Optimizing Multiple-Target Cfar Detection Efficacy Through Advanced Intelligent Clustering Algorithms Within K-Distribution Sea Clutter Environments

In K-distribution sea clutter environments, maintaining a constant false alarm rate (CFAR) is essential due to the unpredictable and dynamic nature of the background. However, CFAR detectors often face reduced performance in scenarios with multiple targets due to a masking effect. To combat this issue, a technique known as "Space-Based Linear Density Clustering for Applications with Noise" (Lin-DBSCAN) is employed alongside CFAR. Lin-DBSCAN is adept at pinpointing both interference targets and sea spikes, typically appearing as outliers, in the designated areas before and after the cell under test (CUT). By integrating Lin-DBSCAN, these irregular signals are efficiently identified and segregated from the general sea clutter, significantly improving target detection accuracy. Extensive simulations under various conditions—varying false alarm rates, target numbers, and shape parameters—have shown that Lin-DBSCAN-CFAR outperforms traditional CFAR methods. Additionally, it reduces computational complexity compared to its counterpart, DBSCAN-CFAR. These enhancements significantly boost the practicality and efficiency of CFAR detection in K-distribution sea clutter scenarios, offering a robust solution to the challenges posed by multiple target environments. Special Issue of AEIC 2024 (Electrical and System & Computer Engineering Session)