Name
Title | ||
|---|---|---|
Vehicle Classification Based on Seismic Signatures Using Convolutional Neural Network |
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. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/LGRS.2018.2879687 | IEEE Geoscience and Remote Sensing Letters |
Keywords | Field | DocType |
Mel frequency cepstral coefficient,Convolution,Feature extraction,Computer architecture,Convolutional neural networks | Mel-frequency cepstrum,Computer vision,Pattern recognition,Convolution,Convolutional neural network,Matrix (mathematics),Geophone,Cepstrum,Feature extraction,Artificial intelligence,Seismic trace,Mathematics | Journal |
Volume | Issue | ISSN |
16 | 4 | 1545-598X |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guozheng Jin | 1 | 0 | 0.34 |
| Bin Ye | 2 | 20 | 3.28 |
| Yezhou Wu | 3 | 100 | 12.21 |
| Fengzhong Qu | 4 | 196 | 19.02 |