LCB-CV-UNet: Enhanced Detector for High Dynamic Range Radar Signals

2025-05-29

AI Summary

To address degraded weak-target detection performance caused by high dynamic range (HDR) radar signals, this paper proposes a hardware-friendly, plug-and-play Logarithmic Connection Block (LCB) and a dual-hybrid dataset construction strategy. The LCB uniquely preserves phase coherence while effectively suppressing dynamic distortion induced by HDR. The proposed semi-synthetic HDR data generation paradigm enables controllable target distribution, thereby enhancing model generalization under low signal-to-noise ratio (SNR) conditions. Integrated into the CV-UNet architecture, the method achieves engineering-feasible performance gains with minimal computational overhead: overall detection probability improves by approximately 1%, while computational complexity increases by only 0.9%. Notably, detection performance rises by 5% within the critical 11–13 dB SNR range. Both simulation and real-world measurements consistently validate the efficacy of the approach.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

We propose the LCB-CV-UNet to tackle performance degradation caused by High Dynamic Range (HDR) radar signals. Initially, a hardware-efficient, plug-and-play module named Logarithmic Connect Block (LCB) is proposed as a phase coherence preserving solution to address the inherent challenges in handling HDR features. Then, we propose the Dual Hybrid Dataset Construction method to generate a semi-synthetic dataset, approximating typical HDR signal scenarios with adjustable target distributions. Simulation results show about 1% total detection probability improvement with under 0.9% computational complexity added compared with the baseline. Furthermore, it excels 5% over the baseline at the range in 11-13 dB signal-to-noise ratio typical for urban targets. Finally, the real experiment validates the practicality of our model.

Problem

• Improves detection of High Dynamic Range radar signals
• Addresses performance degradation in HDR signal processing
• Enhances detection probability with low computational overhead

Innovation

• Logarithmic Connect Block preserves phase coherence
• Dual Hybrid Dataset Construction for HDR scenarios
• Improved detection with minimal computational overhead