Object Sequence Fusion for Sparse LiDAR Mobility Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining mobility parameters of an object, such as orientation and velocity, from sparse lidar point cloud measurements in semantic images is challenging and often results in inaccurate estimations.
Innovation Solution
A multi-modal fusion pipeline system that generates virtual points for objects in semantic images and associates them with lidar points, creating a denser point cloud. This system uses object sequences across multiple semantic images to improve the accuracy of mobility parameter determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If sparse lidar point cloud measurements are used to determine mobility parameters, then the system complexity is reduced, but the measurement precision deteriorates
Solution Approach 1:
The patent combines sparse lidar point cloud measurements with virtual points generated from semantic image data to create a denser composite point cloud. This merging of real sensor data with synthetically generated data points improves the measurement precision of mobility parameters without requiring additional physical sensors or increasing system complexity
Solution Approach 2:
The patent introduces virtual points as an intermediary element that bridges the gap between sparse lidar measurements and the need for dense point cloud data. These virtual points, generated from semantic image information, serve as a mediator to enhance measurement accuracy without directly adding complex hardware
2Measurement precision
If object sequences across multiple semantic images are used, then the measurement precision of mobility parameters is improved, but the loss of time increases
Solution Approach 1:
The patent performs preliminary actions by generating virtual points and creating object sequences in advance, before the actual mobility parameter estimation is needed. This preprocessing allows the system to have ready-to-use enhanced data structures, reducing the computational burden and time required during real-time operation
Data Source
AI summary
A system can use semantic images, lidar images, and/or 3D bounding boxes to determine mobility parameters for objects in the semantic image. In some cases, the system can generate virtual points for an object in a semantic image and associate the virtual points with lidar points to form denser point clouds for the object. The denser point clouds can be used to estimate the mobility parameters for the object. In certain cases, the system can use semantic images, lidar images, and/or 3D bounding boxes to determine an object sequence for an object. The object sequence can indicate a location of the particular object at different times. The system can use the object sequence to estimate the mobility parameters for the object.