In this paper, a method of Synthetic Aperture Radar (SAR) image Automatic Target Recognition (ATR) based on Convolution Auto-encode (CAE) and Support Vector Machine (SVM) is proposed. Using SVM replaces the traditional softmax as the classifier of the CAE model to classify the feature vectors extracted by the CAE model, which solves the problem that the softmax classifier is less effective in the nonlinear case. Since the SVM can only solve the binary classification problem, and in order to realize the classification of the class objectives, the SVM were designed to achieve the classification of the input samples. After unsupervised training for CAE, the coding layer is connected with SVM to form a classification network. CAE can extract the features of the data by an unsupervised method, and the nonlinear classification advantage of SVM can classify the features extracted by CAE and improve the accuracy of the object recognition. At the same time, the high-accuracy identification of key targets is required in some special cases. A new initialization method is proposed, which initializes the network parameters by pretraining the key targets and changes the weights of different targets in the loss function to obtain better feature extraction, so it can ensure good multitarget recognition ability while realizing the high recognition accuracy of the key targets.
Objective. The steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) has received extensive attention in research due to its simple system, less training data, and high information transfer rate (ITR). There are currently two prominent methods dominating the classification of SSVEP signals. One is the knowledge-based task-related component analysis (TRCA) method, whose core idea is to find the spatial filters by maximizing the inter-trial covariance. The other is the deep learning-based approach, which directly learns a classification model from data. However, how to integrate the two methods to achieve better performance has not been studied before. Approach. In this study, we develop a novel algorithm named Task Related Component Analysis-Net (TRCANet) to enhance SSVEP signal classification, which enjoys the advantages of both the knowledge-based method and the deep model. Specifically, the proposed TRCA-Net first performs TRCA to obtain spatial filters, which extract task-related components of data. Then the TRCA-filtered features from different filters are rearranged as new multi-channel signals for a deep convolutional neural network for classification. Introducing the TRCA filters to a deep learning-based approach improves the signal-to-noise ratio (SNR) of input data, hence benefiting the deep learning model. Main results. We evaluate the performance of TRCA-Net using two publicly available large-scale benchmark datasets, and the results demonstrate the effectiveness of TRCA-Net. Additionally,
offline and online experiments separately testing ten and five subjects further validate the robustness of TRCA-Net. Further,
we conduct ablation studies on different convolutional neural network (CNN) backbones and demonstrate that our approach
can be transplanted into other CNN models to boost their performance. Significance. The proposed approach is believed to
have a promising potential for SSVEP classification and promote its practical applications in communication and control.
Airborne VHR SAR image registration is a challenging task. The number of CPs is a key factor for complex CP-based image registration. This paper presents a two-step matching approach to obtain more CPs for VHR SAR image registration. In the past decade, SIFT and other modifications have been widely used for remote sensing image registration. By incorporating feature point location affine transformation, a two-step matching scheme, which includes global and local matching, is proposed to allow for the determination of a much larger number of CPs. The proposed approach was validated by 0.5 m resolution C-band airborne SAR data acquired in Sichuan after the 2008 Wenchuan earthquake via a SAR system designed by the IECAS. With the proposed matching scheme, even the original SIFT, which is widely known to be unsuitable for SAR images, can achieve a much larger number of high-quality CPs than the one-step SIFT–OCT, which is tailored for SAR images. Compared with the classic one-step matching approach using both the SIFT and SITF–OCT algorithms, the proposed approach can obtain a larger number of CPs with improved precision.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.