DEEP LEARNING MITIGATION OF SEA CLUTTER FOR ENHANCED RADAR TARGET DETECTION | ||||
| Journal of Al-Azhar University Engineering Sector | ||||
| Volume 19, Issue 72, July 2024, Page 289-302 PDF (681.41 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/auej.2024.259023.1575 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
Mansoor M Al-dabaa  1; Ahmed A. Emran1; Ahmed Yahya 1; Ashraf Aboshosha2
| ||||
| 1Electrical Engineering Department, Faculty of Engineering, Al-Azhar University, Nasr City, 11884, Cairo, Egypt | ||||
| 2Rad. Eng. Dept, NCRRT, Egyptian Atomic Energy Authority, EAEA, Cairo | ||||
| Abstract | ||||
| This research provides a detailed examination of how deep learning significantly improves radar accuracy. By integrating advanced simulations with real-world tests, the study demonstrates how deep learning enhances the removal of sea clutter, substantially improving target detection in Constant False Alarm Rate (CFAR) algorithms. The results clearly show that deep learning is not just advantageous but critical for advancing radar performance, ensuring a new level of precision and reliability in maritime identification and tracking. The paper highlights deep learning as an essential tool for dealing with the complexities of sea clutter in radar systems. It goes beyond simple improvements, redefining accuracy in target detection and affirming the strength and reliability of radar operations in the chaotic maritime environment. The comprehensive methodology and solid empirical evidence presented emphasize the revolutionary impact of deep learning, marking the beginning of a new chapter in radar technology characterized by unmatched precision, adaptability, and reliability. Special Issue of AEIC 2024 (Electrical and System & Computer Engineering Session) | ||||
| Keywords | ||||
| Convolutional Neural Network; constant false alarm rate; cell under test; clustering algorithm | ||||
|
Statistics Article View: 285 PDF Download: 321 |
||||
