Vision System Line Detection Using Gradient Field Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional machine vision systems face challenges in accurately identifying and characterizing multiple lines in images, especially when lines are closely spaced and have similar orientation and polarity, leading to increased processing overhead and decreased reliability.
Innovation Solution
A system and method that computes gradient components, projects the gradient field over image subregions, detects edge points, fits model lines to consistent edge points, and uses RANSAC-based techniques to iteratively refine line fitting, allowing for efficient and accurate identification of multiple lines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional edge point detection tools are used to find lines, then the process can identify edge points with contrast difference, but the processing overhead increases and reliability decreases when multiple lines are present
Solution Approach 1:
The patent merges the edge point detection and line fitting operations into a unified process. Instead of using independent tools that first detect edge points and then separately fit lines (which causes increased processing overhead), the invention integrates these operations to simultaneously identify multiple lines and their corresponding edge points, thereby reducing processing overhead and improving reliability.
Solution Approach 2:
The patent segments the image into multiple regions and processes line detection independently in each region. This segmentation allows the system to handle multiple lines without interference, improving reliability by ensuring that each line is detected accurately even when lines are closely spaced, while the segmented processing approach manages computational load efficiently.
2Reliability
If traditional line finding tools are used, then a single line can be identified, but the ability to accurately identify multiple closely spaced lines with similar orientation and polarity is limited
Solution Approach 1:
The patent divides the image into multiple regions and applies line detection independently to each region. This segmentation enables the system to accurately identify multiple closely spaced lines with similar orientation and polarity, as each line is processed separately without interference from other lines, thereby improving reliability and adaptability.
Solution Approach 2:
The patent applies different detection parameters and thresholds to different regions of the image based on local characteristics. This allows the system to adapt to varying line densities and orientations in different areas, improving the ability to accurately identify multiple closely spaced lines while maintaining computational efficiency.
3Ease of manufacture
If independent edge point detection and line fitting tools are used, then each tool can perform its specific function, but the processing overhead increases
Solution Approach 1:
The patent combines edge point detection and line fitting into a single integrated process. Instead of using separate independent tools that operate sequentially (increasing processing overhead), the invention merges these functions to perform both operations simultaneously, reducing processing overhead while maintaining the functional capabilities of both edge detection and line fitting.
Data Source
AI summary
This invention provides a system and method for finding multiple line features in an image. Two related steps are used to identify line features. First, the process computes x and y-components of the gradient field at each image location, projects the gradient field over a plurality subregions, and detects a plurality of gradient extrema, yielding a plurality of edge points with position and gradient. Next, the process iteratively chooses two edge points, fits a model line to them, and if edge point gradients are consistent with the model, computes the full set of inlier points whose position and gradient are consistent with that model. The candidate line with greatest inlier count is retained and the set of remaining outlier points is derived. The process then repeatedly applies the line fitting operation on this and subsequent outlier sets to find a plurality of line results. The process can be exhaustive RANSAC-based.