A fast target detection method in SAR images under strong sea clutter

Abstract

The invention discloses a fast detection method of SAR (Synthetic Aperture Radar) image targets under strong sea clutter. The method comprises: S1, adopting a regional block dividing strategy to divide a large-scene SAR image into a plurality of sub-block SAR images; S2, acquiring target-clutter contrast-enhanced sub-block coherence images, which correspond to the sub-block SAR images, on the basis of sub-aperture coherence processing; S3. screening out target sub-block coherence images containing the targets and corresponding target sub-block SAR images on the basis of significance of the sub-block coherence images, and using the same as candidate target sub-block images; S4, carrying out fine target detection on the candidate target sub-block images, wherein fine target detection includes detecting low-scattering target pixels for the target sub-block coherence images, detecting target detail contours for the target sub-block SAR images, and fusing two detection results; and S5, removing false alarms for a fine target detection result, and carrying out regional merging to obtain a final target detection result. According to the method, the targets which are in the sea-surface large-scene SAR image and of complex structures and low scattering intensity can be detected, a detection rate is high, a false-alarm rate is low, self-adaptability is high, and a calculation speed is fast.

Description

technical field [0001] The invention relates to a fast target detection method, in particular to a fast target detection method for SAR images under strong sea clutter, and belongs to the technical field of radar target recognition. Background technique [0002] Synthetic Aperture Radar (SAR) imaging is an important means of sea surface target detection, surveillance and identification, and has important application value in the fields of marine traffic supervision, fishery management, and maritime military target reconnaissance. Target detection is a key processing technology in the SAR image target recognition system, which can extract the region of interest (Region Of Interest, ROI) from the complex large-scene marine environment, and provide the necessary information input for further target feature extraction and recognition , so its performance will have an important impact on the accuracy and efficiency of the entire recognition system. [0003] At present, the most ...

AI Technical Summary

Problems solved by technology

However, the above two algorithms are directly applied to the iterative index processing of large scene images and the complex K-distribution parameter estimation, which will bring a large computational burden and make the target detection speed slower.

In addition, these index CFAR algorithms do not consider clutter suppression preprocessing, and the targets under strong clutter are easily missed or have a high false alarm rate.

Images