“…For other narrowband radar target characteristics such as echo characteristics, the application of deep learning for RATR is relatively rare. Inspired by the huge success of deep learning techniques in the field of SAR-ATR and computer vision, Fan et al [146] designed a five-layer CNN for typical cube, tetrahedron, and triangular prism recognition utilizing raw radar signals with different angles, which could avoid complex signal processing such as matched filtering. Iqbal et al [147] discussed an algorithm to predict the forward motion and backward motion of the target by applying a CNN framework on echo signals.…”
Section: Deep Learning For Other Radar-target-characteristic-based Ratrmentioning
Radar automatic target recognition (RATR) technology is fundamental but complicated system engineering that combines sensor, target, environment, and signal processing technology, etc. It plays a significant role in improving the level and capabilities of military and civilian automation. Although RATR has been successfully applied in some aspects, the complete theoretical system has not been established. At present, deep learning algorithms have received a lot of attention and have emerged as potential and feasible solutions in RATR. This paper mainly reviews related articles published between 2010 and 2022, which corresponds to the period when deep learning methods were introduced into RATR research. In this paper, the current research status of radar target characteristics is summarized, including motion, micro-motion, one-dimensional, and two-dimensional characteristics, etc. This paper reviews the progress of deep learning methods in the feature extraction and recognition of radar target characteristics in recent years, including space, air, ground, sea-surface targets, etc. Due to more and more attention and research results published in the past few years, it is hoped that this review can provide potential guidance for future research and application of deep learning in fields related to RATR.
“…For other narrowband radar target characteristics such as echo characteristics, the application of deep learning for RATR is relatively rare. Inspired by the huge success of deep learning techniques in the field of SAR-ATR and computer vision, Fan et al [146] designed a five-layer CNN for typical cube, tetrahedron, and triangular prism recognition utilizing raw radar signals with different angles, which could avoid complex signal processing such as matched filtering. Iqbal et al [147] discussed an algorithm to predict the forward motion and backward motion of the target by applying a CNN framework on echo signals.…”
Section: Deep Learning For Other Radar-target-characteristic-based Ratrmentioning
Radar automatic target recognition (RATR) technology is fundamental but complicated system engineering that combines sensor, target, environment, and signal processing technology, etc. It plays a significant role in improving the level and capabilities of military and civilian automation. Although RATR has been successfully applied in some aspects, the complete theoretical system has not been established. At present, deep learning algorithms have received a lot of attention and have emerged as potential and feasible solutions in RATR. This paper mainly reviews related articles published between 2010 and 2022, which corresponds to the period when deep learning methods were introduced into RATR research. In this paper, the current research status of radar target characteristics is summarized, including motion, micro-motion, one-dimensional, and two-dimensional characteristics, etc. This paper reviews the progress of deep learning methods in the feature extraction and recognition of radar target characteristics in recent years, including space, air, ground, sea-surface targets, etc. Due to more and more attention and research results published in the past few years, it is hoped that this review can provide potential guidance for future research and application of deep learning in fields related to RATR.
“…In this category, we find radar cross section (RCS) responses or micro-Doppler measurements that can be directly used to classify different objects, moving targets or human activities [10][11][12]. Recent works on object classification based on raw SAR measurements have even shown results that are only slightly inferior to pre-processed data, but at much lower computational costs [13,14]. For these reasons, we will use the results of classifications based on raw data as a reference in this work.…”
This study addresses the classification of objects using their electromagnetic signatures with Convolutional Neural Networks (CNNs) trained on noiseless data. The singularity expansion method (SEM) was applied to establish a compact model that accurately represents the ultra-wideband scattered field of an object, independently of its orientation and observation angle. To perform the classification, we used a CNN associated with a noise-robust SEM technique to classify different objects based on their characteristic parameters. To validate this approach, we compared the performance of the classifier with and without SEM pre-processing of the scattered field for different noise levels and for object sizes not present in the training set. Moreover, we propose a procedure that determines the direction of the receiving antenna and orientation of an object based on the residues associated with each complex natural resonance. This classification procedure using pre-processed SEM data is promising, especially when generalizing to object sizes not included in the training set.
“…Recently, [20]- [22] studied CNNs for radar signal processing. They proposed a low probability of intercept waveform recognition [20], automatic target recognition based on raw radar echoes [21], and radar imaging using CNN [22]. We utilize the characteristics of CNNs to classify road structures using frequency magnitude response of received signals of several scans as input of the CNNs.…”
In this study, we propose a method to recognize road environments with automotive frequency-modulated continuous wave (FMCW) radar systems. For automotive radar systems on the road, diverse road environments are observed. Each road environment generates unnecessary echoes known as clutter, and the magnitude distribution of received radar signal varies depending on road structures. Therefore, it is necessary to classify the road environment and adopt a target detection algorithm suitable for each road environment characteristic. To recognize the road environment in advance, it is necessary to identify the section where the road environment changes. In this paper, we define a changed road area as a transition region, and we classify the road environment and transition regions to improve the road environment recognition performance. Road environments are recognized by applying convolutional neural networks to the frequency-domain received signals of 77 GHz FMCW automotive radar systems. Experimental results in real-road environments demonstrate that the proposed method achieves 100% recognition performance, which is better if compared with that of the conventional methods. INDEX TERMS Automotive frequency-modulated continuous wave (FMCW) radar, road environment recognition, convolutional neural network.
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.