Strong sea clutter is the interference term that has the greatest impact on the target detection performance of sea radar,and the performance of the existing single detection quantity and multi-feature joint detection algorithms is extremely unstable.To solve the above problems,a sea radar target detection algorithm based on clustering is proposed.The algorithm extracts three feature quantities,that is,Relative Amplitude Variance (RAV),Relative Average Power (RAP) and Relative Vector Entropy (RVE).The k-Nearest Neighbor (kNN) algorithm in the clustering algorithm is modified to complete a kNN detector with controllable false alarm.In this feature space,the kNN detector is used to separate the target from clutters.The experimental results of measured radar data show that when the observation time is 0.512 s and 1.024 s, the average detection probability of this algorithm is 56.2% and 58.3% higher than that of the fractal based detector respectively (in HH polarization mode),and 29.2% and 31.3% higher than that of the three-feature-based detector respectively.It can be concluded that this algorithm can realize the sea radar target detection under complex sea conditions,and the detection effect is obviously better than that of the detector algorithm based on three features.