Spatiotemporal Multisensor Calibration via Gaussian Processes Moving Target Tracking

Peršić, Juraj; Petrović, Luka; Marković, Ivan

doi:10.1109/tro.2021.3061364

Cited by 30 publications

(18 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second type of methods, such as those discussed in [44], perform temporal and spatial calibration while having the sensors track the same target. It works in those settings where the target is known to all the sensors.…”

Section: B Temporal Calibrationmentioning

confidence: 99%

TrajMatch: Towards Automatic Spatio-temporal Calibration for Roadside LiDARs through Trajectory Matching

Ren¹,

Zhang²,

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

Recently, it has become popular to deploy sensors such as LiDARs on the roadside to monitor the passing traffic and assist autonomous vehicle perception. Unlike autonomous vehicle systems, roadside sensors are usually affiliated with different subsystems and lack synchronization both in time and space. Calibration is a key technology which allows the central server to fuse the data generated by different location infrastructures, which can deliver improve the sensing range and detection robustness. Unfortunately, existing calibration algorithms often assume that the LiDARs are significantly overlapped or that the temporal calibration is already achieved. Since these assumptions do not always hold in the real world, the calibration results from the existing algorithms are often unsatisfactory and always need human involvement, which brings high labor costs.In this paper, we propose TrajMatch -the first system that can automatically calibrate for roadside LiDARs in both time and space. The main idea is to automatically calibrate the sensors based on the result of the detection/tracking task instead of extracting special features. More deeply, we propose a mechanism for evaluating calibration parameters that is consistent with our algorithm, and we demonstrate the effectiveness of this scheme experimentally, which can also be used to guide parameter iterations for multiple calibration. Finally, to evaluate the performance of TrajMatch , we collect two dataset, one simulated dataset LiDARnet-sim 1.0 and a real-world dataset. Experiment results show that TrajMatch can achieve a spatial calibration error of less than 10cm and a temporal calibration error of less than 1.5ms.

show abstract

Section: B Temporal Calibrationmentioning

confidence: 99%

TrajMatch: Towards Automatic Spatio-temporal Calibration for Roadside LiDARs through Trajectory Matching

Ren¹,

Zhang²,

Li³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In our proposed work, we optimize the extrinsic and the temporal parameter iteratively, avoiding error accumulation along the traveling path. Furthermore, Persic et al propose to use tracking results from both sensor modalities to solve for geometric and temporal calibration parameters [25]. Similarly, the calibration performance is also limited by the accumulated error in tracked objects.…”

Section: Joint Calibrationmentioning

confidence: 99%

SST-Calib: Simultaneous Spatial-Temporal Parameter Calibration between LIDAR and Camera

Kodaira¹,

Zhou²,

Zang³

et al. 2022

Preprint

View full text Add to dashboard Cite

With information from multiple input modalities, sensor fusion-based algorithms usually out-perform their singlemodality counterparts in robotics. Camera and LIDAR, with complementary semantic and depth information, are the typical choices for detection tasks in complicated driving environments. For most camera-LIDAR fusion algorithms, however, the calibration of the sensor suite will greatly impact the performance. More specifically, the detection algorithm usually requires an accurate geometric relationship among multiple sensors as the input, and it is often assumed that the contents from these sensors are captured at the same time. Preparing such sensor suites involves carefully designed calibration rigs and accurate synchronization mechanisms, and the preparation process is usually done offline. In this work, a segmentationbased framework is proposed to jointly estimate the geometrical and temporal parameters in the calibration of a camera-LIDAR suite. A semantic segmentation mask is first applied to both sensor modalities, and the calibration parameters are optimized through pixel-wise bidirectional loss. We specifically incorporated the velocity information from optical flow for temporal parameters. Since supervision is only performed at the segmentation level, no calibration label is needed within the framework. The proposed algorithm is tested on the KITTI dataset, and the result shows an accurate real-time calibration of both geometric and temporal parameters.

show abstract

“…These solutions can also be based on tracking of some object (marker), like a ball of a certain color in the calibration of multiple RGB-D Kinect v2 sensors [8], or marker-less, like proposed by [9] that focuses on working with short sequences or [10] that considers sensor's accuracy to provide the uncertainty of the obtained calibration. In [11], the authors focus on the trajectory representation proposing Gaussian processes as a better alternative for trajectory alignment. The marker-less solutions do not rely on the placement of an artificial marker in the environment but the experimental environment is expected to be well-suited for VO/SLAM systems.…”

Section: Related Workmentioning

confidence: 99%

“…The spatiotemporal calibration with those approaches is usually performed by decoupling the problem of spatial and temporal calibration. The temporal calibration is often found with some form of cross-correlation on the time-evolution of a signal that is independent of the spatial calibration (like linear or rotational speeds) [10], [11]. Some researchers believe that these estimations should not be decoupled [12] and the problem should be solved simultaneously.…”

Section: Related Workmentioning

confidence: 99%

Spatiotemporal Calibration of Camera and 3D Laser Scanner

Nowicki

2020

Preprint

View full text Add to dashboard Cite

The multi-sensory setups consisting of the laser scanners and cameras are popular as the measurements complement each other and provide necessary robustness for applications. Under dynamic conditions or when in motion, a direct transformation (spatial calibration) and time offset between sensors (temporal calibration) is needed to determine the correspondence between measurements. We propose an opensource spatiotemporal calibration framework for a camera and a 3D laser scanner. Our solution is based on commonly available chessboard markers requiring one-minute calibration before the operation that offers accurate and repeatable results. The framework is based on batch optimization of point-to-plane constraints with a time offset calibration possible by a novel continuous representation of the plane equations based on a minimal representation in the Lie algebra and the use of Bsplines. The framework's properties are evaluated in simulation while correctness is verified with two distinct sensory setups with Velodyne VLP-16 and SICK MRS6124 3D laser scanners.

show abstract

Spatiotemporal Multisensor Calibration via Gaussian Processes Moving Target Tracking

Cited by 30 publications

References 40 publications

TrajMatch: Towards Automatic Spatio-temporal Calibration for Roadside LiDARs through Trajectory Matching

TrajMatch: Towards Automatic Spatio-temporal Calibration for Roadside LiDARs through Trajectory Matching

SST-Calib: Simultaneous Spatial-Temporal Parameter Calibration between LIDAR and Camera

Spatiotemporal Calibration of Camera and 3D Laser Scanner

Contact Info

Product

Resources

About