1
|
Yang W, Zhou Q, Yuan M, Li Y, Wang Y, Zhang L. Dual-band polarimetric HRRP recognition via a brain-inspired multi-channel fusion feature extraction network. Front Neurosci 2023; 17:1252179. [PMID: 37674513 PMCID: PMC10477359 DOI: 10.3389/fnins.2023.1252179] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2023] [Accepted: 07/27/2023] [Indexed: 09/08/2023] Open
Abstract
Radar high-resolution range profile (HRRP) provides geometric and structural information of target, which is important for radar automatic target recognition (RATR). However, due to the limited information dimension of HRRP, achieving accurate target recognition is challenging in applications. In recent years, with the rapid development of radar components and signal processing technology, the acquisition and use of target multi-frequency and polarization scattering information has become a significant way to improve target recognition performance. Meanwhile, deep learning inspired by the human brain has shown great promise in pattern recognition applications. In this paper, a Multi-channel Fusion Feature Extraction Network (MFFE-Net) inspired by the human brain is proposed for dual-band polarimetric HRRP, aiming at addressing the challenges faced in HRRP target recognition. In the proposed network, inspired by the human brain's multi-dimensional information interaction, the similarity and difference features of dual-frequency HRRP are first extracted to realize the interactive fusion of frequency features. Then, inspired by the human brain's selective attention mechanism, the interactive weights are obtained for multi-polarization features and multi-scale representation, enabling feature aggregation and multi-scale fusion. Finally, inspired by the human brain's hierarchical learning mechanism, the layer-by-layer feature extraction and fusion with residual connections are designed to enhance the separability of features. Experiments on simulated and measured datasets verify the accurate recognition capability of MFFE-Net, and ablative studies are conducted to confirm the effectiveness of components of network for recognition.
Collapse
Affiliation(s)
- Wei Yang
- Radar Research Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
- Electromagnetic Sensing Research Center of CEMEE State Key Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
| | - Qiang Zhou
- Radar Research Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
- Electromagnetic Sensing Research Center of CEMEE State Key Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
| | - Mingchen Yuan
- Radar Research Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
- Electromagnetic Sensing Research Center of CEMEE State Key Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
| | - Yang Li
- Radar Research Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
- Electromagnetic Sensing Research Center of CEMEE State Key Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
- Chongqing Innovation Center, Beijing Institute of Technology, Chongqing, China
- Beijing Key Laboratory of Embedded Real-time Information Processing Technology, Beijing, China
| | - Yanhua Wang
- Radar Research Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
- Electromagnetic Sensing Research Center of CEMEE State Key Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
- Chongqing Innovation Center, Beijing Institute of Technology, Chongqing, China
- Beijing Key Laboratory of Embedded Real-time Information Processing Technology, Beijing, China
- Advanced Technology Research Institute, Beijing Institute of Technology, Jinan, Shandong, China
| | - Liang Zhang
- Radar Research Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
- Electromagnetic Sensing Research Center of CEMEE State Key Laboratory, School of Information and Electronics, Beijing Institute of Technology, Beijing, China
| |
Collapse
|
2
|
Two-Stream Deep Fusion Network Based on VAE and CNN for Synthetic Aperture Radar Target Recognition. REMOTE SENSING 2021. [DOI: 10.3390/rs13204021] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Usually radar target recognition methods only use a single type of high-resolution radar signal, e.g., high-resolution range profile (HRRP) or synthetic aperture radar (SAR) images. In fact, in the SAR imaging procedure, we can simultaneously obtain both the HRRP data and the corresponding SAR image, as the information contained within them is not exactly the same. Although the information contained in the HRRP data and the SAR image are not exactly the same, both are important for radar target recognition. Therefore, in this paper, we propose a novel end-to-end two stream fusion network to make full use of the different characteristics obtained from modeling HRRP data and SAR images, respectively, for SAR target recognition. The proposed fusion network contains two separated streams in the feature extraction stage, one of which takes advantage of a variational auto-encoder (VAE) network to acquire the latent probabilistic distribution characteristic from the HRRP data, and the other uses a lightweight convolutional neural network, LightNet, to extract the 2D visual structure characteristics based on SAR images. Following the feature extraction stage, a fusion module is utilized to integrate the latent probabilistic distribution characteristic and the structure characteristic for the reflecting target information more comprehensively and sufficiently. The main contribution of the proposed method consists of two parts: (1) different characteristics from the HRRP data and the SAR image can be used effectively for SAR target recognition, and (2) an attention weight vector is used in the fusion module to adaptively integrate the different characteristics from the two sub-networks. The experimental results of our method on the HRRP data and SAR images of the MSTAR and civilian vehicle datasets obtained improvements of at least 0.96 and 2.16%, respectively, on recognition rates, compared with current SAR target recognition methods.
