Surround-View Object Mapping Under Lens Distortion Uncertainty
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing systems for vehicles struggle to accurately detect and avoid obstacles when camera lenses experience distortion due to temperature changes, leading to unreliable object position data.
Innovation Solution
An image processing apparatus and method that generate a two-dimensional map or surround-view image by designating objects with low position reliability as enlarged display objects, with an enlarged region extending around these objects, to ensure safe vehicle navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If lens image height characteristics are used for object position detection, then measurement precision is improved under normal temperature conditions, but reliability deteriorates when temperature changes cause lens distortion
Solution Approach 1:
The system performs preliminary actions by detecting temperature changes and identifying objects with low position reliability before navigation decisions are made. By proactively flagging potentially unreliable objects and expanding their display regions, the system prepares for possible position inaccuracies due to lens distortion, allowing the navigation device to make safer routing decisions.
2Device complexity
If all detected objects are treated with equal confidence, then device complexity is reduced, but reliability deteriorates due to lens distortion affecting some objects more than others
Solution Approach 1:
The system applies local quality by differentiating object processing based on individual reliability assessments. Instead of treating all objects uniformly, the system selectively expands display regions only for objects with low position reliability (those affected by lens distortion), while maintaining normal display for reliable objects. This targeted approach improves navigation safety without unnecessarily increasing overall system complexity.
3Reliability
If enlarged display regions are applied to all objects, then reliability of navigation is improved, but loss of information increases due to excessive visual clutter
Solution Approach 1:
The system applies local quality by differentiating object processing based on individual reliability assessments. Instead of treating all objects uniformly, the system selectively expands display regions only for objects with low position reliability (those affected by lens distortion), while maintaining normal display for reliable objects. This targeted approach improves navigation safety without unnecessarily increasing overall system complexity.
Data Source
AI summary
Provided are an apparatus and a method for generating a two-dimensional map or a surround-view image in which an object with low position reliability is set as an enlarged display object. A data processing section configured to receive an image captured by a camera that captures the image of surroundings of a vehicle and generate a two-dimensional map including objects in the surroundings of the vehicle is included. The data processing section generates the two-dimensional map or a surround-view image including an enlarged display object having an enlarged region set thereto, the enlarged region which, in case of an object with low position reliability, extends around the object.


