Calibration Board Corner Detection Under LED Blob Interference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge of accurate corner detection is hindered in unified calibration between a dynamic vision sensor (DVS) and a camera due to the interference of light blobs generated by LEDs on the chessboard, causing misalignment and detection failures.
Innovation Solution
A method involving image binarization and expansion/erosion of areas to separate chessboard squares, followed by calculating middle points between adjacent squares as corners, to accurately detect chessboard corners in camera images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If LEDs are attached at the corners of the chessboard to generate light spots for DVS detection, then the DVS can capture intensity changes and create asynchronous pixels for corner detection, but the light blobs interfere with the camera image and cause inaccurate corner detection
Solution Approach 1:
The patent segments the image processing into distinct stages: first binarizing the image to separate chessboard squares from light blobs, then expanding specific color areas to isolate squares, and finally detecting contours to identify corners. This segmentation allows the system to handle the interference from light blobs by processing different elements separately rather than simultaneously.
Solution Approach 2:
The patent extracts the chessboard square regions from the interfering light blobs through selective area expansion. By expanding only the areas in colors opposite to the blobs (e.g., expanding white areas when blobs are black), the method isolates the chessboard squares and excludes the light blob interference from corner detection.
2Measurement precision
If conventional corner detection algorithms are used on camera images with LED light spots, then the processing is simple and fast, but the position detection accuracy deteriorates due to light blob interference
Solution Approach 1:
The patent performs preliminary actions before corner detection by first binarizing the image and then expanding areas of specific colors to separate the chessboard squares from light blobs. This preliminary processing creates a cleaned image where squares are isolated, enabling accurate corner detection in subsequent steps without being affected by light blobs.
Solution Approach 2:
The patent introduces an intermediary processing step between raw image capture and corner detection. The area expansion operation acts as a mediator that transforms the original image with light blob interference into an intermediate representation where chessboard squares are clearly separated, facilitating accurate corner detection in the final step.
Data Source
AI summary
A chessboard corner detection method on a camera image of the DVS-camera unified calibration board is provided. The method detects the multiple corners of the chessboard in the camera image by expanding the areas in color opposite to the binarized blob to eliminate the blob and separates the squares in the image, wherein the outer edge of the chessboard with the same color as the binarized spots needs to be filled with the opposite color in advance. Each corner can be marked then at the middle point of the line connecting the separated adjacent squares.