Vehicle Surround View Image Continuity Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional vehicle circumferential image providing devices experience discontinuous edge lines when combining images from multiple cameras, leading to difficulties for drivers in viewing connected parts, due to positional deviations caused by different camera heights and perspectives.
Innovation Solution
A vehicle circumferential image providing device that includes multiple camera modules, a vehicle speed sensor, a steering angle sensor, and an image processing unit capable of generating overhead images by coordinate conversion, with an edge detecting function and three-dimensional determining function to correct image deviations and highlight three-dimensional objects, ensuring accurate representation and safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If multiple cameras are used to image the vehicle circumference, then the coverage area is improved, but the image continuity at connected parts deteriorates due to positional deviations
Solution Approach 1:
The patent applies parameter changes by adjusting the coordinate conversion parameters based on the detected three-dimensional information of objects. When an object is detected to be three-dimensional (having height), the system modifies the coordinate conversion to compensate for the positional deviations that occur when imaging from different camera heights, thereby maintaining image continuity at connected parts while using multiple cameras for expanded coverage.
2Ease of manufacture
If coordinate conversion is performed using ground surface as reference, then the overhead image generation is simplified, but the edge position accuracy deteriorates for objects at different distances from the ground
Solution Approach 1:
The patent applies preliminary action by detecting the three-dimensional information (height) of objects before performing coordinate conversion. The system uses edge detection and three-dimensional determination functions to identify objects with height prior to the coordinate conversion process, then applies appropriate compensation parameters to maintain edge position accuracy while still using the ground surface as the reference for overhead image generation.
3Area of stationary object
If images from multiple cameras are combined, then the overall image coverage is improved, but the driver's ability to view continuous images deteriorates due to edge line discontinuities
Solution Approach 1:
The patent applies parameter changes by dynamically adjusting the coordinate conversion parameters based on detected three-dimensional object information. When objects with height are detected, the system modifies the conversion parameters to eliminate edge line discontinuities at connected parts, thereby maintaining image coverage from multiple cameras while ensuring continuous, easy-to-view images for the driver.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
In a vehicle circumferential image providing device 1, an image converting unit 53 generates an overhead image 205 from images picked up with plural camera modules 10. An image detecting unit 54 performs edge detection in an overhead image 205. Further, the image detecting unit 54 determines continuity of edge lines connecting between connected parts in the overhead image 205, among the detected edge lines. When the edge lines striding over the connected parts in the overhead image 205 are discontinuous, the image detecting unit 54 sets edge lines at the far side of the own vehicle to match edge lines at the near side of the own vehicle, thereby setting the edge lines continuous at the connected parts.