3D Surround View Stitching for Ghost-Free Object Projection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicle surround view systems often suffer from objects disappearing or multiple display ghosts due to inconsistent camera positions, leading to safety issues during parking and driving.
Innovation Solution
Adaptive consideration of foreground object positions and imaging sources during the stitching process of multiple exterior images to prevent partial disappearance and multiple ghost images, using a system comprising cameras, an in-vehicle processing device with units for object cropping, projection-correction, geometric profile fitting, and image projection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If multiple exterior images are stitched together to generate vehicle surround images, then the field of view is expanded and more areas are covered, but objects may disappear or multiple ghost images appear due to inconsistent camera positions
Solution Approach 1:
A 3D model serves as an intermediary to represent the vehicle body, enabling accurate determination of camera positions and imaging ranges. This mediator allows the system to calculate geometric contours and merge them properly, resolving the contradiction between expanded field of view and accurate object positioning
Solution Approach 2:
The patent transitions from 2D image stitching to 3D spatial reasoning by using a 3D vehicle model and calculating geometric contours in three-dimensional space. This dimensional change enables accurate object position determination while maintaining comprehensive coverage
2Device complexity
If simple image stitching is used, then the processing complexity is low and the system is easy to implement, but objects may partially disappear or multiple ghost images are generated
Solution Approach 1:
The system performs preliminary actions by pre-establishing a 3D vehicle model and pre-calculating geometric contours before actual image stitching. This preparation work, though adding some complexity, enables reliable object position determination and eliminates ghost images during the stitching process
Solution Approach 2:
The patent segments the image processing into distinct functional units: object cropping unit, projection-correction unit, geometric profile fitting unit, and image projection unit. This segmentation makes the complex processing manageable while ensuring each unit performs its function reliably to prevent object disappearance and ghost image generation
Data Source
Figure 1
Figure 2~4
Figure 5
AI summary
A processing method for vehicle surround view, a vehicle surround view system and an in-vehicle processing device are provided. The processing method for vehicle surround view includes the following steps: obtaining a first exterior image and a second exterior image; recognizing a first interest object in the first exterior image and a second interest object in the second exterior image; fitting the first interest object to a first geometric contour and fitting the second interest object to a second geometric contour; applying the first geometric contour and the second geometric contour on a 3D model, to obtain a ground point, a first contour position and a second contour position; obtaining a merged contour position according to the ground point; and projecting the first interest object or the second interest object at the merged contour position on a vehicle surround image.