Resource-efficient Deep Neural Networks for Automotive Radar Interference Mitigation

• URL: http://arxiv.org/abs/2201.10360v1
• Date: Tue, 25 Jan 2022 14:41:08 GMT
• Title: Resource-efficient Deep Neural Networks for Automotive Radar Interference Mitigation
• Authors: Johanna Rock, Wolfgang Roth, Mate Toth, Paul Meissner, Franz Pernkopf
• Abstract summary: CNN-based approaches for denoising and interference mitigation yield promising results for radar processing. We investigate quantization techniques for CNN-based denoising and interference mitigation of radar signals. We achieve a memory reduction of around 80% compared to the real-valued baseline.
• Score: 13.310007106264747
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. With a rising number of radar sensors and the so far unregulated automotive radar frequency band, mutual interference is inevitable and must be dealt with. Algorithms and models operating on radar data are required to run the early processing steps on specialized radar sensor hardware. This specialized hardware typically has strict resource-constraints, i.e. a low memory capacity and low computational power. Convolutional Neural Network (CNN)-based approaches for denoising and interference mitigation yield promising results for radar processing in terms of performance. Regarding resource-constraints, however, CNNs typically exceed the hardware's capacities by far. In this paper we investigate quantization techniques for CNN-based denoising and interference mitigation of radar signals. We analyze the quantization of (i) weights and (ii) activations of different CNN-based model architectures. This quantization results in reduced memory requirements for model storage and during inference. We compare models with fixed and learned bit-widths and contrast two different methodologies for training quantized CNNs, i.e. the straight-through gradient estimator and training distributions over discrete weights. We illustrate the importance of structurally small real-valued base models for quantization and show that learned bit-widths yield the smallest models. We achieve a memory reduction of around 80\% compared to the real-valued baseline. Due to practical reasons, however, we recommend the use of 8 bits for weights and activations, which results in models that require only 0.2 megabytes of memory.

Related papers

• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• End-to-End Training of Neural Networks for Automotive Radar Interference Mitigation [9.865041274657823]
  We propose a new method for training neural networks (NNs) for frequency modulated continuous wave (WFMC) radar mutual interference mitigation. Instead of training NNs to regress from interfered to clean radar signals as in previous work, we train NNs directly on object detection maps. We do so by performing a continuous relaxation of the cell-averaging constant false alarm rate (CA-CFAR) peak detector, which is a well-established algorithm for object detection using radar.
  arXiv  Detail & Related papers  (2023-12-15T13:47:16Z)
• Semantic Segmentation of Radar Detections using Convolutions on Point Clouds [59.45414406974091]
  We introduce a deep-learning based method to convolve radar detections into point clouds. We adapt this algorithm to radar-specific properties through distance-dependent clustering and pre-processing of input point clouds. Our network outperforms state-of-the-art approaches that are based on PointNet++ on the task of semantic segmentation of radar point clouds.
  arXiv  Detail & Related papers  (2023-05-22T07:09:35Z)
• Correlating sparse sensing for large-scale traffic speed estimation: A Laplacian-enhanced low-rank tensor kriging approach [76.45949280328838]
  We propose a Laplacian enhanced low-rank tensor (LETC) framework featuring both lowrankness and multi-temporal correlations for large-scale traffic speed kriging. We then design an efficient solution algorithm via several effective numeric techniques to scale up the proposed model to network-wide kriging.
  arXiv  Detail & Related papers  (2022-10-21T07:25:57Z)
• Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns [77.34726150561087]
  We introduce four complicated missing patterns, including missing and three fiber-like missing cases according to the mode-drivenn fibers. Despite nonity of the objective function in our model, we derive the optimal solutions by integrating alternating data-mputation method of multipliers.
  arXiv  Detail & Related papers  (2022-05-19T08:37:56Z)
• DeepHybrid: Deep Learning on Automotive Radar Spectra and Reflections for Object Classification [0.5669790037378094]
  We propose a method that combines classical radar signal processing and Deep Learning algorithms. The proposed method can be used for example to improve automatic emergency braking or collision avoidance systems.
  arXiv  Detail & Related papers  (2022-02-17T08:45:11Z)
• SignalNet: A Low Resolution Sinusoid Decomposition and Estimation Network [79.04274563889548]
  We propose SignalNet, a neural network architecture that detects the number of sinusoids and estimates their parameters from quantized in-phase and quadrature samples. We introduce a worst-case learning threshold for comparing the results of our network relative to the underlying data distributions. In simulation, we find that our algorithm is always able to surpass the threshold for three-bit data but often cannot exceed the threshold for one-bit data.
  arXiv  Detail & Related papers  (2021-06-10T04:21:20Z)
• Deep Interference Mitigation and Denoising of Real-World FMCW Radar Signals [16.748215232763517]
  We evaluate a Convolutional Neural Network (CNN)-based approach for interference mitigation on real-world radar measurements. We combine real measurements with simulated interference in order to create input-output data suitable for training the model.
  arXiv  Detail & Related papers  (2020-12-04T11:22:13Z)
• Quantized Neural Networks for Radar Interference Mitigation [14.540226579203207]
  CNN-based approaches for denoising and interference mitigation yield promising results for radar processing. We investigate quantization techniques for CNN-based denoising and interference mitigation of radar signals.
  arXiv  Detail & Related papers  (2020-11-25T13:18:06Z)
• Deep Networks for Direction-of-Arrival Estimation in Low SNR [89.45026632977456]
  We introduce a Convolutional Neural Network (CNN) that is trained from mutli-channel data of the true array manifold matrix. We train a CNN in the low-SNR regime to predict DoAs across all SNRs. Our robust solution can be applied in several fields, ranging from wireless array sensors to acoustic microphones or sonars.
  arXiv  Detail & Related papers  (2020-11-17T12:52:18Z)
• RAMP-CNN: A Novel Neural Network for Enhanced Automotive Radar Object Recognition [10.006245521984697]
  We propose a radar multiple-perspectives convolutional neural network (RAMP-CNN) that extracts the location and class of objects. To bypass the complexity of 4D convolutional neural networks (NN), we propose to combine several lower-dimension NN models within our RAMP-CNN model. The proposed RAMP-CNN model achieves better average recall and average precision than prior works in all testing scenarios.
  arXiv  Detail & Related papers  (2020-11-13T19:12:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.