Stereo matching implementation method and apparatus for real-time depth estimation of mobile devices
By employing reverse path synchronous aggregation and expanding thread data slices on mobile devices, the problem of mobile graphics processor memory resource limitations is solved, enabling stereo matching with real-time depth estimation.
CN115345912BActive Publication Date: 2026-07-03TSINGHUA UNIVERSITY
1 Cites 0 Cited by
Patent Information
- Application Number
- CN202210793133.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-05
- Publication Date
- 2026-07-03
- Estimated Expiration
- 2042-07-05
AI Technical Summary
Technical Problem
The limited memory resources of mobile graphics processors result in poor stereo vision matching performance, making real-time depth estimation impossible.
Method used
Cost aggregation is performed using a reverse path synchronization aggregation method, and disparity calculation is performed by expanding the thread data slices, thereby reducing global memory access and thread synchronization overhead.
Benefits of technology
This reduces the latency of stereo matching and improves the real-time performance of depth estimation on mobile devices.
✦ Generated by Eureka AI based on patent content.
Abstract
The application relates to a stereo matching implementation method and device for real-time depth estimation of a mobile device, which comprises the following steps: performing matching cost calculation on a target image pair to obtain a cost matrix corresponding to a main image in the target image pair; based on the cost matrix, adopting a reverse path synchronous aggregation mode to determine the aggregation cost of each pixel in the main image under each disparity; according to the aggregation cost, adopting an expanded thread data slice mode to perform disparity calculation on each pixel in the main image; and performing disparity optimization on each pixel in the main image to obtain a disparity map corresponding to the main image. In the cost fusion calculation, the cost aggregation is simultaneously performed on two paths which are reverse paths of each other, so that the access cost of the global memory is reduced. Meanwhile, in the disparity calculation, the number of concurrent threads is reduced through the expanded thread data slice mode, and then the thread synchronization cost is reduced.
Need to check novelty before this filing date? Find Prior Art