Pedestrian detection based on improved LeNet-5 convolutional neural network

In this article, according to the real-time and accuracy requirements of advanced vehicle-assisted driving in pedestrian detection, an improved LeNet-5 convolutional neural network is proposed. Firstly, the structure of LeNet-5 network model is analyzed, and the structure and parameters of the netwo...

Full description

Bibliographic Details
Main Authors:	Chuan-Wei Zhang, Meng-Yue Yang, Hong-Jun Zeng, Jian-Ping Wen
Format:	Article
Language:	English
Published:	SAGE Publishing 2019-09-01
Series:	Journal of Algorithms & Computational Technology
Online Access:	https://doi.org/10.1177/1748302619873601

id	doaj-3ad4aee9776240ab9b8753b56f5b0ff1
record_format	Article
spelling	doaj-3ad4aee9776240ab9b8753b56f5b0ff12020-11-25T03:56:50ZengSAGE PublishingJournal of Algorithms & Computational Technology1748-30262019-09-011310.1177/1748302619873601Pedestrian detection based on improved LeNet-5 convolutional neural networkChuan-Wei ZhangMeng-Yue YangHong-Jun ZengJian-Ping WenIn this article, according to the real-time and accuracy requirements of advanced vehicle-assisted driving in pedestrian detection, an improved LeNet-5 convolutional neural network is proposed. Firstly, the structure of LeNet-5 network model is analyzed, and the structure and parameters of the network are improved and optimized on the basis of this network to get a new LeNet network model, and then it is used to detect pedestrians. Finally, the miss rate of the improved LeNet convolutional neural network is found to be 25% by contrast and analysis. The experiment proves that this method is better than SA-Fast R-CNN and classical LeNet-5 CNN algorithm.https://doi.org/10.1177/1748302619873601
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Chuan-Wei Zhang Meng-Yue Yang Hong-Jun Zeng Jian-Ping Wen
spellingShingle	Chuan-Wei Zhang Meng-Yue Yang Hong-Jun Zeng Jian-Ping Wen Pedestrian detection based on improved LeNet-5 convolutional neural network Journal of Algorithms & Computational Technology
author_facet	Chuan-Wei Zhang Meng-Yue Yang Hong-Jun Zeng Jian-Ping Wen
author_sort	Chuan-Wei Zhang
title	Pedestrian detection based on improved LeNet-5 convolutional neural network
title_short	Pedestrian detection based on improved LeNet-5 convolutional neural network
title_full	Pedestrian detection based on improved LeNet-5 convolutional neural network
title_fullStr	Pedestrian detection based on improved LeNet-5 convolutional neural network
title_full_unstemmed	Pedestrian detection based on improved LeNet-5 convolutional neural network
title_sort	pedestrian detection based on improved lenet-5 convolutional neural network
publisher	SAGE Publishing
series	Journal of Algorithms & Computational Technology
issn	1748-3026
publishDate	2019-09-01
description	In this article, according to the real-time and accuracy requirements of advanced vehicle-assisted driving in pedestrian detection, an improved LeNet-5 convolutional neural network is proposed. Firstly, the structure of LeNet-5 network model is analyzed, and the structure and parameters of the network are improved and optimized on the basis of this network to get a new LeNet network model, and then it is used to detect pedestrians. Finally, the miss rate of the improved LeNet convolutional neural network is found to be 25% by contrast and analysis. The experiment proves that this method is better than SA-Fast R-CNN and classical LeNet-5 CNN algorithm.
url	https://doi.org/10.1177/1748302619873601
work_keys_str_mv	AT chuanweizhang pedestriandetectionbasedonimprovedlenet5convolutionalneuralnetwork AT mengyueyang pedestriandetectionbasedonimprovedlenet5convolutionalneuralnetwork AT hongjunzeng pedestriandetectionbasedonimprovedlenet5convolutionalneuralnetwork AT jianpingwen pedestriandetectionbasedonimprovedlenet5convolutionalneuralnetwork
_version_	1724463528510750720

Pedestrian detection based on improved LeNet-5 convolutional neural network

Similar Items