Lidar Object Recognition Excluding Space Floating Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Object recognition devices using laser radar struggle to accurately distinguish detection points from space floating objects, leading to incorrect object recognition.
Innovation Solution
An object recognition device that includes a detection point acquisition unit, a stereoscopic point determination unit, a detection point number calculation unit, a discontinuity index calculation unit, and an exclusion unit to exclude detection points that do not satisfy specific conditions, such as having a threshold number of nearby points and a low discontinuity index, thereby preventing the use of detection points from space floating objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If laser radar is used to acquire detection points, then object detection capability is improved, but detection points from space floating objects cannot be distinguished from actual objects
Solution Approach 1:
The patent changes spatial parameters (position coordinates) and distribution parameters (density, orientation) of detection points to distinguish valid objects from space floating objects. By analyzing whether detection points satisfy stereoscopic point conditions based on their spatial parameters and distribution characteristics, the system can identify and exclude invalid points while maintaining accurate object detection.
2Area of stationary object
If all detection points are used for object recognition, then detection coverage is improved, but recognition accuracy deteriorates due to inclusion of space floating objects
Solution Approach 1:
The patent extracts and excludes invalid detection points (space floating objects) from the set of all detection points while retaining valid points for object recognition. The exclusion unit removes points that do not satisfy stereoscopic point conditions, thereby maintaining comprehensive detection coverage while improving recognition accuracy by eliminating false positive points.
3Reliability
If multiple detection points are required to satisfy stereoscopic point condition, then reliability of excluding space floating objects is improved, but complexity of determination increases
Solution Approach 1:
The patent segments the determination process into distinct functional units: a stereoscopic point determination unit that evaluates individual points against predefined conditions, and an exclusion unit that removes non-conforming points. This segmentation allows the system to maintain high exclusion accuracy through multiple condition checks while managing complexity through modular architecture and standardized determination criteria.
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
Effectively prevents the use of detection points from space floating objects in object recognition, improving accuracy by excluding randomly distributed points and retaining points from actual objects like vehicles or road surfaces.
Implementation Method 1
An object recognition device recognizes an object by using a laser radar or the like
Data Source
AI summary
An object recognition device includes a detection point acquisition unit that acquires detection points in a plurality of orientations by using a sensor and an object recognition unit that recognizes an object by using at least some of the detection points. The object recognition device includes an exclusion unit. The exclusion unit excludes the detection point that does not satisfy a stereoscopic point condition, the detection point the detection point number of which is a threshold value or smaller, and the detection point the discontinuity index of which is a threshold value or higher, from the detection points acquired by the detection point acquisition unit. The object recognition unit recognizes the object by using the detection point that is acquired by the detection point number calculation unit and has not been excluded by the exclusion unit.