Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149578
Thomas J. Kramer, Erik R. Biehl, Matthew B. Heintzelman, S. Blunt, Erick Steinbach
Spectrally shaped forms of random frequency modulation (RFM) radar waveforms have been experimentally demonstrated for a variety of implementation approaches and applications. Of these, the continuous-wave (CW) perspective is particularly interesting because it enables the prospect of very high signal dimensionality and arbitrary receive processing from a range/Doppler perspective, while also mitigating range ambiguities by avoiding repetition. Here we leverage a modification to the constant-envelope orthogonal frequency division multiplexing (CE-OFDM) framework, which was originally proposed for power-efficient communications, to realize a nonrepeating FMCW radar signal that can be represented with a compact parameterization, thereby circumventing memory constraints that could arise for some applications. Experimental loopback and open-air measurements are used to demonstrate this waveform type.
{"title":"Compact Parameterization of Nonrepeating FMCW Radar Waveforms","authors":"Thomas J. Kramer, Erik R. Biehl, Matthew B. Heintzelman, S. Blunt, Erick Steinbach","doi":"10.1109/RadarConf2351548.2023.10149578","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149578","url":null,"abstract":"Spectrally shaped forms of random frequency modulation (RFM) radar waveforms have been experimentally demonstrated for a variety of implementation approaches and applications. Of these, the continuous-wave (CW) perspective is particularly interesting because it enables the prospect of very high signal dimensionality and arbitrary receive processing from a range/Doppler perspective, while also mitigating range ambiguities by avoiding repetition. Here we leverage a modification to the constant-envelope orthogonal frequency division multiplexing (CE-OFDM) framework, which was originally proposed for power-efficient communications, to realize a nonrepeating FMCW radar signal that can be represented with a compact parameterization, thereby circumventing memory constraints that could arise for some applications. Experimental loopback and open-air measurements are used to demonstrate this waveform type.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"19 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130714170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149749
Grant Norrie, S. Paine
A joint Radar Communications testbed is presented. This testbed leverages the OFDM based DAB standard to generate Radcom signals. The extended DAB mode structure used to describe these signals was used as the basis on which the communications sub-systems were designed. Furthermore, a radar processing subsystem was developed to process the same signal. Finally a functional testbed was deployed and used to complete system integration tests thereby demonstrating the joint RadCom functionality.
{"title":"Design and Demonstration of an OFDM Based RadCom System","authors":"Grant Norrie, S. Paine","doi":"10.1109/RadarConf2351548.2023.10149749","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149749","url":null,"abstract":"A joint Radar Communications testbed is presented. This testbed leverages the OFDM based DAB standard to generate Radcom signals. The extended DAB mode structure used to describe these signals was used as the basis on which the communications sub-systems were designed. Furthermore, a radar processing subsystem was developed to process the same signal. Finally a functional testbed was deployed and used to complete system integration tests thereby demonstrating the joint RadCom functionality.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130887889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149706
Matthew B. Heintzelman, Jonathan Owen, S. Blunt, Brianna Maio, Erick Steinbach
We consider the intersection between nonrepeating random FM (RFM) waveforms and practical forms of optimal mismatched filtering (MMF). Specifically, the spectrally-shaped inverse filter (SIF) is a well-known approximation to the least-squares (LS-MMF) that provides significant computational savings. Given that nonrepeating waveforms likewise require unique nonrepeating MMFs, this efficient form is an attractive option. Moreover, both RFM waveforms and the SIF rely on spectrum shaping, which establishes a relationship between the goodness of a particular waveform and the mismatch loss (MML) the corresponding filter can achieve. Both simulated and open-air experimental results are shown to demonstrate performance.
{"title":"Practical Considerations for Optimal Mismatched Filtering of Nonrepeating Waveforms","authors":"Matthew B. Heintzelman, Jonathan Owen, S. Blunt, Brianna Maio, Erick Steinbach","doi":"10.1109/RadarConf2351548.2023.10149706","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149706","url":null,"abstract":"We consider the intersection between nonrepeating random FM (RFM) waveforms and practical forms of optimal mismatched filtering (MMF). Specifically, the spectrally-shaped inverse filter (SIF) is a well-known approximation to the least-squares (LS-MMF) that provides significant computational savings. Given that nonrepeating waveforms likewise require unique nonrepeating MMFs, this efficient form is an attractive option. Moreover, both RFM waveforms and the SIF rely on spectrum shaping, which establishes a relationship between the goodness of a particular waveform and the mismatch loss (MML) the corresponding filter can achieve. Both simulated and open-air experimental results are shown to demonstrate performance.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130612979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149639
Brandon Ravenscroft, Alfred Fontes, Patrick M. McCormick, S. Blunt, Cameron H. Musgrove
Leveraging a recent method for spectrally-shaped random FM (RFM) waveform generation, in conjunction with a particular implementation of spread-spectrum signaling, a multi-user form of dual-function radar/communication (DFRC) is proposed that seeks to balance the disparate requirements of each function. Using a radar-amenable spread-spectrum multiple-access signaling scheme, receive dynamic range for sensing is preserved by exploiting high-dimensional (and thus separable) waveforms, which are specifically structured to convey encoded information in a manner that can be readily decoded at a communication receiver.
