Overhead Structure Recognition Using Vertical Distance and Reflectance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing overhead-structure recognition devices face challenges in accurately determining the presence of overhead structures, such as signs or bridges, when they are located ahead of a vehicle on a downhill slope, as the relative speed detected by millimeter waves can be equal to the horizontal relative speed calculated using LIDAR, leading to inaccurate determinations.
Innovation Solution
An overhead-structure recognition device is mounted on a vehicle, equipped with an acquisition unit to gather range point cloud data using laser light emitted in various directions, a subdivision unit to subdivide the data based on distance and direction, and a determination unit that focuses on the vertical distance between objects and high-reflectivity objects to accurately identify overhead structures by considering reflectance and spatial relationships.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If relative speed detection using millimeter waves is used to identify overhead structures, then the detection method is simple, but the determination accuracy deteriorates on downhill slopes where relative speed equals horizontal relative speed
Solution Approach 1:
The patent transitions from using only horizontal relative speed (1D measurement) to incorporating vertical distance information (3D spatial measurement) for overhead structure determination. By adding the vertical dimension to the detection parameters, the system can distinguish overhead structures from other objects even when horizontal relative speeds are identical, thereby resolving the accuracy issue on downhill slopes while maintaining operational simplicity.
2Device complexity
If only horizontal relative speed is used for overhead structure recognition, then the device complexity is low, but the recognition accuracy deteriorates in complex spatial scenarios
Solution Approach 1:
The patent enhances the recognition system by integrating vertical distance measurements from LIDAR with horizontal position data. This dimensional expansion allows the system to accurately identify overhead structures in complex spatial scenarios without requiring complex device architecture, as the additional vertical dimension provides sufficient discriminative power.
3Measurement precision
If vertical distance measurement is added to overhead structure determination, then the determination accuracy is improved, but the device complexity increases
Solution Approach 1:
The patent leverages the multi-functionality of the LIDAR device, which can simultaneously measure both vertical distance and horizontal position. By utilizing the existing LIDAR's capability to perform multiple measurement functions, the system achieves improved overhead structure determination accuracy without proportionally increasing device complexity, as the same sensor serves multiple detection purposes.
Solution Approach 2:
The patent combines vertical distance measurement data with horizontal position and relative speed information into a unified overhead structure determination process. By merging these different measurement dimensions into a single integrated recognition system, the patent achieves high determination accuracy while avoiding the complexity that would result from separate independent systems for each measurement type.
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
This configuration allows for high-accuracy determination of overhead structures by quantifying the vertical distance and reflectivity, effectively distinguishing them from other objects, even on downhill slopes, and enhances the reliability of object recognition for driving assistance systems.
Implementation Method 1
The object recognition device calculates a horizontal relative speed between the vehicle and an object of interest using LIDAR
Implementation Method 2
the object recognition device calculates a horizontal relative speed between the vehicle and an object of interest using LIDAR, and compares the calculated relative speed with a relative speed between the vehicle and the object of interest, detected by millimeter waves
Data Source
AI summary
In an overhead-structure recognition device to be mounted to a vehicle, a determination unit is configured to, in response to a vertical distance between an object of interest and a high-reflectivity object being greater than or equal to a predefined value of vertical distance, determine that the object of interest is an overhead structure which is a structure located above the vehicle that does not obstruct travel of the vehicle. The object of interest corresponds to a subset of interest among a plurality of subsets acquired by dividing range point cloud data. The high-reflectivity object is an object other than the object of interest, among objects corresponding to the respective subgroups, whose reflectance is greater than or equal to a predefined value of reflectance.