The airborne unattended ground sensors (UGS) is used in this paper. Because the sensor is located on the ground, its detection effect for seismic signal is weaker than that of the probe type seismic detector buried under the ground, and it is easily disturbed by environmental factors. In order to solve this problem, the method of seismic-acoustic signal fusion is adopted in this paper. The raw waveform is used as the input, and the standard deviation (SD) is used as the input of the auxiliary channel to compensate the lack of scale information after the normalization processing. The experimental results show that the target classification method based on acoustic-seismic signal fusion is significantly better than using only seismic or acoustic signals. In addition, different fusion rules of seismic and acoustic signals are discussed from two levels of data-level and feature-level.
Research on Moving Ground Target Classification Method for Seismic and Acoustic Sensors
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Chapter : 84 ; 852-859
2022-03-18
8 pages
Article/Chapter (Book)
Electronic Resource
English
Automatic Target Classification of Slow Moving Ground Targets in Clutter
Online Contents | 2004
|Dynamic Airborne Sensor Resource Management for Ground Moving Target Tracking and Classification
British Library Conference Proceedings | 2000
|Road-Map Assisted Ground Moving Target Tracking
Online Contents | 2006
|