.png){kind=icon}
.png){kind=icon}
Return
Time-frequency analysis based robust vehicle detection using seismic sensor
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jsv.2015.02.011.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper presents a robust time-frequency approach based on pseuclo-Wigner-Ville distribution assisted Renyi entropy (PWVD-RE) for vehicle detection. Seismic sensors are used to capture the ground vibrations generated by moving vehicles. One of the challenging tasks is to accurately localize a seismic event with minimal or no false alarm. PWVD gives the energy distribution of a non-stationary signal in the time-frequency plane. This energy distribution can be interpreted as probability density function (pdf). Renyi entropy is used as localized measure of the energy distribution. A higher value of entropy indicates the likehood of a possible seismic event. An optimized Constant False Alarm Rate (CFAR) detector is used for detection of events caused by moving vehicles. Experiments were performed with civilian vehicles for validation of the proposed method. The performance is compared with the classical spectrogram based approach. The results show significant improvement in false alarm rate and reasonable enhancement in detection rate. (C) 2015 Elsevier Ltd. All rights reserved.
Keywords:
MOVING TARGET DETECTION
MILITARY VEHICLES
CLASSIFICATION
DISTRIBUTIONS
INFORMATION
SIGNALS
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.9
Papers:
1.7W
Citations:
4.8W