Contour-Based LiDAR Standard Detection in Unstructured Point Clouds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for extrinsic calibration of sensor pairs, such as lidar and camera systems, are limited by access constraints and require time-consuming processes that cannot be performed in the field, leading to misalignment over time.
Innovation Solution
A method for automatically detecting a calibration standard in unstructured lidar point clouds using contour metrics, distance metrics, and distribution criteria to identify and define the boundaries of a calibration standard, enabling efficient extrinsic calibration in real-world scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional metrological methods are used to survey sensor position and orientation, then calibration accuracy is improved, but the process becomes time-consuming and cannot be performed in the field
Solution Approach 1:
The system performs automatic calibration using self-contained sensors (lidar and camera) without requiring external surveying equipment or controlled environments. The sensors capture images and point cloud data of the calibration target, and the processor automatically determines sensor poses through image processing and point cloud analysis, enabling field-ready calibration that is both accurate and time-efficient
Solution Approach 2:
The patent replaces traditional mechanical/metrological surveying methods with optical and computational approaches. Instead of using external measurement instruments and manual surveying, the system uses lidar point cloud data and camera images combined with automated processing algorithms to determine sensor positions and orientations, significantly reducing calibration time while maintaining accuracy
2Reliability
If known calibration targets are arranged in meticulously staged scenes, then calibration reliability is improved, but the process becomes expensive and requires controlled environments with access constraints
Solution Approach 1:
The system uses a self-contained calibration target with machine-readable patterns that can be detected automatically by the sensors. The calibration target includes multiple patterns at different positions and orientations, allowing the system to perform reliable calibration without requiring meticulous manual arrangement or controlled environments, making it suitable for field deployment
Solution Approach 2:
The calibration target serves as an intermediary object that mediates between the sensors and the calibration process. The target's machine-readable patterns provide a reliable reference that the lidar and camera can automatically detect and process, eliminating the need for complex external surveying equipment or controlled staged scenes while maintaining high calibration reliability
3Ease of operation
If sensor platform is disassembled to enable access for calibration, then calibration accessibility is improved, but the process becomes more complex and time-consuming
Solution Approach 1:
The system performs calibration automatically using the sensors already mounted on the platform, without requiring disassembly or external access. The lidar and camera capture data of the calibration target from their fixed positions, and the processor automatically computes sensor poses, making calibration accessible and simple while maintaining accuracy
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Systems and methods include obtaining point cloud data representing a point cloud; selecting a subset of the point cloud data based at least in part on a contour metric; grouping sets of points of the subset of the point cloud into one or more clusters based at least in part on one or more distance metrics; for a cluster that satisfies one or more cluster size criteria based on dimensions of a calibration standard, determining whether a distribution of signal intensities of points of the cluster satisfies a distribution criterion; based on a determination that the distribution of signal intensities of points satisfies the distribution criterion, determining boundaries of a region that represents the calibration standard; and storing data identifying a set of points of the point cloud that correspond to the calibration standard.