned Vehicles with Deep Learning at the Edge

Boschi, Anna; Salvetti, Francesco; Mazzia, Vittorio; Chiaberge, Marcello

doi:10.3390/machines8030049

Cited by 15 publications

(6 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applications that focus on low-cost (45% of PS) choose SBCs to be part of their systems because with such hardwares it is possible to realize applications such as access control and authentication and monitoring systems [Curtin and Matthews 2019, Oliveira and Wehrmeister 2018, Lindner et al 2020, Nikodem et al 2020] while maintaining a feasible cost and easy replication. It is also interesting to note that in applications involving systems that promote user accessibility [Calabrese et al 2020] or that are part of systems that already have a certain high level of cost [Milioto et al 2017, Nikodem et al 2020, Kim et al 2019, Boschi et al 2020] the low cost of the system is a concern for the authors.…”

Section: Results and Discutionsmentioning

confidence: 99%

A Systematic Literature Review on Convolutional Neural Networks applied to Single Board Computers

Silva¹,

Silva²,

Santos³

2022

Anais Da II Escola Regional De Alto Desempenho Norte 2 E II Escola Regional De Aprendizado De Máquina E Inteligência Artificial

View full text Add to dashboard Cite

This work consists of systematically reviewing studies involving applications of convolutional neural network (CNN) algorithms implemented in single board computers (SBC) to verify their feasibility in computer vision (CV) applications. Indicating the main parameters for evaluating the performance of SBCs as the processing time (88.24%) and accuracy (29.41%). Furthermore, the most used SBCs and the motivation for choosing such devices are indicated. The study contributes to help in future works involving CNNs in embedded systems, as well as in discussions about architectures involving deep learning applications.

show abstract

Section: Results and Discutionsmentioning

confidence: 99%

A Systematic Literature Review on Convolutional Neural Networks applied to Single Board Computers

Silva¹,

Silva²,

Santos³

2022

Anais Da II Escola Regional De Alto Desempenho Norte 2 E II Escola Regional De Aprendizado De Máquina E Inteligência Artificial

View full text Add to dashboard Cite

show abstract

“…Previously obtained values were compared with other similar works, such as that of [ 65 ], whose architecture uses a Nano Jetson as an embedded system executing a YOLOv3-tiny network. This network is similar to MobileNet-SSD in size and computational cost.…”

Section: Resultsmentioning

confidence: 99%

Smart Video Surveillance System Based on Edge Computing

Cob-Parro

Losada

Marrón

et al. 2021

Sensors

View full text Add to dashboard Cite

New processing methods based on artificial intelligence (AI) and deep learning are replacing traditional computer vision algorithms. The more advanced systems can process huge amounts of data in large computing facilities. In contrast, this paper presents a smart video surveillance system executing AI algorithms in low power consumption embedded devices. The computer vision algorithm, typical for surveillance applications, aims to detect, count and track people’s movements in the area. This application requires a distributed smart camera system. The proposed AI application allows detecting people in the surveillance area using a MobileNet-SSD architecture. In addition, using a robust Kalman filter bank, the algorithm can keep track of people in the video also providing people counting information. The detection results are excellent considering the constraints imposed on the process. The selected architecture for the edge node is based on a UpSquared2 device that includes a vision processor unit (VPU) capable of accelerating the AI CNN inference. The results section provides information about the image processing time when multiple video cameras are connected to the same edge node, people detection precision and recall curves, and the energy consumption of the system. The discussion of results shows the usefulness of deploying this smart camera node throughout a distributed surveillance system.

show abstract

“…Most indoor localization focuses on estimating the location of a single target [ 6 , 7 , 8 , 9 , 10 , 11 , 12 ], with only a few addressing multi-target localization. In [ 13 , 14 ], multi-targeting was achieved using UHF RFID and microphone devices, respectively.…”

Section: Introductionmentioning

confidence: 99%

Multiple Fingerprinting Localization by an Artificial Neural Network

Yoo

2022

Sensors

View full text Add to dashboard Cite

Fingerprinting localization is a promising indoor positioning methods thanks to its advantage of using preinstalled infrastructure. For example, WiFi signal strength can be measured by pre-existing WiFi routers. In the offline phase, the fingerprinting localization method first stores of position and RSSI measurement pairs in a dataset. Second, it predicts a target’s location by comparing the stored fingerprint database to the current measurement. The database size is normally huge, and data patterns are complicated; thus, an artificial neural network is used to model the relationship of fingerprints and locations. The existing fingerprinting locations, however, have been developed to predict only single locations. In practice, many users may require positioning services, and as such, the core algorithm should be capable of multiple localizations, which is the main contribution of this paper. In this paper, multiple fingerprinting localization is developed based on an artificial neural network and an analysis of the number of targets that can be estimated without loss of accuracy is conducted by experiments.

show abstract

A Cost-Effective Person-Following System for Assistive Unmanned Vehicles with Deep Learning at the Edge

Cited by 15 publications

References 58 publications

A Systematic Literature Review on Convolutional Neural Networks applied to Single Board Computers

A Systematic Literature Review on Convolutional Neural Networks applied to Single Board Computers

Smart Video Surveillance System Based on Edge Computing

Multiple Fingerprinting Localization by an Artificial Neural Network

Contact Info

Product

Resources

About