Autoregressive Model-Based Signal Reconstruction for Automotive Radar Interference Mitigation

Rameez, Muhammad; Dahl, Mattias; Pettersson, Mats I.

doi:10.1109/jsen.2020.3042061

Cited by 41 publications

(21 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As described, the performance of the above traditional signal processing methods depends on a proper selection of a few manually adjustable parameters. Over a wide range of the SINR variations, their performance is not good as the selected DL-based methods 1 .…”

Section: E Comparative Analysis With Other Techniquesmentioning

confidence: 98%

Prior-Guided Deep Interference Mitigation for FMCW Radars

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

A prior-guided deep learning (DL) based interference mitigation approach is proposed for frequency modulated continuous wave (FMCW) radars. In this paper, the interference mitigation problem is tackled as a regression problem. Considering the complex-valued nature of radar signals, the complex-valued convolutional neural network is utilized as an architecture for implementation, which is different from the conventional real-valued counterparts. Meanwhile, as the useful beat signals of FMCW radars and interferences exhibit different distributions in the time-frequency domain, this prior feature is exploited as a regularization term to avoid overfitting of the learned representation. The effectiveness and accuracy of our proposed complex-valued fully convolutional network (CV-FCN) based interference mitigation approach are verified and analyzed through both simulated and measured radar signals.Compared to the real-valued counterparts, the CV-FCN shows a better interference mitigation performance with a potential of half memory reduction in low Signal to Interference plus Noise Ratio (SINR) scenarios. Moreover, the CV-FCN trained using only simulated data can be directly utilized for interference mitigation in various measured radar signals and shows a superior generalization capability. Furthermore, by incorporating the prior feature, the CV-FCN trained on only 1/8 of the full data achieves comparable performance as that on the full dataset in low SINR scenarios, and the training procedure converges faster.

show abstract

Section: E Comparative Analysis With Other Techniquesmentioning

confidence: 98%

Prior-Guided Deep Interference Mitigation for FMCW Radars

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Interference in FMCW depends on the radar parameters like centre frequency, bandwidth, chirp duration and chirp repetition time. Because of the interference there is degradation is due to interference induced noise in the radar images [27]- [29]. The probability of encountering time-limited interference that leads to SINR degradation is much higher than the ghost target scenario.…”

Section: Mutual Interference In Automotive Radarsmentioning

confidence: 99%

Implementation of feature extraction and deep learning-based ensemble classifier for interference mitigation in radar signals

Indira

Rao

2021

IJEECS

View full text Add to dashboard Cite

In automotive vehicles, radar is the one of the component for autonomous driving, used for target detection and long-range sensing. Whereas interference exists in signals, noise increases and it effects severely while detecting target objects. For these reasons, various interference mitigation techniques are implemented in this paper. By using these mitigation techniques interference and noise are reduced and original signals are reconstructed. In this paper, we proposed a method to mitigate interference in signal using deep learning. The proposed method provides the best and accurate performance in relate to the various interference conditions and gives better accuracy compared with other existing methods.

show abstract

“…Several signal processing techniques for interference mitigation have been proposed in recent years. These techniques range from simple ones, such as the zeroing of the part subjected to interference using an inverse cosine window [3], to more complex ones, such as adaptive digital beamforming [4], and IF signal reconstruction [5].…”

Section: Introductionmentioning

confidence: 99%

“…The advantage of this method over the zeroing method in [3] is that the information from the disturbed parts of the received signal can be recovered. The results are compared with the autoregressive (AR) model-based fast-time signal reconstruction approach presented in [5].…”

Section: Introductionmentioning

confidence: 99%

Signal Reconstruction Using Bi-LSTM for Automotive Radar Interference Mitigation

Rameez

Javadi

Dahl

et al. 2022

2021 18th European Radar Conference (EuRAD)

Self Cite

View full text Add to dashboard Cite

Automotive radar has emerged as an important sensor for environmental perception in modern vehicles. A rapid increase in the number of radars present in traffc operating at unregulated frequencies has given rise to a mutual interference problem. In order for radar-based systems to function reliably, such interference must be mitigated. In this paper, this problem is addressed with a bidirectional long short-term memory (Bi-LSTM) network as a deep learning approach. Using the Bi-LSTM network, we reconstruct the intermediate frequency (IF) signal and recover samples lost to interference. The proposed signal reconstruction method is evaluated via real measurement data. The proposed Bi-LSTM network provides a better performance than an autoregressive model-based signal reconstruction method.

show abstract

Autoregressive Model-Based Signal Reconstruction for Automotive Radar Interference Mitigation

Abstract: Interference is mitigated by reconstructing the received signal via fast-or slow-time AR models estimated using the clean samples.

Cited by 41 publications

References 37 publications

Prior-Guided Deep Interference Mitigation for FMCW Radars

Prior-Guided Deep Interference Mitigation for FMCW Radars

Implementation of feature extraction and deep learning-based ensemble classifier for interference mitigation in radar signals

Signal Reconstruction Using Bi-LSTM for Automotive Radar Interference Mitigation

Contact Info

Product

Resources

About