Next Article in Journal
Evaluation of the Weighted Mean X-ray Energy for an Imaging System Via Propagation-Based Phase-Contrast Imaging
Previous Article in Journal
Tracking of Deformable Objects Using Dynamically and Robustly Updating Pictorial Structures
Article

MH-MetroNet—A Multi-Head CNN for Passenger-Crowd Attendance Estimation

1
Institute of Applied Sciences and Intelligent Systems, National Research Council of Italy, 73100 Lecce, Italy
2
Institute of Intelligent Industrial Systems and Technologies for Advanced Manufacturing, National Research Council of Italy, Via Amendola 122 D/O, 70126 Bari, Italy
*
Author to whom correspondence should be addressed.
Received: 25 May 2020 / Revised: 24 June 2020 / Accepted: 29 June 2020 / Published: 2 July 2020
Knowing an accurate passengers attendance estimation on each metro car contributes to the safely coordination and sorting the crowd-passenger in each metro station. In this work we propose a multi-head Convolutional Neural Network (CNN) architecture trained to infer an estimation of passenger attendance in a metro car. The proposed network architecture consists of two main parts: a convolutional backbone, which extracts features over the whole input image, and a multi-head layers able to estimate a density map, needed to predict the number of people within the crowd image. The network performance is first evaluated on publicly available crowd counting datasets, including the ShanghaiTech part_A, ShanghaiTech part_B and UCF_CC_50, and then trained and tested on our dataset acquired in subway cars in Italy. In both cases a comparison is made against the most relevant and latest state of the art crowd counting architectures, showing that our proposed MH-MetroNet architecture outperforms in terms of Mean Absolute Error (MAE) and Mean Square Error (MSE) and passenger-crowd people number prediction. View Full-Text
Keywords: crowd counting; convolutional neural network; multi-head; smart cities; artificial intelligence crowd counting; convolutional neural network; multi-head; smart cities; artificial intelligence
Show Figures

Figure 1

MDPI and ACS Style

Mazzeo, P.L.; Contino, R.; Spagnolo, P.; Distante, C.; Stella, E.; Nitti, M.; Renò, V. MH-MetroNet—A Multi-Head CNN for Passenger-Crowd Attendance Estimation. J. Imaging 2020, 6, 62. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging6070062

AMA Style

Mazzeo PL, Contino R, Spagnolo P, Distante C, Stella E, Nitti M, Renò V. MH-MetroNet—A Multi-Head CNN for Passenger-Crowd Attendance Estimation. Journal of Imaging. 2020; 6(7):62. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging6070062

Chicago/Turabian Style

Mazzeo, Pier L.; Contino, Riccardo; Spagnolo, Paolo; Distante, Cosimo; Stella, Ettore; Nitti, Massimiliano; Renò, Vito. 2020. "MH-MetroNet—A Multi-Head CNN for Passenger-Crowd Attendance Estimation" J. Imaging 6, no. 7: 62. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging6070062

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop