Radatron: Accurate Detection Using Multi-resolution Cascaded MIMO Radar

Madani, Sohrab; Guan, Jayden; Ahmed, Waleed; Gupta, Saurabh; Hassanieh, Haitham

doi:10.1007/978-3-031-19842-7_10

Cited by 10 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most public datasets generate radar labels based on LiDAR or RBG camera data [3]- [5]. After calibrating the sensors and mapping the signals onto the same plane, a human annotator [3], [4] or existing object detection algorithms [6]- [8] detect or annotate objects on the overlapped signals. However, failures in these other sensors can produce incorrect radar annotations.…”

Section: Introductionmentioning

confidence: 99%

ARC: Automotive Radar Consistency Regularization for Semi-Supervised Learning

Lee,

Jovanov,

Kumcu

et al. 2024

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

In recent years, radar has become a crucial part of road scene perception. In particular, radar increases sensing reliability in poor weather and lighting conditions. State-of-theart deep learning methods require training, but the labeling of radar data needed to generate the required "ground truth" is time-consuming and requires expert knowledge, due to the confusing nature of radar signals. This limits the development of accurate radar models. To address the difficulty of annotating radar datasets, we propose a novel semi-supervised learning framework we call Automotive Radar Consistency (ARC), which enables the inclusion of unlabeled radar frames during training. This improves performance without adding manual labor. Our model learns object features based on micro-Doppler signatures from a time series of radar frames. We posit that the same object in both the forward and reverse temporal directions will share similar features, and we use this as a consistency regularization to encourage the model to learn how to distinguish targets. In addition, we propose Focal JS-divergence to alleviate over-fitting and address the class imbalance problem in semisupervised learning, by focusing on the hard classes and samples in the unlabeled data. Our proposed method is a general training strategy that can be incorporated in most existing deep learning frameworks. Our experimental results on two public datasets with limited annotations show that our method significantly improves the performance of existing supervised methods. Under the same network architecture, our method outperforms the fully supervised method in object detection by as much as 36%.

show abstract

Section: Introductionmentioning

confidence: 99%

ARC: Automotive Radar Consistency Regularization for Semi-Supervised Learning

Lee,

Jovanov,

Kumcu

et al. 2024

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

show abstract

“…On the other hand, raw radar data allows for a more detailed analysis of the received signal, enabling enhanced object discrimination and feature extraction. Several datasets [12]- [15] have enabled research for object recognition tasks on range-Doppler (RD) spectra [14], [16], [17], rangeazimuth (RA) maps [6], [18], [19], range-azimuth-Doppler (RAD) cubes [3], [6], [20] and more recently on analog-todigital-converter (ADC) data [5], [21]. This paper focuses on the RD spectrum as it is usually the most efficient representation to use in the radar signal processing chain to detect objects before DoA estimation.…”

Section: Introductionmentioning

confidence: 99%

DAROD: A Deep Automotive Radar Object Detector on Range-Doppler maps

Colin

VanRullen

Salle

et al. 2022

2022 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Due to the small number of raw data automotive radar datasets and the low resolution of such radar sensors, automotive radar object detection has been little explored with deep learning models in comparison to camera and lidarbased approaches. However, radars are low-cost sensors able to accurately sense surrounding object characteristics (e.g., distance, radial velocity, direction of arrival, radar crosssection) regardless of weather conditions (e.g., rain, snow, fog). Recent open-source datasets such as CARRADA, RADDet or CRUW have opened up research on several topics ranging from object classification to object detection and segmentation. In this paper, we present DAROD, an adaptation of Faster R-CNN object detector for automotive radar on the range-Doppler spectra. We propose a light architecture for features extraction, which shows an increased performance compare to heavier vision-based backbone architectures. Our models reach respectively an mAP@0.5 of 55.83 and 46.57 on CARRADA and RADDet datasets, outperforming competing methods.

show abstract