Cover Image

Convolutional neural network for people counting using UWB impulse radar

People counting plays a crucial role in various sensing applications such as in smart cities and shopping malls. In this paper, we propose a data-driven solution that uses a low power ultra-wideband impulse (UWB) radar to count the number of random walking people in an indoor space. A pre-processing...

Full description

Saved in:
Bibliographic Details
Main Authors: C.-T. Pham, V.S. Luong, D.-K. Nguyen, H.H.T. Vu, M. Le1
Format: Bài trích
Language:eng
Published: Journal of Instrumentation 2021
Online Access:https://iopscience.iop.org/article/10.1088/1748-0221/16/08/P08031
https://dlib.phenikaa-uni.edu.vn/handle/PNK/2860
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:PNK-2860
record_format dspace
spelling oai:localhost:PNK-28602022-08-17T05:54:48Z Convolutional neural network for people counting using UWB impulse radar C.-T. Pham V.S. Luong D.-K. Nguyen H.H.T. Vu M. Le1 People counting plays a crucial role in various sensing applications such as in smart cities and shopping malls. In this paper, we propose a data-driven solution that uses a low power ultra-wideband impulse (UWB) radar to count the number of random walking people in an indoor space. A pre-processing signal processing method is applied to clean clutter signals from UWB radar. Instead of the conventional counting methods, which manually extract features and learned from effective data patterns, we investigated deep convolutional neural networks (CNNs) that automatically learn from the data to count the number of people in an indoor space. The CNN model could accurately predict up to 97% accuracy for up to 10 people random walking in an area of 5 × 5 m. The different settings of the CNN models, such as the data input window size, and kernel size in each layer, will be investigated 2021-09-14T07:14:55Z 2021-09-14T07:14:55Z 2021 Bài trích https://iopscience.iop.org/article/10.1088/1748-0221/16/08/P08031 https://dlib.phenikaa-uni.edu.vn/handle/PNK/2860 eng Journal of Instrumentation
institution Digital Phenikaa
collection Digital Phenikaa
language eng
description People counting plays a crucial role in various sensing applications such as in smart cities and shopping malls. In this paper, we propose a data-driven solution that uses a low power ultra-wideband impulse (UWB) radar to count the number of random walking people in an indoor space. A pre-processing signal processing method is applied to clean clutter signals from UWB radar. Instead of the conventional counting methods, which manually extract features and learned from effective data patterns, we investigated deep convolutional neural networks (CNNs) that automatically learn from the data to count the number of people in an indoor space. The CNN model could accurately predict up to 97% accuracy for up to 10 people random walking in an area of 5 × 5 m. The different settings of the CNN models, such as the data input window size, and kernel size in each layer, will be investigated
format Bài trích
author C.-T. Pham
V.S. Luong
D.-K. Nguyen
H.H.T. Vu
M. Le1
spellingShingle C.-T. Pham
V.S. Luong
D.-K. Nguyen
H.H.T. Vu
M. Le1
Convolutional neural network for people counting using UWB impulse radar
author_facet C.-T. Pham
V.S. Luong
D.-K. Nguyen
H.H.T. Vu
M. Le1
author_sort C.-T. Pham
title Convolutional neural network for people counting using UWB impulse radar
title_short Convolutional neural network for people counting using UWB impulse radar
title_full Convolutional neural network for people counting using UWB impulse radar
title_fullStr Convolutional neural network for people counting using UWB impulse radar
title_full_unstemmed Convolutional neural network for people counting using UWB impulse radar
title_sort convolutional neural network for people counting using uwb impulse radar
publisher Journal of Instrumentation
publishDate 2021
url https://iopscience.iop.org/article/10.1088/1748-0221/16/08/P08031
https://dlib.phenikaa-uni.edu.vn/handle/PNK/2860
_version_ 1751856266569842688
score 8.891145

Similar Items