Cargando…

Real-Time Detection of Cook Assistant Overalls Based on Embedded Reasoning

Currently, the target detection based on convolutional neural network plays an important role in image recognition, speech recognition and other fields. However, the current network model features a complex structure, a huge number of parameters and resources. These conditions make it difficult to a...

Descripción completa

Detalles Bibliográficos
Autores principales: Sheng, Qinghua, Sheng, Haixiang, Gao, Peng, Li, Zhu, Yin, Haibing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8659890/
https://www.ncbi.nlm.nih.gov/pubmed/34884074
http://dx.doi.org/10.3390/s21238069
_version_ 1784613071112634368
author Sheng, Qinghua
Sheng, Haixiang
Gao, Peng
Li, Zhu
Yin, Haibing
author_facet Sheng, Qinghua
Sheng, Haixiang
Gao, Peng
Li, Zhu
Yin, Haibing
author_sort Sheng, Qinghua
collection PubMed
description Currently, the target detection based on convolutional neural network plays an important role in image recognition, speech recognition and other fields. However, the current network model features a complex structure, a huge number of parameters and resources. These conditions make it difficult to apply in embedded devices with limited computational capabilities and extreme sensitivity to power consumption. In this regard, the application scenarios of deep learning are limited. This paper proposes a real-time detection scheme for cook assistant overalls based on the Hi3559A embedded processor. With YOLOv3 as the benchmark network, this scheme fully mobilizes the hardware acceleration resources through the network model optimization and the parallel processing technology of the processor, and improves the network reasoning speed, so that the embedded device can complete the task of real-time detection on the local device. The experimental results show that through the purposeful cropping, segmentation and in-depth optimization of the neural network according to the specific processor, the neural network can recognize the image accurately. In an application environment where the power consumption is only 5.5 W, the recognition speed of the neural network on the embedded end is increased to about 28 frames (the design requirement was to achieve a recognition speed of 25 frames or more), so that the optimized network can be effectively applied in the back kitchen overalls identification scene.
format Online
Article
Text
id pubmed-8659890
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86598902021-12-10 Real-Time Detection of Cook Assistant Overalls Based on Embedded Reasoning Sheng, Qinghua Sheng, Haixiang Gao, Peng Li, Zhu Yin, Haibing Sensors (Basel) Article Currently, the target detection based on convolutional neural network plays an important role in image recognition, speech recognition and other fields. However, the current network model features a complex structure, a huge number of parameters and resources. These conditions make it difficult to apply in embedded devices with limited computational capabilities and extreme sensitivity to power consumption. In this regard, the application scenarios of deep learning are limited. This paper proposes a real-time detection scheme for cook assistant overalls based on the Hi3559A embedded processor. With YOLOv3 as the benchmark network, this scheme fully mobilizes the hardware acceleration resources through the network model optimization and the parallel processing technology of the processor, and improves the network reasoning speed, so that the embedded device can complete the task of real-time detection on the local device. The experimental results show that through the purposeful cropping, segmentation and in-depth optimization of the neural network according to the specific processor, the neural network can recognize the image accurately. In an application environment where the power consumption is only 5.5 W, the recognition speed of the neural network on the embedded end is increased to about 28 frames (the design requirement was to achieve a recognition speed of 25 frames or more), so that the optimized network can be effectively applied in the back kitchen overalls identification scene. MDPI 2021-12-02 /pmc/articles/PMC8659890/ /pubmed/34884074 http://dx.doi.org/10.3390/s21238069 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Sheng, Qinghua
Sheng, Haixiang
Gao, Peng
Li, Zhu
Yin, Haibing
Real-Time Detection of Cook Assistant Overalls Based on Embedded Reasoning
title Real-Time Detection of Cook Assistant Overalls Based on Embedded Reasoning
title_full Real-Time Detection of Cook Assistant Overalls Based on Embedded Reasoning
title_fullStr Real-Time Detection of Cook Assistant Overalls Based on Embedded Reasoning
title_full_unstemmed Real-Time Detection of Cook Assistant Overalls Based on Embedded Reasoning
title_short Real-Time Detection of Cook Assistant Overalls Based on Embedded Reasoning
title_sort real-time detection of cook assistant overalls based on embedded reasoning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8659890/
https://www.ncbi.nlm.nih.gov/pubmed/34884074
http://dx.doi.org/10.3390/s21238069
work_keys_str_mv AT shengqinghua realtimedetectionofcookassistantoverallsbasedonembeddedreasoning
AT shenghaixiang realtimedetectionofcookassistantoverallsbasedonembeddedreasoning
AT gaopeng realtimedetectionofcookassistantoverallsbasedonembeddedreasoning
AT lizhu realtimedetectionofcookassistantoverallsbasedonembeddedreasoning
AT yinhaibing realtimedetectionofcookassistantoverallsbasedonembeddedreasoning