一种应用时频域波形熵特征的海面目标识别方法
By employing the time-frequency domain waveform entropy feature method, utilizing radar echo data caching and time-frequency analysis, and combining it with the support vector machine classification algorithm, the similarity problem between ship targets and floating targets in radar identification was solved, achieving efficient target identification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NAVAL AVIATION UNIV
- Filing Date
- 2024-10-21
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to effectively distinguish between ship targets and floating targets under both high-resolution and low-resolution radar systems. In particular, when the radar beam illuminates along the ship's side, ship targets and floating targets exhibit similar one-dimensional range profile characteristics, which affects identification performance.
The time-frequency domain waveform entropy feature method is adopted. By buffering target echo data, extracting time-frequency domain waveform entropy features and using support vector machine classification algorithm, the energy distribution characteristics of ship targets and floating targets in the time-frequency domain are extracted by time-frequency analysis method. Combined with waveform entropy quantization to measure the stationarity of the Doppler channel energy amplitude sequence, feature separability is achieved.
Within a 0.25s observation period, the accuracy of identifying ship targets and floating targets was improved to 93.98%, which is 39.56% higher than existing methods.
Smart Images
Figure CN119395654B_ABST