Surround View Image Distortion Correction Using Map Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for generating an aerial perspective view of a vehicle's surroundings are limited in eliminating distortion, combining individual images, and providing intuitive displays, failing to effectively represent relevant driving information such as obstacles, road markings, and parking zones in a manner that aligns with human visual perception.
Innovation Solution
A method and apparatus that combine map information with vehicle position and orientation data, using image processing and digital maps to generate processed image data, which includes symbols for classified objects, allowing for intuitive visualization of the vehicle's surroundings, including distance grids and highlighting of obstacles, and enabling the display of additional information like parking fees and no-parking zones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If distortion is eliminated and perspective is changed to create an aerial view, then the display becomes more intuitive and easier to understand, but the relative relationship to the real world is lost and distance perception becomes inaccurate
Solution Approach 1:
The patent introduces an intermediary reference system (grid overlay, distance markers, and position indicators) that mediates between the transformed aerial view and the real world. These intermediaries restore distance and position information without compromising the intuitive aerial perspective, allowing drivers to perceive both the simplified view and accurate spatial relationships simultaneously.
2Adaptability or versatility
If only basic image combining and distortion elimination is performed, then the system remains simple, but additional relevant information such as parking zones, obstacles, and distance data cannot be displayed
Solution Approach 1:
The patent merges multiple information sources (camera images, digital map data, obstacle detection data, and position information) into a single integrated aerial view display. By combining these diverse data types and overlaying them on the unified aerial perspective, the system provides comprehensive information without requiring separate display systems, thus managing complexity through integration rather than multiplication.
3Loss of information
If cameras capture complete surround field images, then all objects are visible, but distortion occurs and images become misleading when converted to aerial perspective
Solution Approach 1:
The patent applies different processing qualities to different regions of the image. Objects and regions closer to the vehicle are processed with higher fidelity and less distortion, while distant regions maintain the aerial perspective transformation. This local differentiation allows the display to maintain visual accuracy where it matters most (near-field objects) while preserving the overall aerial view structure.
Data Source
AI summary
A method for determining processed image data about a surround field of a vehicle includes a step of combining a map information item with a position and an orientation of the vehicle and with an image of the surround field acquired by a surround-field monitoring device of the vehicle, in order to obtain a position-specific image of the surround field. In addition, the method includes a step of processing the position-specific image so as to include at least one symbol that is assigned to a classified object in the position-specific image, in order to determine the processed image data.