automatic extrinsic calibration for lidar-stereo vehicle ... · • tested with hdl-64e &...
TRANSCRIPT
Automatic Extrinsic Calibration for Lidar-Stereo
Vehicle Sensor SetupsCarlos Guindel, Jorge Beltrán,
David Martín and Fernando García
Intelligent Systems Laboratory · Universidad Carlos III de Madrid
IEEE 20th International Conference on Intelligent Transportation Systems
Yokohama · 17 October 2017
Agenda
Motivation
Calibration algorithm
Synthetic test suite
Results
Conclusion
2
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Agenda
Motivation
Calibration algorithm
Synthetic test suite
Results
Conclusion
3
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Perception systems in vehicles
• Topologies with complementary sensory modalities
4
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Cameras
Stereo-visionsystems
Rangescanners
Multi-layer3D lidarscanner
• High accuracy
• 360º Field of View
• Appearance information
• Cost-effective
• Dense 3D info.
OvelappingFOVs
Correspondencebetween data
representations
Extrinsiccalibration
requiredData fusion
IVVI 2.0 Research Platform
Previous works
• Camera-to-range calibration in robotic/automotive platforms
• Complex setups / lack of generalization ability
• Strong assumptions are usually made: sensor resolution, limited pose range, environment structure,…
• Assessment of calibration methods
• Ground-truth of extrinsic parameters cannot be obtained in practice
5
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Geiger et al., ICRA 2012 Velas et al., WSCG 2014
Levinson & Thrun, RSS 2013
Proposal overview6
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
• Stereo-vision system–multi-layer lidar calibration
• Suitable for use with different models of lidar scanners (e.g. 16-layer)
• Very different relative poses are allowed
• Performed within a reasonable time using a simple setup
Agenda
Motivation
Calibration algorithm
Synthetic test suite
Results
Conclusion
7
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Calibration algorithm
• Calibration target
• Process overview
8
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
• Single point of view
• Holes visible from the camera and intersected by at least 2 lidar beams
• No alignment required
Registration
Data
CAMERA
Target segmentation
CAMERA
Circlessegmentation
CAMERA
Data
LIDAR
Target segmentation
LIDAR
Circlessegmentation
LIDAR
𝝃CL =𝑡𝑥𝑡𝑦𝑡𝑧𝜙𝜃𝜓
Data representation9
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Registration
Data
CAMERA
Target segmentation
CAMERA
Circlessegmentation
CAMERA
Data
LIDAR
Target segmentation
LIDAR
Circlessegmentation
LIDAR
Data representation10
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Point cloud: 𝒫0𝑐Stereo matching
Left image
Right image
Point cloud: 𝒫0𝑙
• 3D point clouds, 𝒫0 = { 𝑥, 𝑦, 𝑧 }
Stereo matching
• Accuracy in the depth estimation is required (SGM)
• Border localization problem will be tackled using intensity
Data
CAMERA
Data
LIDARLIDAR: 𝒫0
𝑙
Target segmentation · Step 111
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Target segmentation
CAMERA CAMERA
Target segmentation
LIDAR LIDAR
𝝃CL =𝑡𝑥𝑡𝑦𝑡𝑧𝜙𝜃𝜓
Target segmentation · Step 112
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Point clouds: 𝒫0Plane model
extraction
Plane model extraction
• Random sample consensus (RANSAC)
• Tight threshold (1 cm) and requirement for the plane to be roughly parallel to the vertical axis (tol: 0.55 rad)
Remove pts. farfrom the planes
Target segmentation
CAMERA/LIDAR
LIDAR: 𝒫1𝑙CAMERA: 𝒫1
𝑐
• Extracting the points belonging to discontinuities in the target
• Successive segmentations: 𝒫𝑖0 = { 𝑥, 𝑦, 𝑧 } ⊆ 𝒫𝑖0−1
Step 1
Target segmentation · Step 213
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Target segmentation
CAMERA
Left image Sobel filtering
Point cloud: 𝒫1𝑐
Keepdiscontinuities
CAMERA: 𝒫2𝑐
for every point in 𝒫1𝑙
CAMERA: Sobel edges
Target segmentation
LIDAR
Filter out
LIDAR: 𝒫2𝑙
Step 2
Step 2
(50 cm)
Circles segmentation · Step 114
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Circlessegmentation
CAMERA
Circlessegmentation
LIDAR
𝝃CL =𝑡𝑥𝑡𝑦𝑡𝑧𝜙𝜃𝜓
Circles segmentation · Step 1
• Getting rid of the points not belonging to the circles: target boundaries
15
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Circlessegmentation
CAMERA
Step 1
Point cloud: 𝒫2𝑐 3D-line RANSAC Point cloud: 𝒫3
𝑐
Geometricalconstraints
LIDAR: 𝒫3𝑙CAMERA: 𝒫3
𝑐
• Keep only the rings where a circle is possible
• Remove the outer points
Circlessegmentation
LIDAR
Step 1
Circles segmentation · Step 216
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
• Detecting the center of the holes
Circles segmentation
CAMERA/LIDAR
Step 2
Point cloud: 𝒫3Alignment with
XY plane2D CircleRANSAC
4 x centers + radius
Undo the alignment
Geometrical constraints
4 x centers coordinates
• 2D search: only three points are required
