CrossCount: A Deep Learning System for Device-Free Human Counting Using WiFi

Counting humans is an essential part of many people-centric applications. In this paper, we propose CrossCount: an accurate deep-learning-based human count estimator that uses a single WiFi link to estimate the human count in an area of interest. The main idea is to depend on the temporal link-blockage pattern as a discriminant feature that is more robust to wireless channel noise than the signal strength, hence delivering a ubiquitous and accurate human counting system. As part of its design, CrossCount addresses a number of deep learning challenges such as class imbalance and training data augmentation for enhancing the model generalizability. Implementation and evaluation of CrossCount in multiple testbeds show that it can achieve a human counting accuracy to within a maximum of 2 persons 100% of the time. This highlights the promise of CrossCount as a ubiquitous crowd estimator with nonlabor-intensive data collection from off-the-shelf devices.

[1]  Ronald Y. Chang,et al.  Device-Free Indoor People Counting Using Wi-Fi Channel State Information for Internet of Things , 2017, GLOBECOM 2017 - 2017 IEEE Global Communications Conference.

[2]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[3]  Xiangmin Xu,et al.  Multi-scale convolutional neural networks for crowd counting , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[4]  Srinivas S. Kruthiventi,et al.  CrowdNet: A Deep Convolutional Network for Dense Crowd Counting , 2016, ACM Multimedia.

[5]  Moustafa Youssef,et al.  Zero-Calibration Device-Free Localization for the IoT Based on Participatory Sensing , 2018, 2018 IEEE Global Communications Conference (GLOBECOM).

[6]  Moustafa Youssef,et al.  CoSDEO 2016 Keynote: A decade later — Challenges: Device-free passive localization for wireless environments , 2007, 2016 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops).

[7]  Zhiqiang Li,et al.  Deep People Counting with Faster R-CNN and Correlation Tracking , 2016, ICIMCS.

[8]  Takuya Yoshida,et al.  Estimating the number of people using existing WiFi access point in indoor environment , 2015 .

[9]  Saandeep Depatla,et al.  Occupancy Estimation Using Only WiFi Power Measurements , 2015, IEEE Journal on Selected Areas in Communications.

[10]  Xiaonan Guo,et al.  Wi-Counter: Smartphone-Based People Counter Using Crowdsourced Wi-Fi Signal Data , 2015, IEEE Transactions on Human-Machine Systems.

[11]  Paul Lukowicz,et al.  Bluetooth based collaborative crowd density estimation with mobile phones , 2013, 2013 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[12]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[13]  Marcus Liwicki,et al.  Parallel sequence classification using recurrent neural networks and alignment , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[14]  Xiaogang Wang,et al.  Cross-scene crowd counting via deep convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Moustafa Youssef,et al.  Nuzzer: A Large-Scale Device-Free Passive Localization System for Wireless Environments , 2009, IEEE Transactions on Mobile Computing.

[16]  Mauro De Sanctis,et al.  A Trained-once Crowd Counting Method Using Differential WiFi Channel State Information , 2016, WPA '16.

[17]  Jiro Katto,et al.  A Study on Passive Crowd Density Estimation using Wireless Sensors , 2008 .

[18]  Jayashankar M. Swaminathan,et al.  Effect of Traffic on Sales and Conversion Rates of Retail Stores , 2012, Manuf. Serv. Oper. Manag..

[19]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[20]  Moustafa Youssef,et al.  Effectiveness of Data Augmentation in Cellular-based Localization Using Deep Learning , 2019, 2019 IEEE Wireless Communications and Networking Conference (WCNC).

[21]  Shaojie Tang,et al.  Electronic frog eye: Counting crowd using WiFi , 2014, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[22]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[23]  Saandeep Depatla,et al.  Crowd Counting Through Walls Using WiFi , 2017, 2018 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[24]  F. J. Yanovsky,et al.  Through-the-wall surveillance technologies , 2012, 2012 6th International Conference on Ultrawideband and Ultrashort Impulse Signals.

[25]  David Mease,et al.  Boosted Classification Trees and Class Probability/Quantile Estimation , 2007, J. Mach. Learn. Res..