.png){kind=icon}
.png){kind=icon}
Return
Radar High-Resolution Range Profile Target Recognition Method Based on Structure-Aware Network
.png){kind=icon}
PRE
AI
DOI：10.1109/JSEN.2024.3449571.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
High-resolution range profile (HRRP) recognition plays a crucial role in radar automatic target recognition (RATR). It contains a lot of structural features of the target. Thus, it is important to capture and distinguish the features of HRRP. This article proposes a novel radar HRRP target recognition model based on a structure-aware network. The proposed model consists of three parts: a shallow feature extractor, a deep feature extractor, and a classification module. The core innovation lies in the structure-aware module integrated into the deep feature extraction process, enabling the model to capture long-range dependencies within HRRP data and effectively extract structural information of the targets. Our structure-aware module addresses two critical aspects often overlooked by other methods: 1) the relationships across long-range cells in HRRP data and 2) the varying impacts of different features on recognition. By incorporating these considerations, the module enhances the feature selection process and significantly contributes to the model's superior performance. Extensive experimental results on real measured data demonstrate the superior performance of our model compared to reference methods, particularly in scenarios with limited samples.
Keywords:
Feature extraction
Target recognition
Sensors
Data mining
Sensitivity
Data models
Scattering
high-resolution range profile (HRRP)
radar automatic target recognition (RATR)
structure-aware