Collapse
|
3
|
Jasinski T, Brooker G, Antipov I. W-Band Multi-Aspect High Resolution Range Profile Radar Target Classification Using Support Vector Machines. SENSORS 2021; 21:s21072385. [PMID: 33808183 PMCID: PMC8037360 DOI: 10.3390/s21072385] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/19/2021] [Revised: 03/22/2021] [Accepted: 03/24/2021] [Indexed: 11/16/2022]
Abstract
Millimeter-wave (W-band) radar measurements were taken for two maritime targets instrumented with attitude and heading reference systems (AHRSs) in a littoral environment with the aim of developing a multiaspect classifier. The focus was on resource-limited implementations such as short-range, tactical, unmanned aircraft systems (UASs) and dealing with limited and imbalanced datasets. Radar imaging and preprocessing consisted of recording high-resolution range profiles (HRRPs) and performing range alignment using peak detection and fast Fourier transforms (FFTs). HRRPs were used because of their simplicity, reliability, and speed. The features used were fixed-length, frequency domain range profiles. Two linear support vector machine (SVM)-based classifiers were developed which both yielded excellent results in their general forms and were simple to implement. The first approach utilized the positive predictive value (PPV) and negative predictive value (NPV) statistics of the SVM directly to generate target probabilities and consequently determine the optimal aspect transitions for classification. The second approach used the Kolmogorov-Smirnov test for dimensionality reduction, followed by concatenating feature vectors across several aspects. The latter approach is particularly well-suited to resource-constrained scenarios, potentially allowing for retraining and updating in the field.
Collapse
Affiliation(s)
- Tomasz Jasinski
- Cyber and Electronic Warfare Division, Defence Science and Technology Group, Edinburgh, SA 5111, Australia;
- Correspondence:
| | - Graham Brooker
- Australian Centre for Field Robotics, University of Sydney, Camperdown, NSW 2006, Australia;
| | - Irina Antipov
- Cyber and Electronic Warfare Division, Defence Science and Technology Group, Edinburgh, SA 5111, Australia;
| |
Collapse
|
4
|
Xiang Q, Wang X, Song Y, Lei L, Li R, Lai J. One‐dimensional convolutional neural networks for high‐resolution range profile recognition via adaptively feature recalibrating and automatically channel pruning. INT J INTELL SYST 2021. [DOI: 10.1002/int.22302] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Affiliation(s)
- Qian Xiang
- College of Air and Missile Defense Air Force Engineering University Xi'an China
| | - Xiaodan Wang
- College of Air and Missile Defense Air Force Engineering University Xi'an China
| | - Yafei Song
- College of Air and Missile Defense Air Force Engineering University Xi'an China
| | - Lei Lei
- College of Information and Navigation Air Force Engineering University Xi'an China
| | - Rui Li
- College of Air and Missile Defense Air Force Engineering University Xi'an China
| | - Jie Lai
- College of Air and Missile Defense Air Force Engineering University Xi'an China
| |
Collapse
|
5
|
One-dimension hierarchical local receptive fields based extreme learning machine for radar target HRRP recognition. Neurocomputing 2020. [DOI: 10.1016/j.neucom.2020.08.050] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
|
6
|
Multi-parallel Extreme Learning Machine with Excitatory and Inhibitory Neurons for Regression. Neural Process Lett 2019. [DOI: 10.1007/s11063-019-10160-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
7
|
Signal Processing and Target Fusion Detection via Dual Platform Radar Cooperative Illumination. SENSORS 2019; 19:s19245341. [PMID: 31817145 PMCID: PMC6960944 DOI: 10.3390/s19245341] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/08/2019] [Revised: 11/28/2019] [Accepted: 12/03/2019] [Indexed: 11/30/2022]
Abstract
A modified signal processing and target fusion detection method based on the dual platform cooperative detection model is proposed in this paper. In this model, a single transmitter and dual receiver radar system is adopted, which can form a single radar and bistatic radar system, respectively. Clutter suppression is achieved by an adaptive moving target indicator (AMTI). By combining the AMTI technology and the traditional radar signal processing technology (i.e., pulse compression and coherent accumulation processing), the SNR is improved, and false targets generated by direct wave are suppressed. The decision matrix is obtained by cell averaging constant false alarm (CA-CFAR) and order statistics constant false alarm (OS-CFAR) processing. Then, the echo signals processed in the two receivers are fused by the AND-like fusion rule and OR-like fusion rule, and the detection probability after fusion detection in different cases is analyzed. Finally, the performance of the proposed method is quantitatively analyzed. Experimental results based on simulated data demonstrate that: (1) The bistatic radar system with a split transceiver has a larger detection distance than the single radar system, but the influence of clutter is greater; (2) the direct wave can be eliminated effectively, and no false target can be formed after suppression; (3) the detection probability of the bistatic radar system with split transceivers is higher than that of the single radar system; and (4) the detection probability of signal fusion detection based on two receivers is higher than that of the bistatic radar system and single radar system.
