Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Jul 2;6(7):62.
doi: 10.3390/jimaging6070062.

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

Pier Luigi Mazzeo  1 , Riccardo Contino  1 , Paolo Spagnolo  1 , Cosimo Distante  1 , Ettore Stella  2 , Massimiliano Nitti  2 , Vito Renò  2
Affiliations

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

Pier Luigi Mazzeo et al. J Imaging. .

Abstract

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.

Keywords: artificial intelligence; convolutional neural network; crowd counting; multi-head; smart cities.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Proposed MH-MetroNet architecture.
Figure 2
Figure 2
UCF_CC_50 crowd images [12].
Figure 3
Figure 3
ShanghaiTech part A crowd images [14].
Figure 4
Figure 4
ShanghaiTech part B crowd images [14].
Figure 5
Figure 5
Subway cars passenger-crowd images.
Figure 6
Figure 6
UCF_CC_50 density map estimation examples, (Left) the crowd image, (Center) ground-truth density map, (Right) estimated density map.
Figure 7
Figure 7
ShanghaiTech part A density map estimation examples. Left the crowd image, middle ground-truth density map, right estimated density map.
Figure 8
Figure 8
ShanghaiTech part B density map estimation examples. Left the crowd image, middle ground-truth density map, right estimated density map.
Figure 9
Figure 9
Subway cars dataset density map estimation examples:(Left) the crowd image, (center) ground-truth density map, (right) estimated density map (with passengers count).
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Ullah H., Altamimi A.B., Uzair M., Ullah M. Anomalous entities detection and localization in pedestrian flows. Neurocomputing. 2018;290:74–86. doi: 10.1016/j.neucom.2018.02.045. - DOI
    1. Qi W., Su H., Aliverti A. A Smartphone-based Adaptive Recognition and Real-time Monitoring System for Human Activities. IEEE Trans. Hum. Mach. Syst. 2020 doi: 10.1109/THMS.2020.2984181. - DOI
    1. Su H., Qi W., Yang C., Sandoval J., Ferrigno G., Momi E.D. Deep Neural Network Approach in Robot Tool Dynamics Identification for Bilateral Teleoperation. IEEE Robot. Autom. Lett. 2020;5:2943–2949. doi: 10.1109/LRA.2020.2974445. - DOI
    1. Dollar P., Wojek C., Schiele B., Perona P. Pedestrian Detection: An Evaluation of the State of the Art. IEEE PAMI. 2012;34:743–761. doi: 10.1109/TPAMI.2011.155. - DOI - PubMed
    1. Dalal N., Triggs B. Histograms of Oriented Gradients for Human Detection; Proceedings of the IEEE CVPR 2005; San Diego, CA, USA. 20–25 June 2005;

LinkOut - more resources