Circle model extraction
Camera Lidar
Circles segmentation · Step 3
• Robustness against noise
17
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Circles segmentation
CAMERA/LIDAR
Step 3
𝑡0
𝑡1
…
𝑡𝑁4 x center
coordinates
4 x center coordinates
4 x center coordinates
Euclidean clustering
4 x cluster centroids
CAMERA LIDAR
tol: 2 cm
Registration18
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Registration
𝝃CL =𝑡𝑥𝑡𝑦𝑡𝑧𝜙𝜃𝜓
Registration19
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
4 x reference points, 𝒑𝑐
𝑖
Registration
Circles segmentation
CAMERA
Circles segmentation
LIDAR4 x reference
points, 𝒑𝑙𝑖
• Pure translation
• Overdetermined system of 12 equations
𝒕𝐶𝐿 = ഥ𝒑𝑙𝑖 − ഥ𝒑𝑐
𝑖
• Column-pivoting QR decomposition
Step 1
• Iterative Closest Points (ICP)
Step 2
Translation
Translation + Rotation
Composition
𝝃CL =𝑡𝑥𝑡𝑦𝑡𝑧𝜙𝜃𝜓
Agenda
Motivation
Calibration algorithm
Synthetic test suite
Results
Conclusion
20
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Synthetic Test Suite
• Our proposal for quantitative assessment of calibration algorithms
• Exact ground-truth, but also noise and real constraints
• Simulation of sensors and their environment based on Gazebo
• Different calibration scenarios
21
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Calibration target
Stereo-vision system model
Velodyne models
Gazebo models, plugins and worlds available athttp://wiki.ros.org/velo2cam_gazeboOpen source · GPLv2 License
Agenda
Motivation
Calibration algorithm
Synthetic test suite
Results
Conclusion
22
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Experimental setup
• Using the synthetic test suite
• Nine different calibration setups
• 7 simple setups to evaluate the parameters of the transform
• 2 challenging situations
• Gaussian noise added to the sensor measurements
• Models simulated with real parameters
• 12 cm stereo baseline and 16-layer lidar
23
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
𝑒𝑡 = ‖𝒕 − 𝒕𝒈‖
Translation error (linear)
𝑒𝑟 = ∠(𝑹−𝟏𝑹𝒈)
Rotation error (angular)
𝑹 𝒕
Selection of the length of the window, 𝑁
Translation error (linear) Rotation error (angular)
Experiments
• Accumulation of cluster centroids over 𝑁 frames
• 𝑁 images and 𝑁 point clouds processed
• Not every window provides clusters to be accumulated
24
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Circles segmentation
CAMERA/LIDAR
Step 3
Experiments
• Noise is included in the measurements from the sensors
• Gaussian noise: 𝒩 0, 𝐾𝜎02
25
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
𝜎0𝑐 = 0.007
CAMERA
𝜎0𝑙 = 0.008 𝑚
LIDAR
Translation error (linear) Rotation error (angular)
Robustness to noise, 𝐾
Comparison26
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Geiger et al., ICRA 2012Geiger et al., ICRA 2012
• Public web toolbox
• Monocular cam., provide intrinsics
• Tested with HDL-64E & Kinect
Velas et al., WSCG 2014
• Public ROS package
• Monocular camera
• Not suitable for large pose displacements
• Tested with HDL-32E
RecreatedIn Gazebo
16 layers 32 layers 64 layers
Experiments27
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Tra
ns
lati
on
err
or
Ro
tati
on
err
or
16 layers 32-layer 64-layer16-layer
Experiments28
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Tra
ns
lati
on
err
or
Ro
tati
on
err
or
16 layers 32-layer 64-layer16-layer
Results
• IVVI 2.0 platform
• Bumblebee XB3 stereo system: 1280 x 960 images, 12 cm baseline
• Velodyne VLP-16
29
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Results30
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Results in real scenarios31
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Stereo + lidar point clouds aligned
Results in real scenarios32
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Lidar measurements projected on the image
Agenda
Motivation
Calibration algorithm
Synthetic test suite
Results
Conclusion
33
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
Conclusion
• Method for calibration of lidar–stereo-camera setups:
• Without user intervention
• Suitable for close-to-production devices
• Assessment of the calibration methods using advanced simulation
• Exact ground-truth in unlimited calibration scenarios
• Results validate our calibration approach
34
Automatic Extrinsic Calibration for Lidar-Stereo Vehicle Sensor SetupsC. Guindel, J. Beltrán et al. · ITSC 2017
ROS Package available athttp://wiki.ros.org/velo2cam_calibrationOpen source · GPLv2 License
Future work
• Further testing
• Sensitivity to different stereo matching approaches (e.g. CNN-based), weather/illumination conditions,…
• Monocular camera–multi-layer lidar calibration
• Geometrical information may be extracted from the calibration target
Thank youfor your attention
Carlos Guindel · [email protected]
IEEE 20th International Conference on Intelligent Transportation Systems
Yokohama · 17 October 2017