Vehicle Edge Elimination in Road Line Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for recognizing travel division lines on roads from images captured by on-board cameras face instability in eliminating vehicle edges, leading to erroneous recognition and decreased recognition rates due to inaccurate depth calculation of vehicles.
Innovation Solution
A travel division line recognition apparatus that includes an extracting unit, a calculating unit, and a recognizing unit, which sets suppression areas based on recognized solid objects to reduce the reliability of travel division line candidates within these areas, preventing vehicle edges from being recognized as division lines, even when vehicle depth is not acquired.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If vehicle edges are eliminated using inaccurate depth calculation, then vehicle edge elimination is performed, but the elimination is excessive or insufficient leading to unstable recognition
Solution Approach 1:
The system performs preliminary classification of line candidates into division lines and non-division lines based on image luminance gradients and geometric continuity before final recognition. This preliminary action filters out vehicle edges early in the process, preventing them from interfering with subsequent depth-based elimination steps.
Solution Approach 2:
The system changes the parameter used for vehicle edge elimination from depth-based to reliability-based. By calculating a reliability value for each line candidate based on luminance gradient continuity and geometric properties, the system can stably eliminate vehicle edges without requiring accurate depth information.
2Device complexity
If edges of solid objects are eliminated without considering depth, then processing is simplified, but elimination of vehicle edges is insufficient leading to erroneous recognition
Solution Approach 1:
The system replaces the mechanical depth calculation approach with an image-based reliability assessment approach. By using luminance gradient analysis and geometric continuity checks on the captured image, the system achieves accurate vehicle edge elimination without the complexity of 3D depth reconstruction.
3Measurement precision
If reliability-based selection is used for travel division line candidates, then recognition accuracy is improved, but computational load increases
Solution Approach 1:
The system applies partial reliability calculation only to line candidates that pass initial geometric and luminance filters. By not calculating reliability for all possible line candidates but only for those that meet basic criteria, the system achieves high recognition accuracy while limiting computational power consumption.
Data Source
AI summary
In a travel division line recognition apparatus, an extracting unit extracts a travel division line candidate from an image of a surrounding environment including a road, captured by an on-board camera. A calculating unit calculates a degree of reliability that the extracted travel division line candidate will be the travel division line. A recognizing unit selects the travel division line candidate based on the calculated degree of reliability, and recognizes the travel division line using the selected travel division line candidate. In the calculating unit, a solid object processing unit recognizes solid objects including vehicles, sets a suppression area including a frontal-face suppression area covering a frontal face of the other vehicle and a side-face suppression area covering a side face of the other vehicle, based on the recognized solid objects, and reduces the degree of reliability of the travel division line candidate present within the suppression area.