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.
翻译:关键性能因素是天气阻力和直接测量速度的可能性。随着雷达传感器数量的增加和迄今为止不受管制的汽车雷达频率频带的增多,相互干扰是不可避免的,必须加以处理。在早期处理阶段根据雷达数据运行的等级和模型需要直接用专用硬件,即雷达传感器运行。这种专门硬件通常有严格的资源限制,即记忆能力低和计算能力低。基于革命神经网络的分辨和干扰减缓方法在性能方面为雷达处理工作带来有希望的结果。然而,这些模型通常包含数百万项参数,储存在数百兆字节的记忆中,在执行过程中需要额外的记忆。在本文中,我们调查对CNN的分辨和干扰雷达信号的缓解的定量技术。我们分析基于CNN的不同模型结构和大小的四分化潜力,方法是考虑(一) 分辨的重量和(二) 分辨的恒定的恒定引爆功能,这在模型存储和步骤期间分别导致记忆要求的减少。