{"title":"Physically Realizable Multi-User Radar/Communications (MURC)","authors":"Brandon Ravenscroft, Alfred Fontes, Patrick M. McCormick, S. Blunt, Cameron H. Musgrove","doi":"10.1109/RadarConf2351548.2023.10149639","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149639","url":null,"abstract":"Leveraging a recent method for spectrally-shaped random FM (RFM) waveform generation, in conjunction with a particular implementation of spread-spectrum signaling, a multi-user form of dual-function radar/communication (DFRC) is proposed that seeks to balance the disparate requirements of each function. Using a radar-amenable spread-spectrum multiple-access signaling scheme, receive dynamic range for sensing is preserved by exploiting high-dimensional (and thus separable) waveforms, which are specifically structured to convey encoded information in a manner that can be readily decoded at a communication receiver.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130535192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149775
A. Diewald, Benjamin Nuss, T. Zwick
Radar target simulators (RTSs) have recently drawn much attention in research and commercial development, as they are capable of performing over-the-air validation tests under laboratory conditions by generating virtual radar echoes that are perceived as targets by a radar under test (RuT). The estimated angle of arrival (AoA) of such a virtual target is controlled, among others, by the physical position of the respective RTS channel that generates it. In this contribution the authors investigate the achievable angle accuracy of RTS systems in dependence of their channel spacing and calibration. This allows to derive the number of RTS channels required given the field of view of the RuT and the desired angle accuracy. For this purpose, a signal model is developed that incorporates the angular positions of the RTS channels and thereby allows an estimation of the achievable angle accuracy under consideration of coherence conditions. The signal model is verified by a measurement campaign.
{"title":"Angle Accuracy in Radar Target Simulation","authors":"A. Diewald, Benjamin Nuss, T. Zwick","doi":"10.1109/RadarConf2351548.2023.10149775","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149775","url":null,"abstract":"Radar target simulators (RTSs) have recently drawn much attention in research and commercial development, as they are capable of performing over-the-air validation tests under laboratory conditions by generating virtual radar echoes that are perceived as targets by a radar under test (RuT). The estimated angle of arrival (AoA) of such a virtual target is controlled, among others, by the physical position of the respective RTS channel that generates it. In this contribution the authors investigate the achievable angle accuracy of RTS systems in dependence of their channel spacing and calibration. This allows to derive the number of RTS channels required given the field of view of the RuT and the desired angle accuracy. For this purpose, a signal model is developed that incorporates the angular positions of the RTS channels and thereby allows an estimation of the achievable angle accuracy under consideration of coherence conditions. The signal model is verified by a measurement campaign.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124380129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149616
B. K. Chalise, Jahi Douglas, K. Wagner
The effectiveness of target detection methods in radar systems depend on how accurately clutter can be characterized. However, depending on application, clutter statistics vary, and therefore it is difficult to accurately predict such statistics and their parameters. Model-based detection algorithms that are developed for one clutter scenario will fail to yield satisfactory results in another scenario. In this paper, we propose a complete data driven multiple change point detection (CPD) for target detection which does not requires the knowledge of the underlying clutter distribution. The key concept is to iteratively search for slow time instance that maximizes the cumulative sum (CUMSUM) Kolmogorov-Smirnov (KS) statistics. If such statistics exceeds a pre-specified threshold value, then this slow time instance is added to the collection of the estimated change points. This process continues until all CUMSUM-KS statistics are below the threshold. Computer simulations are used to demonstrate the effectiveness of this method for different clutter distributions.
