A Multi-Feature Deep Learning Algorithm for Urban Traffic Classification with Limited Labeled Data

Authors: Rohan Putatunda, Aryya Gangopadhyay

Abstract:

Acoustic sensors, if embedded in smart street lights, can help in capturing the activities (car honking, sirens, events, traffic, etc.) in cities. Needless to say, the acoustic data from such scenarios are complex due to multiple audio streams originating from different events, and when decomposed to independent signals, the amount of retrieved data volume is small in quantity which is inadequate to train deep neural networks. So, in this paper, we address the two challenges: a) separating the mixed signals, and b) developing an efficient acoustic classifier under data paucity. So, to address these challenges, we propose an architecture with supervised deep learning, where the initial captured mixed acoustics data are analyzed with Fast Fourier Transformation (FFT), followed by filtering the noise from the signal, and then decomposed to independent signals by fast independent component analysis (Fast ICA). To address the challenge of data paucity, we propose a multi feature-based deep neural network with high performance that is reflected in our experiments when compared to the conventional convolutional neural network (CNN) and multi-layer perceptron (MLP).

Keywords: FFT, ICA, vehicle classification, multi-feature DNN, CNN, MLP.

References:

[1] S. Kozhisseri and M. Bikdash. Spectral features for the classification of civilian vehicles using acoustic sensors. In 2009IEEE Workshop on Computational Intelligence in Vehicles and vehicular Systems, pages 93–100, March 2009.
[2] Ali Dalir, Ali Asghar Beheshti Shirazi, and Morteza Hoseini Masoom. Classification of vehicles based on audio signals using quadratic discriminant analysis and high energy feature vectors. CoRR, abs/1804.01212, 2018.
[3] V. Ovchinnikov A. Grakovski. The analysis of possibility of acoustic sensors application for moving road vehicles detecting. In Proceedings of the 9th International Conference “Reliability and Statistics in Transportation and Communication” (Rel-Stat’09), 2009.
[4] Peter E. William and Michael W. Hoffman. Efficient sensor network vehicle classification using peak harmonics of acoustic emissions. In Edward M.Carapezza, editor, Unattended Ground, Sea, and Air Sensor Technologies and Applications X, volume 6963, pages 198 – 209. International Society for Optics and photonics, SPIE, 2008.
[5] Shigemi Ishida, Song Liu, Kohei Mimura, Shigeaki Tagashira, and Akira Fukuda. Design of acoustic vehicle count system using dtw. In ITS World Congress, Melbourne, Australia, 10 2016.
[6] Rijurekha Sen, Abhinav Maurya, Bhaskaran Raman, Rupesh Mehta, Ramakrishnan Kalyanaraman, Nagamanoj Vankadhara, Swaroop Roy, and Prashima Sharma. Kyun queue: A sensor network system to monitor road traffic queues. pages 127–140,11 2012.
[7] Maria Nadia Postorino and Giuseppe M. L. Sarn`e. An agent-based sensor grid to monitor urban traffic. CEUR Workshop Proceedings, 1260, 01 2014.
[8] M. V. Peppa, D. Bell, T. Komar, and W. Xiao. Urban traffic flow analysis based on deep learning car detection from cctv image series. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-4:499–506,2018.
[9] Mohammadhani Fouladgar, Mostafa Parchami, Ramez Elmasri, and Amir Ghaderi. Scalable deep traffic flow neural networks for urban traffic congestion prediction. CoRR, abs/1703.01006,2017.
[10] Manuel Lopez-Martin, Bel ́en Carro, Antonio Sanchez-Esguevillas, and Jaime Lloret. Network traffic classifier with convolutional and recurrent neural networks for internet of things. IEEE Access, PP:1–1, 09 2017.