Collapse
|
8
|
Wu H, Dai D, Wang X. A Novel Radar HRRP Recognition Method with Accelerated T-Distributed Stochastic Neighbor Embedding and Density-Based Clustering. SENSORS 2019; 19:s19235112. [PMID: 31766679 PMCID: PMC6928858 DOI: 10.3390/s19235112] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/21/2019] [Revised: 11/09/2019] [Accepted: 11/20/2019] [Indexed: 11/22/2022]
Abstract
High-resolution range profile (HRRP) has attracted intensive attention from radar community because it is easy to acquire and analyze. However, most of the conventional algorithms require the prior information of targets, and they cannot process a large number of samples in real time. In this paper, a novel HRRP recognition method is proposed to classify unlabeled samples automatically where the number of categories is unknown. Firstly, with the preprocessing of HRRPs, we adopt principal component analysis (PCA) for dimensionality reduction of data. Afterwards, t-distributed stochastic neighbor embedding (t-SNE) with Barnes–Hut approximation is conducted for the visualization of high-dimensional data. It proves to reduce the dimensionality, which has significantly improved the computation speed. Finally, it is exhibited that the recognition performance with density-based clustering is superior to conventional algorithms under the condition of large azimuth angle ranges and low signal-to-noise ratio (SNR).
Collapse
Affiliation(s)
- Hao Wu
- Correspondence: ; Tel.: +86-155-8162-8873
| | | | | |
Collapse
|
9
|
Aircraft Target Classification for Conventional Narrow-Band Radar with Multi-Wave Gates Sparse Echo Data. REMOTE SENSING 2019. [DOI: 10.3390/rs11222700] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
For a conventional narrow-band radar system, the detectable information of the target is limited, and it is difficult for the radar to accurately identify the target type. In particular, the classification probability will further decrease when part of the echo data is missed. By extracting the target features in time and frequency domains from multi-wave gates sparse echo data, this paper presents a classification algorithm in conventional narrow-band radar to identify three different types of aircraft target, i.e., helicopter, propeller and jet. Firstly, the classical sparse reconstruction algorithm is utilized to reconstruct the target frequency spectrum with single-wave gate sparse echo data. Then, the micro-Doppler effect caused by rotating parts of different targets is analyzed, and the micro-Doppler based features, such as amplitude deviation coefficient, time domain waveform entropy and frequency domain waveform entropy, are extracted from reconstructed echo data to identify targets. Thirdly, the target features extracted from multi-wave gates reconstructed echo data are weighted and fused to improve the accuracy of classification. Finally, the fused feature vectors are fed into a support vector machine (SVM) model for classification. By contrast with the conventional algorithm of aircraft target classification, the proposed algorithm can effectively process sparse echo data and achieve higher classification probability via weighted features fusion of multi-wave gates echo data. The experiments on synthetic data are carried out to validate the effectiveness of the proposed algorithm.
