Electronics Optics & Control, Volume. 27, Issue 8, 19(2020)
High-Resolution Range Profile Recognition Based on Improved One-Dimensional Convolutional Neural Network
To improve the performance of wideband radar in High-Resolution Range Profile (HRRP) target recognition,an improved One-Dimensional Convolutional Neural Network (1D-CNN) model is proposed.In view of the inadequate samples and low Signal-to-Noise Ratio (SNR) of the target,global average pooling is employed to regularize the whole network model and prevent over-fitting.In view of the similar shape and size of real and fake targets,the recognition performance of targets with different shapes and sizes is analyzed.The experimental results show that the proposed model can realize the recognition of target categories and sizes effectively under the condition of limited training samples and noise interference.The proposed model is helpful for automatic target recognition based on radar high-resolution range profile in the case of similar shape and size of real and fake targets,inadequate samples and low SNR.
Get Citation
Copy Citation Text
LU Jinwen, YIN Hongcheng, SHENG Jing, YUAN Li, DONG Chunzhu. High-Resolution Range Profile Recognition Based on Improved One-Dimensional Convolutional Neural Network[J]. Electronics Optics & Control, 2020, 27(8): 19
Category:
Received: Jul. 26, 2019
Accepted: --
Published Online: Dec. 25, 2020
The Author Email: