A Multistage Detection Framework Based on TFA and Multiframe Correlation for HFSWR
Bibliographic record
Abstract
Maritime surveillance heavily relies on high-frequency surface wave radar (HFSWR) systems. However, clutter and interference make it difficult to accurately detect vessel targets using a single-frame detection method. This study introduces an improved time-frequency analysis (TFA) algorithm to enhance the features in single-frame detection. In this article, TFA, multiframe correlation, and deep neural networks are integrated to develop a three-stage detection framework. Firstly, faster R-CNN is customized for the preprocessing stage to identify sea clutter regions. Then, based on the range-Doppler (RD) spectrum, suspicious targets are swiftly identified amidst clutter in the initial stage. Subsequently, the improved TFA algorithm is applied to adjacent range cells of suspicious targets to generate multiframe TF images, forming a three-dimensional data block structured as time-range-Doppler frequency. To reduce computational complexity, a TFA method using multisynchrosqueezing transform is employed, enhancing detection accuracy for targets within cluttered regions. In the final stage, a 3DResnet model is utilized to leverage the differences in features between clutter and targets across three dimensions. This allows for distinguishing genuine targets from false targets using time series information from multiple frames. Comparative analysis against classical target detection algorithms demonstrates the superior detection performance of the proposed framework within clutter regions. This showcases its potential for enhancing the maritime surveillance capabilities of HFSWR.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".