A Continuous-Time Approach for 3D Radar-to-Camera Extrinsic Calibration

Wise, Emmett; Peršić, Juraj; Grebe, Christopher; Petrović, Ivan; Kelly, Jonathan

doi:10.1109/icra48506.2021.9561938

Cited by 18 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Heng [18] proposes a 6-DoF target-less calibration method by optimizing point-to-plane distances between radar scans and a 3D map. Using 4D radar velocity measurements, Wise et al [19] also propose a target-less calibration approach which minimizes the errors between the radar velocity measurements and the motion of other sensors. Although these approaches can accomplish 6-DoF calibration with fewer restrictions, it is still challenging to calibrate planar automotive radars, which are still more widely used in autonomous vehicles currently.…”

Section: A Radar-related Extrinsic Calibrationmentioning

confidence: 99%

Extrinsic and Temporal Calibration of Automotive Radar and 3-D LiDAR in Factory and On-Road Calibration Settings

Lee,

Hou,

Wang

et al. 2023

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

While automotive radars are widely used in ADAS and autonomous driving, extrinsic and temporal calibration of automotive radars with other sensors is still daunting due to the sparsity, uncertainty, and missing elevation angles of automotive radar measurements. We propose a target-based calibration approach of 3D automotive radar and 3D LiDAR that performs extrinsic and temporal calibration in both factory and on-road settings. In factory calibration settings, a map is built with precise target poses; target trajectories are estimated based on map-based target localization in which the accuracy of both nearby and faraway target pose estimates can be ensured. The spatial and temporal relationships between radar and LiDAR measurements are established with target trajectories to accomplish extrinsic and temporal calibration. The proposed data collection procedure provides sufficient motion for analyzing time delay between sensors and can significantly reduce the data collection effort and time. There is 52.3% distance error reduction after time delay compensation in the experiment, which shows the improvements of temporal calibration. In on-road calibration settings, the metal objects with semantic labels, such as traffic signs, are selected as calibration targets. Although there could be insufficient correspondences to infer the missing dimension of planar radar for six DoF extrinsic calibration as demonstrated in factory calibration settings, the three extrinsic parameters and the time delay are shown still to be accurate. We validated the proposed method using the nuScenes datasets, which provide sensor measurements, poses, and HD map. With twenty-two data logs, each has over 1000 correspondences, the result of extrinsic parameters reaches centimeter-level accuracy compared with the offered benchmark. The time delay compensation improves 1 meter error for radar tracking in a 20 m/s vehicle case and improves mapping quality in real world data.

show abstract

Section: A Radar-related Extrinsic Calibrationmentioning

confidence: 99%

Extrinsic and Temporal Calibration of Automotive Radar and 3-D LiDAR in Factory and On-Road Calibration Settings

Lee,

Hou,

Wang

et al. 2023

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

show abstract

“…When conducting experiments on intersection scenes, it is also necessary to calibrate the sensors in terms of time and space after arranging the sensors [25]. Time calibration is the inter frame time synchronization of heterogeneous sensors, which solves the problem of misalignment between radar frames and video frames caused by different sampling frequencies.…”

Section: A Multi-sensor Spatiotemporal Calibrationmentioning

confidence: 99%

Target Detection Algorithm Based on MMW Radar and Camera Fusion

Jiang

Zhang

Meng

2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

An efficient and accurate traffic monitoring system often takes advantages of multi-sensor detection to ensure the safety of urban traffic, promoting the accuracy and robustness of target detection and tracking. A method for target detection using Radar-Vision Fusion Path Aggregation Fully Convolutional One-Stage Network (RV-PAFCOS) is proposed in this paper, which is extended from Fully Convolutional One-Stage Network (FCOS) by introducing the modules of radar image processing branches, radar-vision fusion and path aggregation. The radar image processing branch mainly focuses on the image modeling based on the spatiotemporal calibration of millimeter-wave (mmw) radar and cameras, taking the conversion of radar point clouds to radar images. The fusion module extracts features of radar and optical images based on the principle of spatial attention stitching criterion. The path aggregation module enhances the reuse of feature layers, combining the positional information of shallow feature maps with deep semantic information, to obtain better detection performance for both large and small targets. Through the experimental analysis, the method proposed in this paper can effectively fuse the mmw radar and vision perceptions, showing good performance in traffic target detection.

show abstract

“…However, this method cannot process the information generated by 3D radar because the transformation between sensors is no longer a fixed relationship between faces. To get rid of the dependence on calibrated targets, Schöller et al [26] and Wise et al [27] made separate attempts, the former using end-to-end deep learning in a targetless scenario to estimate the extrinsic rotation parameters of the associated vehicle detected in radar measurements and camera images. However, the algorithm requires extrinsic measurements of the translational parameters first.…”

Section: Introductionmentioning

confidence: 99%

A Target-based co-calibration framework for 3DRadar-camera using a modified corner reflector

Chen,

Shao,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Most intelligent transportation and autonomous driving systems use the combination of millimeter-wave (MMW) radar and camera to achieve strong perception, and correct extrinsic calibration is a prerequisite for sensor fusion. Most prior calibration methods rely on specific calibration environment, resulting in low calibration efficiency, and are unsuitable for practical scenarios. This paper proposes a progressive and efficient extrinsic calibration method for 3D MMW radar and camera, which only requires testers to walk around the testing range with the calibration target, and the progressive process of extrinsic parameters regression is visualized. The proposed method has been tested on the View-of-Delft dataset and in the real world, and the results show that the method proposed in this paper can converge the calibrated extrinsic parameters quickly and has strong robustness to the noise present during the testing process. Compared to EPNP, LM, P3P (based on RANSAC), and LM (based on RANAC), our proposed calibration method demonstrates a smaller re-projection error and higher accuracy in terms of extrinsic parameters. All results indicate that our calibration method has good accuracy and efficiency for practical calibration scenarios.

show abstract

A Continuous-Time Approach for 3D Radar-to-Camera Extrinsic Calibration

Cited by 18 publications

References 23 publications

Extrinsic and Temporal Calibration of Automotive Radar and 3-D LiDAR in Factory and On-Road Calibration Settings

Extrinsic and Temporal Calibration of Automotive Radar and 3-D LiDAR in Factory and On-Road Calibration Settings

Target Detection Algorithm Based on MMW Radar and Camera Fusion

A Target-based co-calibration framework for 3DRadar-camera using a modified corner reflector

Contact Info

Product

Resources

About