Target Detection Method in BTR based on SVM
- Resource Type
- Conference
- Authors
- Wang, Qiang; Cheng, Yongmei; Liu, Chengyuan; Cheng, Siyuan; Yang, Su
- Source
- 2021 China Automation Congress (CAC) Automation Congress (CAC), 2021 China. :1509-1514 Oct, 2021
- Subject
- Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Support vector machines
Automation
Object detection
Feature extraction
Robustness
Data mining
Underwater acoustics
BTR
SVM
TBD
Target Detection
- Language
- ISSN
- 2688-0938
Aiming at the problem of low SNR in complex sea conditions, which leads to low target detection rate and robustness in BTR, a BTR target detection method based on SVM is proposed. The method uses the waveform difference between target and noise in spatial domain to give the feature description; In this paper, SVM is used to train BTR target detection model; The underwater acoustic target point trace detection is completed by region-to-point trace extraction method. The experimental results show that the proposed method can extract underwater acoustic targets in low SNR effectively and robustly.