Abstract
Seismic signals can be used for vehicle classification. However, this task becomes difficult as a result of various noises. Convolutional neural networks (CNNs) have been employed successfully in many fields as a result of its ability to learn low-/mid-/high-level features. This letter investigates the application of CNN to classify vehicles by means of the seismic trace that the geophone recorded. The study has two primary contributions. First, a deep CNN architecture for vehicle classification by seismic signal is proposed. Second, considering the similarities between speech recognition and vehicle classification based on seismic signal, log-scaled frequency cepstral coefficient (LFCC) matrix is proposed to extract features of seismic signals as the input of CNN. The data from DARPA’s SensIt project, which contain seismic signals from two kinds of vehicles, are used to evaluate the method. By combining the proposed LFCC matrix and CNN architecture, the algorithm produces a state-of-the-art result compared with other methods.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.