Vehicle Contour Detection Using Polygonal Chain Edge Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle detection systems rely on bounding boxes to identify objects, which are inexact and can lead to erroneous triggerings of passive safety elements, especially in pre-crash situations.
Innovation Solution
A method that uses measurement data from environment sensor systems to produce a polygonal chain envelope around detected objects, reduces irrelevant points, and classifies edges to accurately identify the vehicle contour, thereby improving the precision of accident predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a bounding box is used to identify objects, then the processing is simple, but the identification precision is low
Solution Approach 1:
The patent segments the object identification process into multiple stages: first creating a bounding box for rough localization, then extracting contour points from the bounding box region, and finally generating a polygonal chain envelope from these contour points. This segmentation allows the system to maintain processing efficiency while achieving higher identification precision through progressive refinement.
Solution Approach 2:
The patent transitions from two-dimensional bounding box representation to a more precise polygonal chain envelope that closely follows the object's contour. By moving from a simplified geometric approximation to a contour-based representation, the system achieves higher measurement precision while managing complexity through algorithmic processing.
2Measurement precision
If a polygonal chain envelope is used to identify vehicle contour, then the identification precision is improved, but the device complexity increases
Solution Approach 1:
The patent performs preliminary actions by first generating a bounding box to define the region of interest, then extracting contour points within this region before constructing the final polygonal chain envelope. This preliminary structuring of data reduces the complexity of the final envelope generation by pre-organizing the spatial information.
Solution Approach 2:
The patent extracts only the relevant contour points from the bounding box region that are necessary for constructing the polygonal chain envelope. By taking out and focusing only on the essential contour-defining points rather than processing all points within the bounding box, the system reduces computational complexity while maintaining high identification precision.
3Reliability
If all spatial points are processed to identify contour, then the completeness is improved, but the processing time increases
Solution Approach 1:
The patent applies local quality by focusing processing efforts only on the boundary region of the object rather than all spatial points. By identifying and processing only the contour points that define the vehicle's shape, the system achieves complete and accurate contour identification while significantly reducing the number of points that require processing.
Solution Approach 2:
The patent extracts contour points from the set of all spatial points within the bounding box. By taking out only the relevant contour-defining points and excluding interior points, the system maintains complete and accurate contour identification while reducing processing time through selective point processing.
Data Source
AI summary
A method for identifying the contour of a vehicle based on measurement data from an environment sensor system is disclosed. The measurement data includes a set of spatial points of an object detected by the environment sensor system. The method includes: producing an envelope in the form of a polygonal chain around the object based on the set of spatial points; reducing the set of spatial points; removing spatial points from the polygonal chain that are irrelevant to identifying the contour of the vehicle and determining spatial points of the polygonal chain that are relevant to identifying the contour of the vehicle; classifying one or more edges as belonging to a front and a side of the vehicle on the basis of the reduced set of spatial points.