CARRADA Dataset: Camera and Automotive Radar with Range- Angle- Doppler Annotations

Ouaknine, Arthur; Newson, Alasdair; Rebut, Julien; Tupin, Florence; Pérez, Patrick

doi:10.1109/icpr48806.2021.9413181

Cited by 89 publications

(53 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While they provide accurate range and velocity, they suffer from a low azimuth resolution leading to ambiguity in separating close objects. Recent datasets include processed radar representations such as the entire Range-Azimuth-Doppler (RAD) tensor [31], [43] or single views of this tensor -either Range-Azimuth (RA) [1], [38], [17], [41], [27] or Range-Doppler (RD) [27]. These representations require large bandwidth to be transmitted as well as large memory storage.…”

Section: Radar Backgroundmentioning

confidence: 99%

“…Owing to the promising capabilities of HD radars, our work [24] 2019 Small HD CL 3D Boxes RadarRobotCar [1] 2020 Large S CLO CARRADA [31] 2020 Small LD C Segmentation RADIATE [38] 2020 Medium S CLO 2D Boxes MulRan [17] 2020 Medium S CLO Zendar [27] 2020 Small HD CL 2D Boxes CRUW [41] 2021 Medium LD C Point Location RadarScenes [36] 2021 Large HD CO Point-wise RADDet [43] 2021…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Raw High-Definition Radar for Multi-Task Learning

Rebut¹,

Ouaknine²,

Malik³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Fig. 1: Overview of our RADIal dataset. RADIal includes a set of 3 sensors (camera, laser scanner, high-definition radar) and comes with GPS and vehicle's CAN traces; 25K synchronized samples are recorded in raw format. (a) Camera image with projected laser point cloud in red and radar point cloud in indigo, vehicle annotation in orange and free driving space annotation in green; (b) Radar power spectrum with bounding box annotations; (c) Free driving space annotation in bird-eye view, with annotated vehicle bounding boxes in orange, radar point cloud in indigo and laser point cloud in red; (d) Range-Azimuth map in Cartesian coordinates overlayed with radar point cloud and laser point cloud; (e) GPS trace in red and odometry trajectory reconstruction in green.

show abstract

Section: Radar Backgroundmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Raw High-Definition Radar for Multi-Task Learning

Rebut¹,

Ouaknine²,

Malik³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some sets expose low sample rates and imbalanced object class distributions whereas other records do not include Doppler information [15], [16], depriving themselves of radars unique feature altogether. Only recently, first radar datasets featuring annotations on the frequency level were made publicly available [17], [18], [19] but it remains to be seen if these are going to have a similar impact on the community and will incite comparable research efforts as the famous KITTI [20] and Cityscapes [21] benchmarks did for vision-based scene-understanding. Both aspects, the tedious annotation of radar data followed by an inevitable inflow of misinformation and the preferable elimination of equivocation call for completely different approaches, establishing the subfield of self-supervised learning.…”

Section: B Foregoing Explicit Data Annotationsmentioning

confidence: 99%

GenRadar: Self-Supervised Probabilistic Camera Synthesis Based on Radar Frequencies

Ditzel

Dietmayer

2021

IEEE Access

View full text Add to dashboard Cite

Autonomous systems require a continuous and dependable environment perception for navigation and decision-making, which is best achieved by combining different sensor types. Radar continues to function robustly in compromised circumstances in which cameras become impaired, guaranteeing a steady inflow of information. Yet, camera images provide a more intuitive and readily applicable impression of the world. This work combines the complementary strengths of both sensor types in a unique self-learning fusion approach for a probabilistic scene reconstruction in adverse surrounding conditions. After reducing the memory requirements of both high-dimensional measurements through a decoupled stochastic self-supervised compression technique, the proposed algorithm exploits similarities and establishes correspondences between both domains at different feature levels during training. Then, at inference time, relying exclusively on radio frequencies, the model successively predicts camera constituents in an autoregressive and self-contained process. These discrete tokens are finally transformed back into an instructive view of the respective surrounding, allowing to visually perceive potential dangers for important tasks downstream.

show abstract

Section: B Foregoing Explicit Data Annotationsmentioning

confidence: 99%

GenRadar: Self-supervised Probabilistic Camera Synthesis based on Radar Frequencies

Ditzel¹,

Dietmayer²

2021

Preprint

View full text Add to dashboard Cite

Autonomous systems require a continuous and dependable environment perception for navigation and decisionmaking, which is best achieved by combining different sensor types. Radar continues to function robustly in compromised circumstances in which cameras become impaired, guaranteeing a steady inflow of information. Yet, camera images provide a more intuitive and readily applicable impression of the world. This work combines the complementary strengths of both sensor types in a unique self-learning fusion approach for a probabilistic scene reconstruction in adverse surrounding conditions. After reducing the memory requirements of both high-dimensional measurements through a decoupled stochastic self-supervised compression technique, the proposed algorithm exploits similarities and establishes correspondences between both domains at different feature levels during training. Then, at inference time, relying exclusively on radio frequencies, the model successively predicts camera constituents in an autoregressive and selfcontained process. These discrete tokens are finally transformed back into an instructive view of the respective surrounding, allowing to visually perceive potential dangers for important tasks downstream.

show abstract

CARRADA Dataset: Camera and Automotive Radar with Range- Angle- Doppler Annotations

Cited by 89 publications

References 36 publications

Raw High-Definition Radar for Multi-Task Learning

Raw High-Definition Radar for Multi-Task Learning

GenRadar: Self-Supervised Probabilistic Camera Synthesis Based on Radar Frequencies

GenRadar: Self-supervised Probabilistic Camera Synthesis based on Radar Frequencies

Contact Info

Product

Resources

About