Attached Object Detection via Luminance Dispersion Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional attached object detection apparatuses struggle to accurately determine the presence of objects on a camera lens due to changes in luminance caused by camera gain adjustments, leading to potential misidentification of attached objects.
Innovation Solution
An attached object detection apparatus that divides the captured image into regions, calculates representative luminance values and luminance dispersion, and detects attached regions based on predetermined differences and values, ensuring accurate detection by setting conditions such as minimal differences in luminance and dispersion between frames.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If camera gain is adjusted to adapt to changing lighting conditions, then adaptability is improved, but measurement precision deteriorates due to luminance changes causing misidentification of attached objects
Solution Approach 1:
The captured image is divided into multiple divided regions, and attached object detection is performed independently for each region. This segmentation allows the system to compare luminance characteristics within each small region against its historical data, making the detection robust to global gain adjustments while maintaining precision in identifying local attached objects.
Solution Approach 2:
The system stores historical luminance information and luminance dispersion data for each divided region before attached objects appear or before gain adjustments occur. This preliminary storage of baseline characteristics enables the detector to compare current readings against known good states, allowing accurate detection of attached objects even when overall luminance changes due to gain adjustments.
2Reliability
If luminance threshold is set low to detect attached objects, then detection sensitivity is improved, but reliability deteriorates due to false positives from normal luminance variations
Solution Approach 1:
The system evaluates attached object detection based on local luminance characteristics within each divided region rather than global image properties. By analyzing luminance dispersion and comparing against historical data specific to each region, the detector can reliably identify attached objects based on local anomalies without being triggered by global luminance variations or requiring overly sensitive thresholds.
Solution Approach 2:
The system uses chronological luminance data as feedback to continuously update and compare against current readings. This feedback mechanism allows the detector to distinguish between normal luminance fluctuations (which recur predictably) and actual attached objects (which cause persistent deviations), improving reliability without requiring low thresholds that would cause false positives.
Data Source
AI summary
An attached object detection apparatus includes a setting part, a calculator, and a detector. A setting part sets a plurality of divided regions within a captured image captured by an image capturing apparatus. A calculator calculates, for each of the plurality of divided regions and based on luminance of pixels in the divided region, a representative luminance value and an amount of luminance dispersion. A detector detects, as an attached region that has an attached object, a divided region among the plurality of divided regions that satisfies the following conditions: i) a first difference is equal to or smaller than a first predetermined difference, ii) a second difference is equal to or smaller than a second predetermined difference, and iii) the representative luminance value of the current divided region is equal to or smaller than a first predetermined value.