Multi-Baseline Stereo Vision Depth Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Stereo vision systems with a single baseline restrict the viewable range and accuracy of depth information, leading to significant errors in estimating depth at longer distances.
Innovation Solution
A method and system using at least three image capturing devices with different baseline lengths to generate multiple depth maps, with an image processing device determining the estimated region for each pixel and integrating depth information from overlapping regions to create a more accurate and extensive depth map.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single baseline is used between two lenses in stereo vision, then the system structure is simple, but the viewable range and accuracy of depth information are restricted
Solution Approach 1:
The patent divides the depth estimation task into multiple segments by using multiple device groups with different baselines. Each device group (e.g., first, second, third device groups with baselines B1, B2, B3) estimates depth for specific regions, and these segmented estimates are integrated to form a complete depth map with extended viewable range and maintained accuracy
Solution Approach 2:
The patent transitions from a single baseline (one-dimensional constraint) to multiple baselines (adding another dimension of variation). By introducing multiple baseline lengths through different device groups arranged in arrays, the system gains additional degrees of freedom to estimate depth accurately across extended ranges
2Reliability
If multiple device groups with different baseline lengths are used, then the viewable range and accuracy of depth estimation are increased, but the device complexity increases
Solution Approach 1:
Multiple device groups perform universal depth estimation functions but with different baseline configurations. Each device group can estimate depth for its corresponding region, and through integration, they collectively provide reliable depth information across the entire extended viewable range, making the system multi-functional in terms of coverage
Solution Approach 2:
The patent merges depth information from multiple device groups with different baselines into a single integrated depth map. By combining the depth estimates from first, second, third and subsequent device groups, the system achieves extended reliable range while managing device complexity through coordinated integration
Data Source
AI summary
A method and a system including at least three image capturing devices for generating depth information are proposed. Multiple depth maps associated with a specific scene are obtained, where each of the depth maps corresponds to a different group of the image capturing devices and a different estimated region of the specific scene. For each pixel corresponding to the specific scene, whether the pixel is within a joint overlapping region of its estimated region is determined. If no, the depth information of the pixel is set according to its depth value in the depth map corresponding to a non-joint overlapping region of its estimated region. If yes, the depth information of the pixel is set according to its depth values in the depth maps corresponding to the joint overlapping region within its estimated region. An integrated depth map is generated by using the depth information of all the pixels.