Non-Obstacle Map Generation via Multi-Directional Depth Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current obstacle detection systems in electronic devices, such as those used in automotive and autonomous vehicle applications, face challenges in efficiently processing images to identify non-obstacle areas, often requiring significant resources and being slow and inaccurate, especially when dealing with complex environments like roads with varying terrain.
Innovation Solution
The system performs both vertical and horizontal processing of depth maps to determine non-obstacle estimations, combining these using reliability maps to generate a non-obstacle map, which identifies regions free of obstacles by analyzing the depth values and terrain, thereby improving accuracy and reducing resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If complex image processing is performed to improve obstacle detection accuracy, then measurement precision is improved, but use of energy and processing time increase
Solution Approach 1:
The patent segments the image processing task into distinct stages: depth map generation, vertical processing, horizontal processing, and combination. Each stage processes only necessary portions of the data with appropriate complexity, avoiding full complex processing across the entire image while maintaining detection accuracy through systematic division of labor among processing modules
Solution Approach 2:
The patent applies partial processing by performing vertical and horizontal analyses only on regions where obstacles are likely to be present, rather than processing the entire depth map with full complexity. This selective approach reduces energy consumption while maintaining detection precision in critical areas
2Measurement precision
If complex image processing is performed to improve obstacle detection accuracy, then measurement precision is improved, but productivity decreases
Solution Approach 1:
By dividing the processing into vertical and horizontal independent streams that can be executed in parallel, the patent achieves both high precision through comprehensive analysis and high productivity through concurrent processing. The segmentation allows the system to process multiple regions simultaneously rather than sequentially
Solution Approach 2:
The patent processes the depth map in both vertical and horizontal dimensions independently, then combines the results. This multi-dimensional approach enables parallel processing execution while maintaining comprehensive obstacle detection accuracy, effectively doubling the processing throughput compared to single-direction analysis
3Productivity
If simple processing is used to reduce energy consumption and increase speed, then use of energy is reduced and productivity is improved, but measurement precision deteriorates
Solution Approach 1:
The patent applies partial processing by performing vertical and horizontal analyses only on regions where obstacles are likely to be present, rather than processing the entire depth map with full complexity. This selective approach reduces energy consumption while maintaining detection precision in critical areas
Solution Approach 2:
The patent processes the depth map in both vertical and horizontal dimensions independently, then combines the results. This multi-dimensional approach enables parallel processing execution while maintaining comprehensive obstacle detection accuracy, effectively doubling the processing throughput compared to single-direction analysis
4Reliability
If complex processing algorithms are used to improve detection reliability, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent segments the detection algorithm into modular components: depth map generation, vertical processing module, horizontal processing module, and combination module. Each module performs a specific function with well-defined inputs and outputs, making the overall complex system manageable through clear separation of concerns and independent optimization of each segment
Solution Approach 2:
The patent processes the depth map in both vertical and horizontal dimensions independently, then combines the results. This multi-dimensional approach enables parallel processing execution while maintaining comprehensive obstacle detection accuracy, effectively doubling the processing throughput compared to single-direction analysis
Data Source
AI summary
A method performed by an electronic device is described. The method includes generating a depth map of a scene external to a vehicle. The method also includes performing first processing in a first direction of a depth map to determine a first non-obstacle estimation of the scene. The method also includes performing second processing in a second direction of the depth map to determine a second non-obstacle estimation of the scene. The method further includes combining the first non-obstacle estimation and the second non-obstacle estimation to determine a non-obstacle map of the scene. The combining includes combining comprises selectively using a first reliability map of the first processing and/or a second reliability map of the second processing The method additionally includes navigating the vehicle using the non-obstacle map.