Shuai Xu

In low-altitude unmanned aerial vehicle (UAV) detection scenarios, the initial segment of radar linear frequency modulation (LFM) signals is often corrupted due to building occlusions and noise interference, making accurate range estimation difficult. To address this issue, we propose a deep learning-based framework named Deep Time-Frequency Inverse Reconstruction Network (DTFIRNet) for radar echo signal restoration and precise ranging.

TANG FENG: IMAGE PROCESSING AND COMPUTER VISION.

Existing work on radar modulation recognition is

widely based on the assumption of a single in-pulse signal,

whereas overlapping two pulse signals is an actual situation. This

paper introduces a challenging problem: modulation recognition

of overlapping intra-pulse signals, where the difficulty lies in

the fact that the number of samples grows stepwise with the

permutation of the sub-signals. In this paper, for the first time,

a series of methods for target detection are used to solve this