Feature United Detection Algorithm on Floating Small Target of Sea Surface

This paper focus on the detection of floating small targets in high range resolution sea clutter. Floationg targets disarrange the scattering of neighboring sea surface, which results in that the received echoes in the cell targets located satisfy a non-additive model. While, it is hardly to model the paramters correlated to targets in the non-additive model. In order to keep away from the parameter modeling, target detection can be regarded as a binary-classification, where the clutter-only pattern is available for the classifier design and target detection is to judge whether the received echoes belong to the clutter-only pattern. For the classification, a feature united detection algrithm based on the non-additive model is proposed in the paper. First, two extracted features from the received echoes are combined into a normalized vector for target detection. Then, a convex hull training algorithm is utilized to determine a decision region. Finally, the detection rule is whether the decision region surrounds the vector. Experimental results by the raw IPIX radar data show that the proposed algorithm outperforms the compared algorithms. It provides a new detection guidance for the marine radar to detect samll targets.