Resource-Efficient Deep Neural Networks for Automotive Radar Interference Mitigation
نویسندگان
چکیده
Radar sensors are crucial for environment perception of driver assistance systems as well autonomous vehicles. With a rising number radar and the so far unregulated automotive frequency band, mutual interference is inevitable must be dealt with. Algorithms models operating on data required to run early processing steps specialized sensor hardware. This hardware typically has strict resource-constraints, i.e. low memory capacity computational power. Convolutional Neural Network (CNN)-based approaches denoising mitigation yield promising results in terms performance. Regarding however, CNNs exceed hardware's capacities by far. In this paper we investigate quantization techniques CNN-based signals. We analyze (i) weights (ii) activations different model architectures. reduced requirements storage during inference. compare with fixed learned bit-widths contrast two methodologies training quantized CNNs, straight-through gradient estimator distributions over discrete weights. illustrate importance structurally small real-valued base show that smallest models. achieve reduction around 80\% compared baseline. Due practical reasons, recommend use 8 bits activations, which require only 0.2 megabytes memory.
منابع مشابه
Nonlinear Interference Mitigation via Deep Neural Networks
A neural-network-based approach is presented to efficiently implement digital backpropagation (DBP). For a 32×100 km fiber-optic link, the resulting “learned” DBP significantly reduces the complexity compared to conventional DBP implementations. OCIS codes: (060.0060) Fiber optics and optical communications, (060.2330) Fiber optics communications.
متن کاملInterference Mitigation in Automotive Radars
We study the mutual interference problem arising in the fast growing market of automotive radars. For the widely used frequency-modulated continuous waveform automotive radars, the major consequences of mutual interference are ghost targets and increased noise floor. The schemes of interference mitigation are then investigated, including adaptive signal processing in the time domain at receive ...
متن کاملResource allocation with interference mitigation in femtocellular networks
The introduction of femtocells enabled high data rates and better indoor coverage without the need for expanding or increasing the density of cellular networks deployment or upgrading the cellular network infrastructure. Despite this direct advantage, the introduction of femtocells challenges traditional interference mechanisms because of the ad hoc and dense nature of femtocell deployment. In ...
متن کاملEfficient Model Averaging for Deep Neural Networks
Large neural networks trained on small datasets are increasingly prone to overfitting. Traditional machine learning methods can reduce overfitting by employing bagging or boosting to train several diverse models. For large neural networks, however, this is prohibitively expensive. To address this issue, we propose a method to leverage the benefits of ensembles without explicitely training sever...
متن کاملRadar-to-Radar Interference Suppression for Distributed Radar Sensor Networks
Radar sensor networks, including biand multi-static radars, provide several operational advantages, like reduced vulnerability, good system flexibility and an increased radar cross-section. However, radar-to-radar interference suppression is a major problem in distributed radar sensor networks. In this paper, we present a cross-matched filtering-based radar-to-radar interference suppression alg...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Journal of Selected Topics in Signal Processing
سال: 2021
ISSN: ['1941-0484', '1932-4553']
DOI: https://doi.org/10.1109/jstsp.2021.3062452