Collapse
|
10
|
Yu H, Ding M, Zhang X. Laplacian Eigenmaps Network-Based Nonlocal Means Method for MR Image Denoising. SENSORS (BASEL, SWITZERLAND) 2019; 19:E2918. [PMID: 31266234 PMCID: PMC6650831 DOI: 10.3390/s19132918] [Citation(s) in RCA: 17] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/30/2019] [Revised: 06/22/2019] [Accepted: 06/25/2019] [Indexed: 11/16/2022]
Abstract
Magnetic resonance (MR) images are often corrupted by Rician noise which degrades the accuracy of image-based diagnosis tasks. The nonlocal means (NLM) method is a representative filter in denoising MR images due to its competitive denoising performance. However, the existing NLM methods usually exploit the gray-level information or hand-crafted features to evaluate the similarity between image patches, which is disadvantageous for preserving the image details while smoothing out noise. In this paper, an improved nonlocal means method is proposed for removing Rician noise in MR images by using the refined similarity measures. The proposed method firstly extracts the intrinsic features from the pre-denoised image using a shallow convolutional neural network named Laplacian eigenmaps network (LEPNet). Then, the extracted features are used for computing the similarity in the NLM method to produce the denoised image. Finally, the method noise of the denoised image is utilized to further improve the denoising performance. Specifically, the LEPNet model is composed of two cascaded convolutional layers and a nonlinear output layer, in which the Laplacian eigenmaps are employed to learn the filter bank in the convolutional layers and the Leaky Rectified Linear Unit activation function is used in the final output layer to output the nonlinear features. Due to the advantage of LEPNet in recovering the geometric structure of the manifold in the low-dimension space, the features extracted by this network can facilitate characterizing the self-similarity better than the existing NLM methods. Experiments have been performed on the BrainWeb phantom and the real images. Experimental results demonstrate that among several compared denoising methods, the proposed method can provide more effective noise removal and better details preservation in terms of human vision and such objective indexes as peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM).
Collapse
Affiliation(s)
- Houqiang Yu
- Department of Biomedical Engineering, School of Life Science and Technology, Ministry of Education Key Laboratory of Molecular Biophysics, Huazhong University of Science and Technology, No 1037, Luoyu Road, Wuhan 430074, China
- Department of Mathematics and Statistics, Hubei University of Science and Technology, No 88, Xianning Road, Xianning 437000, China
| | - Mingyue Ding
- Department of Biomedical Engineering, School of Life Science and Technology, Ministry of Education Key Laboratory of Molecular Biophysics, Huazhong University of Science and Technology, No 1037, Luoyu Road, Wuhan 430074, China
| | - Xuming Zhang
- Department of Biomedical Engineering, School of Life Science and Technology, Ministry of Education Key Laboratory of Molecular Biophysics, Huazhong University of Science and Technology, No 1037, Luoyu Road, Wuhan 430074, China.
| |
Collapse
|
11
|
A Novel Multi-Input Bidirectional LSTM and HMM Based Approach for Target Recognition from Multi-Domain Radar Range Profiles. ELECTRONICS 2019. [DOI: 10.3390/electronics8050535] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Radars, as active detection sensors, are known to play an important role in various intelligent devices. Target recognition based on high-resolution range profile (HRRP) is an important approach for radars to monitor interesting targets. Traditional recognition algorithms usually rely on a single feature, which makes it difficult to maintain the recognition performance. In this paper, 2-D sequence features from HRRP are extracted in various data domains such as time-frequency domain, time domain, and frequency domain. A novel target identification method is then proposed, by combining bidirectional Long Short-Term Memory (BLSTM) and a Hidden Markov Model (HMM), to learn these multi-domain sequence features. Specifically, we first extract multi-domain HRRP sequences. Next, a new multi-input BLSTM is proposed to learn these multi-domain HRRP sequences, which are then fed to a standard HMM classifier to learn multi-aspect features. Finally, the trained HMM is used to implement the recognition task. Extensive experiments are carried out on the publicly accessible, benchmark MSTAR database. Our proposed algorithm is shown to achieve an identification accuracy of over 91% with a lower false alarm rate and higher identification confidence, compared to several state-of-the-art techniques.
