Dynamic Edge Threshold for Low-Contrast White Line Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional white line recognition processes in lane control systems face challenges in accurately extracting edges from low-contrast images due to fixed edge thresholds, which are affected by internal noise variations in on-vehicle cameras, leading to erroneous edge extraction.
Innovation Solution
An image processing apparatus with light-shielded and non-light-shielded solid-state image acquisition elements, where the edge threshold is dynamically set based on noise variations estimated from light-shielded pixels, reducing the probability of erroneous edge extraction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a fixed edge threshold is used in white line recognition, then the device complexity is reduced and ease of operation is improved, but the reliability deteriorates due to erroneous edge extraction when internal noise exceeds the threshold
Solution Approach 1:
The edge threshold is changed from a fixed value to a dynamically adjustable value that adapts to changing internal noise conditions. The threshold is automatically updated based on real-time noise level detection, allowing the system to maintain high reliability across varying operating conditions without requiring manual intervention.
Solution Approach 2:
A feedback mechanism is introduced where the system continuously monitors internal noise levels and uses this information to adjust the edge threshold. The noise detection unit provides feedback about current noise conditions, which is then used by the threshold determination unit to set appropriate threshold values, creating a closed-loop control system that improves reliability.
2Measurement precision
If a small edge threshold is used to detect low-contrast edges, then the measurement precision is improved, but the reliability deteriorates due to increased erroneous edge extraction from internal noise
Solution Approach 1:
The system dynamically changes the edge threshold parameter based on internal noise conditions. When internal noise levels are low, a smaller threshold is used to detect low-contrast edges with high precision. When internal noise levels increase, the threshold is automatically increased to prevent erroneous detections, thus maintaining both precision and reliability across different operating conditions.
Solution Approach 2:
The edge threshold transitions from a static fixed value to a dynamic value that adapts to changing noise conditions. This allows the system to optimize the threshold for current operating conditions, achieving high measurement precision for low-contrast edges when noise is low, while preventing errors when noise increases.
3Reliability
If a large edge threshold is used to avoid erroneous edge extraction, then the reliability is improved, but the measurement precision deteriorates due to inability to detect low-contrast edges
Solution Approach 1:
The edge threshold parameter is dynamically adjusted based on internal noise levels. When noise is low, a smaller threshold enables detection of low-contrast edges with high precision. When noise increases, the threshold is automatically increased to maintain reliability by preventing erroneous detections. This dynamic parameter adjustment resolves the trade-off between precision and reliability.
Solution Approach 2:
The system employs a dynamic threshold that adapts to changing noise conditions rather than using a fixed large threshold. This allows the system to achieve high reliability when needed while maintaining the ability to detect low-contrast edges when noise levels permit, optimizing both reliability and precision based on real-time conditions.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The apparatus effectively recognizes objects on low-contrast images by minimizing edge extraction errors and adapting to dynamic noise conditions, ensuring accurate white line detection in varying imaging conditions.
Implementation Method 1
a light-shielded region where a plurality of light-shielded solid-state image acquisition elements are arrayed as light-shielded pixels
Implementation Method 2
Such an imaging device is adapted to photoelectrically convert an optical subject image, which is imaged via a lens, into electric charges using a plurality of solid-state image acquisition elements
Data Source
AI summary
An image processing apparatus communicates with an image acquisition apparatus provided with an image acquisition region comprising light-shielded pixels and effective pixels. Data of an image are acquired based on output signals from the effective pixels. An edge of an object is extracted in the acquired image data using a preset edge threshold, and the object is recognized based on the extracted edge. Output signals are acquired from the light-shielded pixels and a degree of variations in noise contained in the output signals from the effective pixels is estimated based on the output signals acquired. The edge threshold is set based on the degree of variations in noise which is estimated, such that the noise having a level which exceeds the edge threshold occurs at a probability lower than a preset value.