Video Bad-Point Detection Using Extreme Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to accurately detect bad points in videos due to dynamic brightness changes in adjacent frames, leading to inaccurate detection of points with incorrect display contents.
Innovation Solution
Perform extreme filtering on sequential frames to create difference images, determine candidate points based on threshold brightness values, and refine using corrosion and expansion processing to identify bad points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If simple brightness comparison between adjacent frames is used, then detection speed is fast, but detection accuracy is low due to dynamic brightness changes
Solution Approach 1:
The patent applies preliminary action by performing extreme filtering on the first frame, second frame, and third frame before calculating difference images. This pre-processing step prepares the image data in advance to highlight potential bad points, enabling accurate detection without requiring complex real-time analysis during the actual detection process.
Solution Approach 2:
The patent segments the detection process into multiple independent steps: extreme filtering on individual frames, calculation of first and second difference images, threshold comparison to identify candidate points, and validation against multiple criteria. This segmentation allows each step to be optimized independently, improving overall accuracy while maintaining manageable complexity.
2Measurement precision
If multiple filtering and difference calculation steps are applied, then detection accuracy is improved, but processing time increases
Solution Approach 1:
The patent implements continuity of useful action by processing three consecutive frames (first, second, and third frames) through extreme filtering and difference calculation in a continuous manner. This approach ensures that no potential bad points are missed due to isolated frame analysis, improving detection accuracy while the efficient algorithm keeps processing time acceptable.
Solution Approach 2:
The patent utilizes parameter changes by applying different extreme filtering operations (maximum filtering and minimum filtering) to different frames and using multiple threshold values (first threshold and second threshold) for validation. These parameter variations enable the system to detect different types of bad points effectively while maintaining processing efficiency through structured computation.
3Reliability
If threshold-based point identification is used, then false positive reduction is improved, but detection sensitivity decreases
Solution Approach 1:
The patent applies feedback by using the first difference image and second difference image to validate candidate points against multiple criteria. Points must satisfy specific brightness difference conditions in both difference images to be confirmed as bad points, providing feedback validation that reduces false positives while maintaining sensitivity through the multi-criteria check.
Data Source
AI summary
Embodiments of the disclosure provide a method for detecting bad points in a video, including: performing extreme filtering respectively on first, second and third frames of images which are sequentially and continuously in the video to obtain first, second and third filtered images, respectively; wherein the extreme filtering is one of maximum filtering and minimum filtering; determining first and second difference images according to the first, second and third filtered images; determining a candidate image according to the first and second difference images; and determining that at least part of points in the second frame of image corresponding to the valid point in the candidate image are bad points. The embodiment of the disclosure also provides a device and a computer-readable medium for detecting bad points in the video.