Camera Exposure Segmentation for Display Board and Electronic Sign Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image capture systems face challenges in accurately recognizing information from both display boards and electronic display apparatuses using a single camera, as exposure time adjustments to reduce blurring can lead to flicker, decreasing the accuracy of sign recognition.
Innovation Solution
An image generation apparatus that captures images in specific states to generate suitable frames for display board and electronic sign recognition, using a single camera to set exposure times and gains based on vehicle speed and lighting conditions, and combines multiple images to correct positional misalignment and reduce blurring and flicker.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If exposure time is shortened to reduce blurring, then blurring is reduced, but flicker occurs when electronic display apparatus is captured
Solution Approach 1:
The patent segments the image capture process into multiple imaging operations with different exposure times. One image is captured with a first exposure time optimized for display board recognition, while another image is captured with a second exposure time optimized for electronic display apparatus recognition. This segmentation allows each image to be optimized for its specific purpose without compromising the other.
Solution Approach 2:
The patent dynamically adjusts exposure time based on the target object being captured. The system selects between at least two different exposure times depending on whether the target is a display board or an electronic display apparatus. This dynamic adjustment enables optimal image quality for different recognition tasks using a single camera.
2Reliability
If exposure time is extended to capture electronic display apparatus, then flicker is reduced, but blurring increases
Solution Approach 1:
The patent separates the capture of display boards and electronic display apparatus into distinct imaging operations. For electronic display apparatus, a longer exposure time is used to eliminate flicker, while for display boards, a shorter exposure time maintains sharpness. This segmentation resolves the contradiction by applying different exposure settings to different targets.
Solution Approach 2:
The patent changes the exposure time parameter based on the recognition target. When capturing electronic display apparatus, the exposure time is extended to prevent flicker. When capturing display boards, the exposure time is kept short to maintain image sharpness. This parameter adaptation allows optimal recognition accuracy for different object types.
3Device complexity
If a single camera is used for both display board and electronic display recognition, then device complexity is reduced, but recognition accuracy for both targets decreases
Solution Approach 1:
The patent makes a single camera dynamic by implementing multiple imaging operations with varying exposure times. The camera switches between at least two different exposure time settings depending on the recognition target. This dynamic capability allows one camera to perform the work of multiple cameras, maintaining simplicity while achieving high recognition accuracy for both display boards and electronic displays.
Solution Approach 2:
The patent enables a single camera to serve multiple functions by implementing different imaging conditions for different targets. The same camera hardware is used for both display board recognition and electronic display apparatus recognition, with the software controlling exposure time adjustments. This multi-functionality reduces device complexity while maintaining high measurement precision for both applications.
Data Source
AI summary
In an image generation apparatus, an image of a periphery of an own vehicle is captured using an imaging operation of a camera mounted in the own vehicle in a first state that is suitable for capturing an image for recognizing information illustrated on a display board, at a predetermined first timing, and a first captured image is generated from the image captured in the first state. An image of the periphery of the own vehicle is captured using an imaging operation of the camera in a second state that is suitable for capturing an image for recognizing information displayed by light emitted from an electronic display apparatus, at a predetermined second timing, and a second captured image is generated from the image captured in the second state. A process using the first captured image and the second captured image is performed.