Raw High-Definition Radar for Multi-Task Learning

Rebut, Julien; Ouaknine, Arthur; Malik, Waqas; Pérez, Patrick

doi:10.1109/cvpr52688.2022.01651

Cited by 48 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also worth highlighting the low-level radar datasets that have been facilitating the research in this direction. These include RADIATE [34], RADIal [29], ORR [2], CRUW [35], while new ones (e.g. K-Radar [23]) continue to emerge.…”

Section: Related Workmentioning

confidence: 99%

“…To assist discussion, we provide a brief introduction to the RADIal [29] dataset, and readers are referred to the original publication for more details.…”

Section: The Radial Datasetmentioning

confidence: 99%

“…A learnable signal processing module, as shown in the dashed box, is introduced within the network to enable end-to-end learning. The backbone and head networks are adopted from [29] for comparison, while other types of backbone and head networks can be easily incorporated.…”

Section: The Radial Datasetmentioning

confidence: 99%

“…In [29], the authors presented a model termed FFT-RadNet. This model learns to perform object detection and freespace segmentation, using radar RD data.…”

Section: A Trainable Dsp Modulementioning

confidence: 99%

See 3 more Smart Citations

ADCNet: End-to-end perception with raw radar ADC data

Yang¹,

Khatri²,

Happold³

et al. 2023

Preprint

View full text Add to dashboard Cite

There is a renewed interest in radar sensors in the autonomous driving industry. As a relatively mature technology, radars have seen steady improvement over the last few years, making them an appealing alternative or complement to the commonly used LiDARs. An emerging trend is to leverage rich, low-level radar data for perception. In this work we push this trend to the extremewe propose a method to perform end-to-end learning on the raw radar analog-to-digital (ADC) data. Specifically, we design a learnable signal processing module inside the neural network, and a pre-training method guided by traditional signal processing algorithms. Experiment results corroborate the overall efficacy of the end-to-end learning method, while an ablation study validates the effectiveness of our individual innovations.

show abstract

Section: Related Workmentioning

confidence: 99%

“…To assist discussion, we provide a brief introduction to the RADIal [29] dataset, and readers are referred to the original publication for more details.…”

Section: The Radial Datasetmentioning

confidence: 99%

Section: The Radial Datasetmentioning

confidence: 99%

“…In [29], the authors presented a model termed FFT-RadNet. This model learns to perform object detection and freespace segmentation, using radar RD data.…”

Section: A Trainable Dsp Modulementioning

confidence: 99%

See 2 more Smart Citations

ADCNet: End-to-end perception with raw radar ADC data

Yang¹,

Khatri²,

Happold³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Decourt et al [15] work on range-Doppler spectra to solve an object detection task. Rebut et al [16] also use range-Doppler spectra, but in their approach the angular representation is learned as part of the object detection network.…”

Section: Related Workmentioning

confidence: 99%

Histogram-based Deep Learning for Automotive Radar

Tatarchenko¹,

Rambach²

2023

Preprint

View full text Add to dashboard Cite

There are various automotive applications that rely on correctly interpreting point cloud data recorded with radar sensors. We present a deep learning approach for histogrambased processing of such point clouds. Compared to existing methods, the design of our approach is extremely simple: it boils down to computing a point cloud histogram and passing it through a multi-layer perceptron. Our approach matches and surpasses state-of-the-art approaches on the task of automotive radar object type classification. It is also robust to noise that often corrupts radar measurements, and can deal with missing features of single radar reflections. Finally, the design of our approach makes it more interpretable than existing methods, allowing insightful analysis of its decisions.

show abstract

ROFusion: Efficient Object Detection Using Hybrid Point-Wise Radar-Optical Fusion

Liu,

Zhi,

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Raw High-Definition Radar for Multi-Task Learning

Cited by 48 publications

References 32 publications

ADCNet: End-to-end perception with raw radar ADC data

ADCNet: End-to-end perception with raw radar ADC data

Histogram-based Deep Learning for Automotive Radar

ROFusion: Efficient Object Detection Using Hybrid Point-Wise Radar-Optical Fusion

Contact Info

Product

Resources

About