Accurate pedestrian localization in overhead depth images via Height-Augmented HOG
DOI:
https://doi.org/10.17815/CD.2020.30Keywords:
real-life pedestrian dynamics measurements, depth-based localization, machine learning, augmented HOG features, high-density localizationAbstract
We tackle the challenge of reliably and automatically localizing pedestrians in real-life conditions through overhead depth imaging at unprecedented high-density conditions. Leveraging upon a combination of Histogram of Oriented Gradients-like feature descriptors, neural networks, data augmentation and custom data annotation strategies, this work contributes a robust and scalable machine learning-based localization algorithm, which delivers near-human localization performance in real-time, even with local pedestrian density of about 3 ped/m2, a case in which most stateof- the art algorithms degrade significantly in performance.References
A. Corbetta, C. Lee, R. Benzi, A. Muntean and F. Toschi, “Fluctuations around mean walking
behaviors in diluted pedestrian flows,” in Physical Review E, vol. 95, no. 3, 032316, 2017.
A. Corbetta, L. Bruno, A. Muntean and F. Toschi, “High Statistics Measurements of Pedestrian
Dynamics,” Transportation Research Procedia, vol. 2, pp. 96–104, 2014.
Microsoft Corporation, “Kinect for Xbox 360,” Redmond, WA, USA.
A. Corbetta, J. Meeusen, C. Lee and F. Toschi, “Continuous measurements of real-life
bidirectional pedestrian flows on a wide walkway,” in Proceedings of Pedestrian and Evacuation
Dynamics, pp. 18–24, 2016.
D. Brscic, T. Kanda, T. Ikeda and T. Miyashita, “Person Tracking in Large Public Spaces Using
-D Range Sensors,” in IEEE Transactions on Human-Machine Systems, vol. 43, no. 6, pp. 522–
, 2013.
S. Seer, N. Brändle and C. Ratti, “Kinects and human kinetics: A new approach for studying
pedestrian behavior,” in Transportation Research Part C: Emerging Technologies, vol. 48, pp.
–228, 2014.
A. Corbetta, W. Kroneman, M. Donners, A. Haans, P. Ross, M. Trouwborst, S. vd Wijdeven, M.
Hultermans, D. Sekulowski, F. vd Heijden, S. Mentink and F. Toschi, “A large-scale real-life
crowd steering experiment via arrow-like stimuli,” in Pedestrian and Evacuation Dynamics, 2018
(accepted).
N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” in IEEE
Computer Society Conference on Computer Vision and Pattern Recognition (CVPR05), 2005, pp.
–893
A. Corbetta, “Multiscale crowd dynamics: physical analysis, modeling and applications,” Ph. D.
thesis, Eindhoven University of Technology, 2016.
J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You Only Look Once: Unified, Real-Time
Object Detection,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition
(CVPR), 2016, pp. 779–788.
A. Corbetta, V. Menkovski and F. Toschi, “Weakly supervised training of deep convolutional
neural networks for overhead pedestrian localization in depth fields,” in 14th IEEE International
Conference on Advanced Video and Signal Based Surveillance (AVSS), 2017, pp 1-6.
R. Collobert and S. Bengio, “Links between perceptrons, MLPs and SVMs,” in Proceedings of
the Twenty-first international conference on Machine learning - ICML 04, 2004.
Q. Xia, H.-D. Zhu, Y. Gan and L. Shang, “Plant Leaf Recognition Using Histograms of
Oriented Gradients,” in Intelligent Computing Methodologies Lecture Notes in Computer Science,
pp. 369–374, 2014.
D. Ciresan, U. Meier and J. Schmidhuber, “Multi-column deep neural networks for image
classification,” Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern
Recognition, 2012, pp. 3642-3649.
L. Perez and J. Wang, “The Effectiveness of Data Augmentation in Image Classification using
Deep Learning,” arXiv:1712.04621, 2017.
K.-K. Sung, “Learning and example selection for object and pattern detection,” Ph. D. thesis,
Massachusetts Institute of Technology, 1996.
M. Abadi, et al, “TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems,”
Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation
(OSDI’16), 2016, pp 265-283.
F. Chollet, et al, “Keras,” 2015. Available: https://keras.io.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2020 Werner Kroneman, Alessandro Corbetta, Federico Toschi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to Collective Dynamics agree to publish their articles under the Creative Commons Attribution 4.0 license.
This license allows:
Share — copy and redistribute the material in any medium or format
Adapt — remix, transform, and build upon the material
for any purpose, even commercially.
The licensor cannot revoke these freedoms as long as you follow the license terms.
Authors retain copyright of their work. They are permitted and encouraged to post items submitted to Collective Dynamics on personal or institutional websites and repositories, prior to and after publication (while providing the bibliographic details of that publication).
