Obstacle Detection Using Histogram Segmentation for Road Surface Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional obstacle detection apparatuses inaccurately detect road features like colored lines, signs, and objects on non-asphalt road surfaces as obstacles due to preset brightness ranges, leading to false positives.
Innovation Solution
An obstacle detection apparatus that includes an obstacle distance detection unit, imaging unit, image transform unit, histogram generation region extraction unit, histogram calculation unit, first running-allowed region detection unit, obstacle region extraction unit, and obstacle position detection unit to enhance accuracy by transforming road surface images and calculating histograms within specific regions, distinguishing between running-allowed and obstacle regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If preset brightness ranges are used to detect obstacles, then detection speed is improved, but detection accuracy deteriorates due to false positives from road features
Solution Approach 1:
The patent divides the road surface into multiple regions with different brightness characteristics. Instead of using a single preset brightness range for the entire road surface, the system segments the detection area and applies region-specific brightness thresholds. This allows the system to maintain fast detection speeds while improving accuracy by adapting to local variations in road surface brightness caused by different materials, markings, and environmental conditions.
2Device complexity
If preset brightness ranges are used for obstacle detection, then device complexity is reduced, but false positive detection increases
Solution Approach 1:
The patent implements dynamic brightness threshold adjustment based on the detected road surface type. The system automatically adapts the brightness range parameters according to the identified road material (asphalt, concrete, gravel, etc.) and environmental conditions. This dynamic adaptation reduces false positives from road features while maintaining relatively simple device architecture, as the complexity is managed through software algorithms rather than additional hardware components.
3Ease of operation
If conventional brightness-based detection is used, then ease of operation is improved, but adaptability to different road surfaces deteriorates
Solution Approach 1:
The patent changes the detection parameters (brightness thresholds, contrast levels) automatically based on the detected road surface characteristics. The system identifies different road types and adjusts the brightness range parameters accordingly, enabling the same detection device to operate effectively on various road surfaces (asphalt, concrete, gravel, dirt) without requiring manual parameter reconfiguration. This maintains ease of operation while significantly improving adaptability.
Data Source
AI summary
A histogram is calculated based on a road surface image of a portion around a vehicle, a running-allowed region in which the vehicle can run is detected based on the histogram, an obstacle region is extracted based on the running-allowed region, and a position of an obstacle in the obstacle region is detected, to further enhance the accuracy of detecting an obstacle around the vehicle as compared with conventional art.