arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.12706eess.SPcs.LG
收藏

量化神经网络在雷达干扰抑制中的应用

Quantized Neural Networks for Radar Interference Mitigation

Graz University of Technology(格拉茨技术大学);Infineon Technologies Austria AG(英飞凌科技奥地利股份公司)

Johanna Rock, Wolfgang Roth, Paul Meissner, Franz Pernkopf

摘要:

雷达传感器对于驾驶员辅助系统和自动驾驶汽车的环境感知至关重要。关键性能因素是耐候性和直接测量速度的可能性。随着雷达传感器数量的不断增加和汽车雷达频段的不规范,相互干扰是不可避免的,必须加以处理。在早期处理阶段对雷达数据进行操作的算法和模型需要直接在专用硬件(即雷达传感器)上运行。这种专用硬件通常具有严格的资源约束,即低存储器容量和低计算能力。基于卷积神经网络(CNN)的去噪和干扰抑制方法在性能方面为雷达处理带来了有希望的结果。然而,这些模型通常包含数百万个参数,存储在数百兆字节的内存中,并且在执行期间需要额外的内存。在本文中,我们研究基于CNN的去噪和雷达信号的干扰减轻量化技术。我们通过考虑(i)量化权重和(ii)分段常数激活函数来分析不同基于CNN的模型架构和大小的量化潜力,这分别降低了模型存储和推理步骤的内存需求。

英文摘要:

Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. Key performance factors are weather resistance and the possibility to directly measure velocity. 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 in early processing stages are required to run directly on specialized hardware, i.e. the radar sensor. 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. However, these models typically contain millions of parameters, stored in hundreds of megabytes of memory, and require additional memory during execution. In this paper we investigate quantization techniques for CNN-based denoising and interference mitigation of radar signals. We analyze the quantization potential of different CNN-based model architectures and sizes by considering (i) quantized weights and (ii) piecewise constant activation functions, which results in reduced memory requirements for model storage and during the inference step respectively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