Under-Vehicle View Rendering Using Temporal Image Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle surround view systems lack coverage of areas not within the field of view of external cameras, such as the under-vehicle region, and are hindered by camera failures, necessitating an improved technique for sensor fusion and perceptually enhanced surround view rendering.
Innovation Solution
The technique involves obtaining and storing images from a set of cameras mounted around a vehicle, determining motion data based on the vehicle's location change, and using this data to render a view under the vehicle by blending relevant images captured at previous times, effectively utilizing temporal mapping to provide coverage of obscured regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If multiple external cameras are used to provide surround views, then the field of view coverage is improved, but the device complexity and cost increase
Solution Approach 1:
The system captures and stores images at multiple predetermined locations before the vehicle reaches the target position. By pre-capturing images at locations where the under-vehicle region will be visible from future camera positions, the system avoids the need for additional cameras while ensuring coverage of areas currently obscured by the vehicle body.
Solution Approach 2:
The system transitions from spatial redundancy (adding more cameras) to temporal redundancy (using images captured at different times). By utilizing the time dimension and storing images captured at previous locations, the system can reconstruct views of regions that are currently blocked, effectively adding a temporal dimension to the surround view system.
2Area of stationary object
If more cameras are deployed to cover all areas including under-vehicle regions, then the visibility coverage is improved, but the reliability decreases due to higher failure probability
Solution Approach 1:
Instead of using additional physical cameras to capture images from multiple positions, the system creates temporal copies of images captured at previous locations. By storing and reusing images from when the vehicle was at different positions, the system reconstructs views of currently obscured regions without requiring redundant camera hardware, thus maintaining reliability while improving coverage.
3Area of stationary object
If images are captured and stored from multiple locations over time, then the under-vehicle view coverage is improved, but the memory requirements and data processing complexity increase
Solution Approach 1:
The system applies different processing and storage strategies to different regions of the image data. Rather than uniformly storing all images from all cameras at all times, the system identifies and prioritizes storage of images that contain relevant under-vehicle region information based on vehicle position and camera orientation, reducing overall memory requirements while maintaining coverage.
Data Source
AI summary
A technique for rendering an under-vehicle view including obtaining a first location of a vehicle, the vehicle having a set of cameras disposed about the vehicle, capturing a set of images; storing images of the set of images in a memory, wherein the images are associated with a time the images were captured, moving the vehicle to a second location, obtaining the second location of the vehicle, determining an amount of time for moving the vehicle from the first location to the second location, generating a set of motion data, the motion data indicating a relationship between the second location of the vehicle and the first location of the vehicle, obtaining one or more stored images from the memory based on the determined amount of time, rendering a view under the vehicle based on the one or more stored images and set of motion data, and outputting the rendered view.