SAR image target recognition based on GBMLWM algorithm and Bayesian neural networks

2016 ◽  
Author(s):  
Lei Wang ◽  
Yingjun Li ◽  
Kai Song
Keyword(s):  
Neural Networks ◽  
Target Recognition ◽  
Sar Image ◽  
Bayesian Neural Networks

scholarly journals CNN-LRP: Understanding Convolutional Neural Networks Performance for Target Recognition in SAR Images

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4536
Author(s):  
Bo Zang ◽  
Linlin Ding ◽  
Zhenpeng Feng ◽  
Mingzhe Zhu ◽  
Tao Lei ◽  
...  
Keyword(s):  
Neural Networks ◽  
Target Recognition ◽  
Sar Image ◽  
Sar Images ◽  
Recognition Mechanism ◽  
Rearrangement Algorithm ◽  
Causes Of Errors ◽  
Visual Understanding ◽  
Processing Techniques ◽  
Fully Connected

Target recognition is one of the most challenging tasks in synthetic aperture radar (SAR) image processing since it is highly affected by a series of pre-processing techniques which usually require sophisticated manipulation for different data and consume huge calculation resources. To alleviate this limitation, numerous deep-learning based target recognition methods are proposed, particularly combined with convolutional neural network (CNN) due to its strong capability of data abstraction and end-to-end structure. In this case, although complex pre-processing can be avoided, the inner mechanism of CNN is still unclear. Such a “black box” only tells a result but not what CNN learned from the input data, thus it is difficult for researchers to further analyze the causes of errors. Layer-wise relevance propagation (LRP) is a prevalent pixel-level rearrangement algorithm to visualize neural networks’ inner mechanism. LRP is usually applied in sparse auto-encoder with only fully-connected layers rather than CNN, but such network structure usually obtains much lower recognition accuracy than CNN. In this paper, we propose a novel LRP algorithm particularly designed for understanding CNN’s performance on SAR image target recognition. We provide a concise form of the correlation between output of a layer and weights of the next layer in CNNs. The proposed method can provide positive and negative contributions in input SAR images for CNN’s classification, viewed as a clear visual understanding of CNN’s recognition mechanism. Numerous experimental results demonstrate the proposed method outperforms common LRP.

Hierarchical fusion convolutional neural networks for SAR image segmentation

2021 ◽  
Vol 147 ◽  
pp. 115-123
Author(s):  
Yinyin Jiang ◽  
Ming Li ◽  
Peng Zhang ◽  
Xiaofeng Tan ◽  
Wanying Song
Keyword(s):  
Neural Networks ◽  
Image Segmentation ◽  
Convolutional Neural Networks ◽  
Sar Image ◽  
Sar Image Segmentation

SAR Image Target Recognition Based on Improved Residual Attention Network

2021 ◽  
Vol 58 (8) ◽  
pp. 0810008
Author(s):  
史宝岱 Shi Baodai ◽  
张秦 Zhang Qin ◽  
李瑶 Li Yao ◽  
李宇环 Li Yuhuan
Keyword(s):  
Target Recognition ◽  
Sar Image ◽  
Attention Network
Sign in / Sign up

Export Citation Format

Share Document