Machine Vision Carriage Control for Accurate Maintenance Striping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current maintenance striping technologies for roadway lane demarcation markings are inefficient and prone to human error, requiring manual labor, leading to inaccuracies and increased costs, and existing automated systems struggle to accurately detect and align with pre-existing marks under varying conditions.
Innovation Solution
A machine learning network and machine vision-based system that uses convolutional neural networks to detect and align the roadway mark dispensing hardware over pre-existing marks, enabling accurate and efficient application of new markings without manual intervention, even under challenging environmental conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual labor is used for maintenance striping, then ease of operation is maintained, but productivity is low and manufacturing precision is poor
Solution Approach 1:
The patent replaces manual mechanical operations with an automated system comprising an imager, machine learning network, and carriage control apparatus. The system automatically detects pre-existing marks through imaging, processes them via machine learning to determine carriage positioning, and electronically controls carriage movement and marking material dispensing, eliminating manual labor while improving productivity and precision.
Solution Approach 2:
The system enables self-service automation where the carriage control apparatus autonomously performs detection, decision-making, and execution functions. The imager captures mark images, the machine learning network automatically processes images to determine carriage position and marking parameters, and the control apparatus autonomously positions and dispenses marking material without human intervention.
2Measurement precision
If automated systems are used for maintenance striping, then productivity increases, but measurement precision deteriorates under varying conditions
Solution Approach 1:
The machine learning network is trained to recognize and adapt to various environmental parameters including different lighting conditions, mark wear levels, and roadway surface variations. The system changes its detection parameters dynamically based on the input image characteristics, allowing accurate mark detection across diverse environmental conditions while maintaining high measurement precision.
3Manufacturing precision
If automated detection and alignment is implemented, then manufacturing precision improves, but device complexity increases
Solution Approach 1:
The machine learning network serves as an intermediary between the imager and the carriage control apparatus. It processes the raw image data from the imager, extracts relevant features, determines optimal carriage positioning and marking parameters, and transmits control signals to the carriage apparatus. This intermediary layer simplifies the overall control architecture while achieving high manufacturing precision through intelligent image processing and decision-making.
Data Source
AI summary
A control system for positioning a marker over a pre-existing roadway surface mark. The control system has one or more imagers having a field of view for imaging an area of roadway mark surface encompassing the roadway mark and a computer having a machine learning network to process the roadway mark image and position the marker over the pre-existing roadway mark.