Scene global depth estimation method for multi-vision angle video image
A technology of video image and depth estimation, which is applied in image communication, image analysis, image data processing, etc., and can solve problems such as unsolved problems
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0114] In this embodiment, for convenience of description, a converging camera system composed of two cameras is taken as an example. Using the internal parameters A of the two cameras i (i∈1, 2) external parameter R i , t i (i ∈ 1, 2) and the view I formed under each camera system 1 with I 2 Do global depth estimation. Take view I 1 as the target view, view I 2 As the reference view, find the view I 1 The steps of the global depth value are as follows Figure 5 Shown:
[0115] Step 1: Compute the two cameras c 1 with c 2 The converging point of the optical axes of , the initial depth value of the scene under the camera coordinates is obtained.
[0116] According to formula (5), the depth value z of the convergence point in the two-camera coordinate system is obtained 1 0 and z 2 0 The linear equation for :
[0117] R 1 [ 0,0 , z 1 0 ] ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 