Vehicle Occlusion Detection Using LiDAR Point Cloud Model Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems using LiDAR sensors struggle to accurately and quickly determine the occlusion level of target objects, which is crucial for predicting movement routes and adjusting driving routes.
Innovation Solution
A vehicle control apparatus and method that utilize a processor to analyze point clouds from LiDAR sensors by matching them with pre-defined models stored in memory, determining the occlusion level based on overlapping proportions, and correcting incorrectly labeled occlusions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If traditional LiDAR point cloud analysis is used, then system simplicity is maintained, but processing speed deteriorates
Solution Approach 1:
The patent applies preliminary action by pre-defining 3D models of target objects before actual occlusion detection occurs. These pre-defined models contain predetermined geometric features and structural information that are prepared in advance. During runtime, the system only needs to match the LiDAR point cloud against these pre-prepared models, significantly reducing processing time compared to analyzing point clouds from scratch, thus improving productivity while maintaining reasonable system complexity.
2Device complexity
If occlusion level determination is performed without pre-defined models, then device complexity is reduced, but measurement precision deteriorates
Solution Approach 1:
The patent uses copying by creating and storing pre-defined 3D model copies of target objects in the system memory. These digital model copies contain accurate geometric representations of objects with known features. During occlusion detection, the system copies or loads these pre-defined models and compares them with the LiDAR point cloud data. This copying approach enables precise occlusion level identification by providing a reference standard, while the models can be stored efficiently in memory without requiring complex additional hardware.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables accurate and rapid identification of occlusion levels in point clouds, allowing for effective vehicle route adjustments and improved autonomous driving capabilities.
Implementation Method 1
a sensor, such as light detection and ranging (LiDAR)
Data Source
AI summary
The present disclosure may relate to a vehicle control apparatus and a method thereof. The vehicle control apparatus may include a sensor, such as a light detection and ranging (LiDAR) sensor, a memory storing a plurality of models, and a processor. The processor may obtain a point cloud corresponding to a target object via the sensor, match, based on identifying a target model, of the plurality of models, that corresponds to an object type of the target object, a first reference point with a second reference point, determine, based on matching a first heading direction of the point cloud with a second heading direction of the target model, a proportion, of the target model, that overlaps with the point cloud, determine an occlusion level of the point cloud based on the proportion, and output a signal indicating the occlusion level of the point cloud for controlling a vehicle.