The progress brought by the deep learning technology over the last decade has inspired many research domains, such as radar signal processing, speech and audio recognition, etc., to apply it to their respective problems. Most of the prominent deep learning models exploit data representations acquired with either Lidar or camera sensors, leaving automotive radars rarely used. This is despite the vital potential of radars in adverse weather conditions, as well as their ability to simultaneously measure an object’s range and radial velocity seamlessly. As radar signals have not been exploited very much so far, there is a lack of available benchmark data. However, recently, there has been a lot of interest in applying radar data as input to various deep learning algorithms, as more datasets are being provided. To this end, this paper presents a survey of various deep learning approaches processing radar signals to accomplish some significant tasks in an autonomous driving application, such as detection and classification. We have itemized the review based on different radar signal representations, as it is one of the critical aspects while using radar data with deep learning models. Furthermore, we give an extensive review of the recent deep learning-based multi-sensor fusion models exploiting radar signals and camera images for object detection tasks. We then provide a summary of the available datasets containing radar data. Finally, we discuss the gaps and important innovations in the reviewed papers and highlight some possible future research prospects.
The time-domain maximum likelihood estimation of chirp signal parameters is investigated in this study. Three amplitude weighted phase-based estimators and two phase-unwrapping algorithms, that is, phase prediction and unwrapping algorithm (PP-UA) and differenced-phase prediction and unwrapping algorithm (DPP-UA) were proposed. The DPP-UA and PP-UA have their merits and drawbacks. The authors combine the merits of these two methods and propose a new phaseunwrapping algorithm, which outperforms PP-UA and DPP-UA under low signal-to-noise ratio (SNR) conditions. The authors' further study on the optimal number of initial data sample show that it is SNR-related and can be determined according to the '3σ' rule and the Cramer-Rao lower bound.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.