Rolling-Shutter Scene View Image Generation with Motion-Adjusted Mesh
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advanced driver assistance systems (ADAS) face challenges in generating accurate scene view images due to distortion caused by the rolling shutter mechanism of camera sensors, which results in warped images when the vehicle is in motion.
Innovation Solution
A method and device that utilize a camera sensor to generate a scene view image by obtaining a planar mesh through back-projection of image pixels onto a target plane, adjusting vertices based on the motion of the vehicle, and generating a scene view image from the planar mesh, compensating for distortion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a rolling shutter camera sensor is used to capture images, then the camera can capture images sequentially by scanning scan lines, but the generated scene view image becomes distorted when the vehicle is in motion
Solution Approach 1:
The patent applies preliminary action by obtaining motion information of the vehicle before generating the scene view image. The processor acquires motion information indicating the movement of the vehicle during the scanning process, and uses this information to compensate for distortion in advance when mapping scan lines to the scene view image, thereby preventing geometric distortion rather than correcting it after the fact
Solution Approach 2:
The patent applies parameter changes by modifying the mapping parameters between scan lines and scene view image based on the vehicle's motion state. The processor adjusts the geometric parameters of the scene view image generation process according to the obtained motion information, changing the transformation parameters to account for vehicle movement during image capture
2Manufacturing precision
If the vehicle motion is compensated for during image generation, then the scene view image accuracy is improved, but the processing complexity increases
Solution Approach 1:
The patent introduces an intermediary element - the motion information - that mediates between the vehicle's physical movement and the image generation process. This motion information serves as a bridge, providing the necessary data to adjust the scene view image generation without requiring complex real-time correction mechanisms, thereby simplifying the overall system architecture
Data Source
AI summary
An electronic device includes: a camera sensor, disposed on a body, and configured to generate an image including image data by sequentially scanning scan lines; and memory storing instructions configured to cause a processor to: obtain a default mesh with vertices corresponding to positions of image pixels along a scan line of the camera sensor and back-projected onto a target plane, obtain a planar mesh from the default mesh according to motion of the body, and generate a scene view image from the image data based on the obtained planar mesh.