Collapse
|
12
|
Lu W, Zhang Y, Xu C, Lin C, Huo Y. A Deep Learning-Based Satellite Target Recognition Method Using Radar Data. SENSORS (BASEL, SWITZERLAND) 2019; 19:s19092008. [PMID: 31035670 PMCID: PMC6540144 DOI: 10.3390/s19092008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/27/2019] [Revised: 04/18/2019] [Accepted: 04/25/2019] [Indexed: 06/09/2023]
Abstract
A novel satellite target recognition method based on radar data partition and deep learning techniques is proposed in this paper. For the radar satellite recognition task, orbital altitude is introduced as a distinct and accessible feature to divide radar data. On this basis, we design a new distance metric for HRRPs called normalized angular distance divided by correlation coefficient (NADDCC), and a hierarchical clustering method based on this distance metric is applied to segment the radar observation angular domain. Using the above technology, the radar data partition is completed and multiple HRRP data clusters are obtained. To further mine the essential features in HRRPs, a GRU-SVM model is designed and firstly applied for radar HRRP target recognition. It consists of a multi-layer GRU neural network as a deep feature extractor and linear SVM as a classifier. By training, GRU neural network successfully extracts effective and highly distinguishable features of HRRPs, and feature visualization technology shows its advantages. Furthermore, the performance testing and comparison experiments also demonstrate that GRU neural network possesses better comprehensive performance for HRRP target recognition than LSTM neural network and conventional RNN, and the recognition performance of our method is almost better than that of other several common feature extraction methods or no data partition.
Collapse
Affiliation(s)
- Wang Lu
- Graduate School, Space Engineering University, Beijing 101416, China.
| | - Yasheng Zhang
- Space Engineering University, Beijing 101416, China.
| | - Can Xu
- Space Engineering University, Beijing 101416, China.
| | - Caiyong Lin
- Space Engineering University, Beijing 101416, China.
| | - Yurong Huo
- Graduate School, Space Engineering University, Beijing 101416, China.
| |
Collapse
|
13
|
A New Radar Signal Recognition Method Based on Optimal Classification Atom and IDCQGA. Symmetry (Basel) 2018. [DOI: 10.3390/sym10110659] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
Radar electronic reconnaissance is an important part of modern and future electronic warfare systems and is the primary method to obtain non-cooperative intelligence information. As the task requirement of radar electronic reconnaissance, it is necessary to identify the non-cooperative signals from the mixed signals. However, with the complexity of battlefield electromagnetic environment, the performance of traditional recognition system is seriously affected. In this paper, a new recognition method based on optimal classification atom and improved double chains quantum genetic algorithm (IDCQGA) is researched, optimal classification atom is a new feature for radar signal recognition, IDCQGA with symmetric coding performance can be applied to the global optimization algorithm. The main contributions of this paper are as follows: Firstly, in order to measure the difference of multi-class signals, signal separation degree based on distance criterion is proposed and established according to the inter-class separability and intra-class aggregation of the signals. Then, an IDCQGA is proposed to select the best atom for classification under the constraint of distance criterion, and the inner product of the signal and the best atom for classification is taken as the eigenvector. Finally, the extreme learning machine (ELM) is introduced as classifier to complete the recognition of signals. Simulation results show that the proposed method can improve the recognition rate of multi-class signals and has better processing ability for overlapping eigenvector parameters.
Collapse
|
14
|
Enhancing the Visibility of Delamination during Pulsed Thermography of Carbon Fiber-Reinforced Plates Using a Stacked Autoencoder. SENSORS 2018; 18:s18092809. [PMID: 30149654 PMCID: PMC6164668 DOI: 10.3390/s18092809] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/21/2018] [Revised: 08/19/2018] [Accepted: 08/22/2018] [Indexed: 11/17/2022]
Abstract
The effectiveness of pulsed thermography (PT) for detecting delamination in carbon fiber-reinforced polymer (CFRP) plates has been widely verified. However, delaminations are usually characterized by weak visibility due to the influences of inspection factors and the delaminations with weak visibility are easily missed in real inspections. In this study, by introducing a deep learning algorithm—stacked autoencoder (SAE)—to PT, we propose a novel approach (SAE-PT) to enhance the visibility of delaminations. Based on the ability of SAE to learn unsupervised features from data, the thermal features of delaminations are extracted from the raw thermograms. The extracted features are then employed to construct SAE images, in which the visibility of delaminations is expected to be enhanced. To test the performance of SAE-PT, we inspected CFRP plates with prefabricated delaminations. By implementing SAE-PT on the raw inspection data, the delaminations were more clearly indicated in the constructed SAE images. We also compare SAE-PT to the widely used principal component thermography (PCT) method to further verify the validity of the proposed approach. The results reveal that compared to PCT, SAE-PT can show delaminations in CFRP with higher contrast. By effectively enhancing the delamination visibility, SAE-PT thus has potential for improving the inspection accuracy of PT for non-destructive testing (NDT) of CFRP.
