A new spectral estimation-based feature extraction method for vehicle classification in distributed sensor networks

Ground vehicle detection and classification with distributed sensor networks is of growing interest for bordersecurity. Different sensing modalities including electro-optical, seismic, and acoustic were evaluated individually and incombination to develop a more efficient system. Despite previous works that mostly studied frequency-domain featuresand acoustic sensors, in this work we analyzed the classification performance for both frequency and time-domain featuresand seismic and acoustic modalities. Despite their infrequent use, we show that when fused with frequency-domainfeatures, time-domain features improve the classification performance and reduce the false positive rate, especially forseismic signals. We investigated the performance of seismic sensors and showed that the classification performance varieswith the type of road due to the distinct spectral characteristics of the medium. Our proposed classifier fuses time andfrequency-domain features and acoustic and seismic modalities to achieve the highest classification rate of 98.6% usinga relatively small number of features.

PDF

___

[1] Padmavathi G, Shanmugapriya D, Kalaivani M. A study on vehicle detection and tracking using wireless sensor networks. Wireless Sensor Network 2010; 2: 173-185. doi: 10.4236/wsn.2010.22023
[2] Narayanaswami R, Gandhe A, Tyurina A, Mehra RK. Sensor fusion and feature-based human/animal classification for unattended ground sensors. In: IEEE International Conference on Technologies for Homeland Security (HST); Waltham, MA, USA; 2010. pp. 344–350.
[3] Faghfouri AE, Frish MB. Robust discrimination of human footsteps using seismic signals. In: Proceedings of SPIE 8046, Unattended Ground, Sea, and Air Sensor Technologies and Applications XIII; Orlando, FL, USA; 2011. p. 80460D. doi: 10.1117/12.882726
[4] Hodge VJ, O’Keefe S, Weeks M, Moulds A. Wireless sensor networks for condition monitoring in the railway industry: a survey. IEEE Transactions on Intelligent Transportation Systems 2015; 16: 1088–1106. doi: 10.1109/TITS.2014.2366512
[5] Mayvan AD, Beheshti SA, Masoom MH. Classification of vehicles based on audio signals using quadratic discriminant analysis and high energy feature vectors. International Journal of Soft Computing 2015; 6: 53–64. doi: 10.5121/ijsc.2015.6105
[6] Yang B, Lei Y. Vehicle detection and classification for low-speed congested traffic with anisotropic magnetoresistive sensor. IEEE Sensors Journal 2015; 15: 1132–1138. doi: 10.1109/JSEN.2014.2359014
[7] Nellore K, Hancke GP. A survey on urban traffic management system using wireless sensor networks. Sensors 2016; 16: 157. doi: 10.3390/s16020157
[8] Odat E, Shamma JS, Claudel C. Vehicle classification and speed estimation using combined passive infrared/ultrasonic sensors. IEEE Transactions on Intelligent Transportation Systems 2018; 19: 1593-1606. doi: 10.1109/TITS.2017.2727224
[9] Atrey PK, Maddage NC, Kankanhalli MS. Audio based event detection for multimedia surveillance. In: IEEE International Conference on Acoustics, Speech and Signal Processing; Toulouse, France; 2006. pp. 1-5.
[10] Küçükbay SE, Sert M, Yazici A. Use of acoustic and vibration sensor data to detect objects in surveillance wireless sensor networks. In: International Conference on Control Systems and Computer Science; Bucharest, Romania; 2017. pp. 207–212.
[11] Duarte MF, Hu YH. Vehicle classification in distributed sensor networks. Journal of Parallel and Distributed Computing 2004; 64: 826–838. doi: 10.1016/j.jpdc.2004.03.020
[12] Mazarakis GP, Avaritsiotis JN. Vehicle classification in sensor networks using time-domain signal processing and neural networks. Microprocessors and Microsystems 2007; 31: 381–392. doi: 10.1016/j.micpro.2007.02.005
[13] Kornaropoulos EM, Tsakalides P. A novel KNN classifer for acoustic vehicle classification based on alpha-stable statistical modeling. In: IEEE/SP Workshop on Statistical Signal Processing; Cardiff, UK; 2009. pp. 1–4.
[14] Wang R, Guo S, Li Y, Zhang Y. Fisher discriminative dictionary learning for vehicle classification in acoustic sensor networks. Journal of Signal Processing Systems 2017; 86: 99–107. doi: 10.1007/s11265-016-1105-x
[15] Wang K, Wang R, Feng Y, Zhang H, Huang Q et al. Vehicle recognition in acoustic sensor networks via sparse representation. In: IEEE International Conference on Multimedia and Expo Workshops; Chengdu, China; 2014. pp. 1–4.
[16] Taheri SM, Nosrati H. Acoustic signature identification using distributed diffusion adaptive networks. In: International Symposium on Communication Systems, Networks & Digital Signal Processing; Manchester, UK; 2014. pp. 943–948.
[17] Guo S, Wang R, Liu B, Wei Q, Li Y. Vehicle classification in acoustic sensor networks based on hybrid dictionary learning. In: IEEE International Conference on Big Data Intelligence and Computing; Auckland, New Zealand; 2016. pp. 861–865. doi: 10.1109/DASC-PICom-DataCom-CyberSciTec.2016.147
[18] Ntalampiras S. Moving vehicle classification using wireless acoustic sensor networks. IEEE Transactions on Emerging Topics in Computational Intelligence 2018; 2: 129–138. doi: 10.1109/TETCI.2017.2783340
[19] Kakar VK, Kandpal M. Techniques of acoustic feature extraction for detection and classification of ground vehicles. International Journal of Emerging Technology and Advanced Engineering 2013; 3: 419–426.
[20] Lara-Cueva R, Bernal P, Saltos MG, Benítez DS, Rojo-Álvarez JL. Time and frequency feature selection for seismic events from Cotopaxi Volcano. In: Asia-Pacifc Conference on Computer Aided System Engineering; Quito, Ecuador; 2015. pp. 129–134.
[21] Loshchilov I, Hutter F. Sgdr: Stochastic gradient descent with warm restarts. In: International Conference on Learning Representations; Toulon, France; 2017. pp. 1-16
[22] Trottier L, Giguere P, Chaib-Draa B. Parametric exponential linear unit for deep convolutional neural networks. In: IEEE International Conference On Machine Learning And Applications; Cancun, Mexico; 2017. pp. 207-214.
[23] Fernández-Redondo M, Hernandez-Espinosa C. Weight initialization methods for multilayer feedforward. In: European Symposium on Artificial Neural Networks; Brussels, Belgium; 2001. pp. 119–124.
[24] Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics; Sardinia, Italy; 2010. pp. 249–256.