{"title":"Multiple Change Point Detection-based Target Detection in Clutter","authors":"B. K. Chalise, Jahi Douglas, K. Wagner","doi":"10.1109/RadarConf2351548.2023.10149616","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149616","url":null,"abstract":"The effectiveness of target detection methods in radar systems depend on how accurately clutter can be characterized. However, depending on application, clutter statistics vary, and therefore it is difficult to accurately predict such statistics and their parameters. Model-based detection algorithms that are developed for one clutter scenario will fail to yield satisfactory results in another scenario. In this paper, we propose a complete data driven multiple change point detection (CPD) for target detection which does not requires the knowledge of the underlying clutter distribution. The key concept is to iteratively search for slow time instance that maximizes the cumulative sum (CUMSUM) Kolmogorov-Smirnov (KS) statistics. If such statistics exceeds a pre-specified threshold value, then this slow time instance is added to the collection of the estimated change points. This process continues until all CUMSUM-KS statistics are below the threshold. Computer simulations are used to demonstrate the effectiveness of this method for different clutter distributions.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125843689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149670
Sunila Akbar, R. Adve, Z. Ding, P. Moo
A radar resource management module in a cognitive multifunction radar manages the resources by first prioritizing and then scheduling the tasks. Apart from scheduling the tasks, the task scheduler of a cognitive radar requires the scheduling to be adaptable to the changing environment. We formulate a gen-eral model for the distributions of task parameters, specifically, task priorities and delay tolerance, to ensure priority-based task scheduling. We develop the use of transfer learning (TL) within a deep reinforcement learning (DRL) framework to address the challenge of adaptability to a varying environment. Our approach builds on using a Monte Carlo Tree Search (MCTS) aided by a deep neural network (DNN). We show that TL allows accelerated training by transferring the policy learned by training the D NN-based MCTS on initial parameter distribution (environment) to the policy required for a new environment. Our results show that the high priority tasks are least delayed and dropped with the new formulation, whereas TL ensures the respective adaptation to the dynamic environment.
{"title":"Priority-based Task Scheduling in Dynamic Environments for Cognitive MFR via Transfer DRL","authors":"Sunila Akbar, R. Adve, Z. Ding, P. Moo","doi":"10.1109/RadarConf2351548.2023.10149670","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149670","url":null,"abstract":"A radar resource management module in a cognitive multifunction radar manages the resources by first prioritizing and then scheduling the tasks. Apart from scheduling the tasks, the task scheduler of a cognitive radar requires the scheduling to be adaptable to the changing environment. We formulate a gen-eral model for the distributions of task parameters, specifically, task priorities and delay tolerance, to ensure priority-based task scheduling. We develop the use of transfer learning (TL) within a deep reinforcement learning (DRL) framework to address the challenge of adaptability to a varying environment. Our approach builds on using a Monte Carlo Tree Search (MCTS) aided by a deep neural network (DNN). We show that TL allows accelerated training by transferring the policy learned by training the D NN-based MCTS on initial parameter distribution (environment) to the policy required for a new environment. Our results show that the high priority tasks are least delayed and dropped with the new formulation, whereas TL ensures the respective adaptation to the dynamic environment.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"3 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113941389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149764
David Luong, Ian Lam, B. Balaji, S. Rajan
In previous work, it was shown that a noise radars have two signal-to-noise ratios (SNRs) associated with them: one for the receive signal and another for the signal retained within for matched filtering. However, these two SNRs can be combined into a single correlation coefficient which can be easily be used for performance prediction. Unlike SNR, this correlation coefficient can be estimated directly from radar detection data. This work presents experimental verification of the theoretical relationship between the SNRs of a noise radar and the correlation coefficient, showing that it holds for a wide range of transmit powers.
{"title":"Correlation Coefficient vs. Transmit Power for an Experimental Noise Radar","authors":"David Luong, Ian Lam, B. Balaji, S. Rajan","doi":"10.1109/RadarConf2351548.2023.10149764","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149764","url":null,"abstract":"In previous work, it was shown that a noise radars have two signal-to-noise ratios (SNRs) associated with them: one for the receive signal and another for the signal retained within for matched filtering. However, these two SNRs can be combined into a single correlation coefficient which can be easily be used for performance prediction. Unlike SNR, this correlation coefficient can be estimated directly from radar detection data. This work presents experimental verification of the theoretical relationship between the SNRs of a noise radar and the correlation coefficient, showing that it holds for a wide range of transmit powers.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"195 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114121150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149625
Nicolai Kern, Julian Aguilar, Pirmin Schoeder, C. Waldschmidt
A key element for the interaction between pedestrians and autonomous vehicles is the automated recognition of traffic and communication gestures. Gestures help vehicles to resolve critical or ambiguous situations. Detecting gestures with radar sensors is advantageous with respect to environmental conditions and lighting. However, the collection of a radar dataset that covers the wide range of variations in automotive scenarios comes at high cost and effort. On the other side, datasets with limited variations lead to reduced recognition accuracy or even complete failure in new scenarios. Hence, this paper analyzes the impact that deficiencies of traffic gesture datasets can have on the accuracy and investigates mitigation strategies based on the augmentation by simulated, variation-rich radar data. It is shown that by augmentation the robustness of a convolutional neural network (CNN)-based classifier against variations not covered by the training data is significantly improved. As a key result, both complete failure of the classifier and strongly decreased classification accuracy are avoided.