Collapse
|
15
|
Attention-Based Recurrent Temporal Restricted Boltzmann Machine for Radar High Resolution Range Profile Sequence Recognition. SENSORS 2018; 18:s18051585. [PMID: 29772725 PMCID: PMC5982540 DOI: 10.3390/s18051585] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/30/2018] [Revised: 05/13/2018] [Accepted: 05/14/2018] [Indexed: 11/22/2022]
Abstract
The High Resolution Range Profile (HRRP) recognition has attracted great concern in the field of Radar Automatic Target Recognition (RATR). However, traditional HRRP recognition methods failed to model high dimensional sequential data efficiently and have a poor anti-noise ability. To deal with these problems, a novel stochastic neural network model named Attention-based Recurrent Temporal Restricted Boltzmann Machine (ARTRBM) is proposed in this paper. RTRBM is utilized to extract discriminative features and the attention mechanism is adopted to select major features. RTRBM is efficient to model high dimensional HRRP sequences because it can extract the information of temporal and spatial correlation between adjacent HRRPs. The attention mechanism is used in sequential data recognition tasks including machine translation and relation classification, which makes the model pay more attention to the major features of recognition. Therefore, the combination of RTRBM and the attention mechanism makes our model effective for extracting more internal related features and choose the important parts of the extracted features. Additionally, the model performs well with the noise corrupted HRRP data. Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that our proposed model outperforms other traditional methods, which indicates that ARTRBM extracts, selects, and utilizes the correlation information between adjacent HRRPs effectively and is suitable for high dimensional data or noise corrupted data.
Collapse
|
16
|
Gallego AJ, Gil P, Pertusa A, Fisher RB. Segmentation of Oil Spills on Side-Looking Airborne Radar Imagery with Autoencoders. SENSORS 2018; 18:s18030797. [PMID: 29509720 PMCID: PMC5876930 DOI: 10.3390/s18030797] [Citation(s) in RCA: 22] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/08/2018] [Revised: 02/27/2018] [Accepted: 03/04/2018] [Indexed: 11/16/2022]
Abstract
In this work, we use deep neural autoencoders to segment oil spills from Side-Looking Airborne Radar (SLAR) imagery. Synthetic Aperture Radar (SAR) has been much exploited for ocean surface monitoring, especially for oil pollution detection, but few approaches in the literature use SLAR. Our sensor consists of two SAR antennas mounted on an aircraft, enabling a quicker response than satellite sensors for emergency services when an oil spill occurs. Experiments on TERMA radar were carried out to detect oil spills on Spanish coasts using deep selectional autoencoders and RED-nets (very deep Residual Encoder-Decoder Networks). Different configurations of these networks were evaluated and the best topology significantly outperformed previous approaches, correctly detecting 100% of the spills and obtaining an F1 score of 93.01% at the pixel level. The proposed autoencoders perform accurately in SLAR imagery that has artifacts and noise caused by the aircraft maneuvers, in different weather conditions and with the presence of look-alikes due to natural phenomena such as shoals of fish and seaweed.
Collapse
Affiliation(s)
- Antonio-Javier Gallego
- Pattern Recognition and Artificial Intelligence Group, Department of Software and Computing Systems, University of Alicante, E-03690 Alicante, Spain.
- Computer Science Research Institute, University of Alicante, E-03690 Alicante, Spain.
| | - Pablo Gil
- Automation, Robotics and Computer Vision Group, Department of Physics, Systems Engineering and Signal Theory, University of Alicante, E-03690 Alicante, Spain.
- Computer Science Research Institute, University of Alicante, E-03690 Alicante, Spain.
| | - Antonio Pertusa
- Pattern Recognition and Artificial Intelligence Group, Department of Software and Computing Systems, University of Alicante, E-03690 Alicante, Spain.
- Computer Science Research Institute, University of Alicante, E-03690 Alicante, Spain.
| | - Robert B Fisher
- School of Informatics, University of Edinburgh, EH1 2QL Edinburgh, UK.
| |
Collapse
|