Polyline Construction from Line Segments for Localization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional computer vision systems face challenges in constructing coherent models of detected objects from broken line segments, which can lead to increased processing time and reduced localization accuracy in applications like autonomous driving, due to the segmented representation of continuous edges.

Innovation Solution

A method is introduced to construct a polyline representation from line segments by selecting candidate segments and merging neighboring segments based on proximity and distance criteria, thereby forming continuous edges for improved edge modeling and localization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If broken line segments are used to represent continuous edges, then object detection can be performed, but localization accuracy deteriorates and processing time increases

Engineering Contradiction:
Improvelocalization accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent merges multiple broken line segments into a single continuous polyline representation by identifying spatial and angular relationships between segments. This combining process reduces the number of discrete objects to process, thereby decreasing processing time while improving localization accuracy through a unified edge representation.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent segments the polyline representation into individual line segments for detection, then reconstructs them into a continuous polyline. This segmentation approach allows the system to work with manageable discrete elements while achieving continuous edge representation, resolving the contradiction between detectability and accuracy.

Inventive Principle:
Principle #1Segmentation

2Difficulty of detecting and measuring

If broken line segments are used to represent continuous edges, then edge detection can be performed, but the representation coherence deteriorates

Engineering Contradiction:
Improveedge detection capabilityVSAvoidrepresentation coherence
Core Design Contradiction:
Difficulty of detecting and measuringVSStability of the object's composition

Solution Approach 1:

The patent combines multiple broken line segments into a unified polyline structure that maintains spatial relationships and angular continuity. This merging preserves the detectability of individual segments while creating a coherent continuous representation, thereby improving representation coherence without losing edge detection capability.

Inventive Principle:
Principle #5Merging (Combining)

3Reliability

If multiple broken line segments are processed individually, then detection completeness is maintained, but processing complexity increases

Engineering Contradiction:
Improvedetection completenessVSAvoidprocessing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent merges multiple line segments into a single polyline object that retains information about all constituent segments. This approach maintains detection completeness by preserving all segment data while reducing processing complexity through unified object management, eliminating the need to process each segment independently.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3594852B1Method, apparatus, and system for constructing a polyline from line segments
Publication Date: 2023.10.25 HERE GLOBAL BV
  • EP3594852B1 patent drawingFigure 1
  • EP3594852B1 patent drawingFigure 2
  • EP3594852B1 patent drawingFigure 3A

AI summary

An approach is provided for generating a polyline from line segments (e.g., line segments representing objects detected by a computer vision system). The approach involves selecting a line segment from a plurality of line segments. The approach also involves determining a neighboring line segment from among the plurality of line segments. The determined neighboring line segment has a closest distance to the line segment from among the plurality of line segments. The approach further involves merging the line segment and the neighboring line segment into a polyline based on determining that the closest distance is a mutual closest distance between line segment and the neighboring line segment.