{"title":"Improving the Robustness of Automotive Gesture Recognition by Diversified Simulation Datasets","authors":"Nicolai Kern, Julian Aguilar, Pirmin Schoeder, C. Waldschmidt","doi":"10.1109/RadarConf2351548.2023.10149625","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149625","url":null,"abstract":"A key element for the interaction between pedestrians and autonomous vehicles is the automated recognition of traffic and communication gestures. Gestures help vehicles to resolve critical or ambiguous situations. Detecting gestures with radar sensors is advantageous with respect to environmental conditions and lighting. However, the collection of a radar dataset that covers the wide range of variations in automotive scenarios comes at high cost and effort. On the other side, datasets with limited variations lead to reduced recognition accuracy or even complete failure in new scenarios. Hence, this paper analyzes the impact that deficiencies of traffic gesture datasets can have on the accuracy and investigates mitigation strategies based on the augmentation by simulated, variation-rich radar data. It is shown that by augmentation the robustness of a convolutional neural network (CNN)-based classifier against variations not covered by the training data is significantly improved. As a key result, both complete failure of the classifier and strongly decreased classification accuracy are avoided.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125725318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/RadarConf2351548.2023.10149792
Juezhu Lai, D. Yuan, Jifang Pei, Deqing Mao, Yin Zhang, Xingyu Tuo, Yulin Huang
Complex scene reconstruction is one of the most critical issues in scanning radar processing. The azimuth echo of the scanning radar can be equivalent to the convolution result of the scene scattering coefficient and the antenna pattern. Iter-ative shrinkage-thresholding algorithm (ISTA) has been proven effective in the target reconstruction of the scanning radar, but it often performs unsatisfactory reconstruction quality on complex scenes. This paper proposes a new learning-based approach, an improved ISTA-based deep unfolding network, to reconstruct the scene information from the scanning radar echoes. Unlike the traditional analysis-based method, we established a deep unfolded scene reconstruction network based on the structure of ISTA. This network can learn the optimal network parameters through the input radar data, which avoids the manual selection of parameters in the traditional method. Besides, we apply a loss function to ensure the effectiveness of the sparse transformation so that the method can recover target information from scanning radar echoes in various complex scenes. Extensive experiments demonstrate that this method can highly improve scene reconstruction performance.
{"title":"Scanning Radar Scene Reconstruction With Deep Unfolded ISTA Neural Network","authors":"Juezhu Lai, D. Yuan, Jifang Pei, Deqing Mao, Yin Zhang, Xingyu Tuo, Yulin Huang","doi":"10.1109/RadarConf2351548.2023.10149792","DOIUrl":"https://doi.org/10.1109/RadarConf2351548.2023.10149792","url":null,"abstract":"Complex scene reconstruction is one of the most critical issues in scanning radar processing. The azimuth echo of the scanning radar can be equivalent to the convolution result of the scene scattering coefficient and the antenna pattern. Iter-ative shrinkage-thresholding algorithm (ISTA) has been proven effective in the target reconstruction of the scanning radar, but it often performs unsatisfactory reconstruction quality on complex scenes. This paper proposes a new learning-based approach, an improved ISTA-based deep unfolding network, to reconstruct the scene information from the scanning radar echoes. Unlike the traditional analysis-based method, we established a deep unfolded scene reconstruction network based on the structure of ISTA. This network can learn the optimal network parameters through the input radar data, which avoids the manual selection of parameters in the traditional method. Besides, we apply a loss function to ensure the effectiveness of the sparse transformation so that the method can recover target information from scanning radar echoes in various complex scenes. Extensive experiments demonstrate that this method can highly improve scene reconstruction performance.","PeriodicalId":168311,"journal":{"name":"2023 IEEE Radar Conference (RadarConf23)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131257265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：