Distance Estimation Device Using SLAM and Aberration Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional distance estimation devices, such as those using SLAM and aberration mapping methods, require significant processing time to estimate distances of target objects over a wide range, limiting their efficiency and accuracy.
Innovation Solution
A distance estimation device that combines multiple estimation methods, including SLAM and aberration mapping, using a monocular camera, where the SLAM processor estimates distances through triangulation and the aberration mapping processor uses a deep neural network to analyze lens aberration, with a merge unit combining the results to enhance reliability and reduce processing time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If SLAM method is used for distance estimation, then measurement precision is improved, but processing time increases
Solution Approach 1:
The patent divides the image into multiple regions (first region and second region) and applies different processing methods to each region. The first region is processed using SLAM method for high precision, while the second region uses a different approach, thereby reducing overall processing time while maintaining accuracy where needed.
Solution Approach 2:
Different processing qualities are applied to different regions of the image. The first region receives full SLAM processing for maximum precision, while the second region receives simplified processing, optimizing the balance between accuracy and processing speed for different areas.
2Loss of time
If aberration mapping method is used for distance estimation, then processing time is reduced, but measurement precision deteriorates
Solution Approach 1:
The image is segmented into regions where aberration mapping is applied to the first region for fast processing, while the second region uses alternative processing. This segmentation allows the system to benefit from the speed of aberration mapping while maintaining overall accuracy through complementary methods.
3Reliability
If multiple estimation methods are combined, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent combines SLAM method and aberration mapping method in a unified processing system. By merging these two different estimation approaches, the system achieves improved reliability through multiple verification paths while managing complexity through integrated architecture.
Solution Approach 2:
The processing system is designed to perform multiple functions: it can execute SLAM processing, aberration mapping, and region-based selective processing within a single unified device, reducing the need for separate specialized systems and managing overall complexity.
4Adaptability or versatility
If distance estimation is performed over wide area, then adaptability is improved, but processing time increases
Solution Approach 1:
The wide area is divided into multiple regions with different processing priorities. By segmenting the coverage area and applying differentiated processing strategies to each segment, the system maintains adaptability across the entire wide area while reducing total processing time through selective optimization.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach allows for accurate and efficient distance estimation over a wide area by leveraging the strengths of multiple methods, reducing processing time and improving reliability, particularly near image edges and in areas where single methods may fail.
Implementation Method 1
the SLAM processor estimates distances through triangulation
Implementation Method 2
the aberration mapping processor uses a deep neural network to analyze lens aberration
Data Source
AI summary
According to one embodiment, a distance estimation device comprises a first distance estimation unit based on a first estimation method, and a second distance estimation unit based on a second estimation method different from the first estimation method. The second distance estimation unit is configured to change a part of the second estimation method according to an output of the first distance estimation unit.