.png){kind=icon}
.png){kind=icon}
Return
Automatic objects' depth estimation based on integral imaging
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-022-13221-3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A new approach for depth estimation based on integral imaging is proposed. In this method, multiple viewpoint images captured from a three-dimensional scene are used to extract the range information of the scene. These elemental images are captured through an array of lenses over a high-resolution camera or an array of cameras. Then the scene is computationally reconstructed in different depths using integral imaging reconstruction algorithm. Finally, by processing the reconstructed images and finding objects of the scene in these images using a matching technique with speeded-up robust features (SURF), the depth information of the objects will be acquired. Experimental results show that the proposed method has high accuracy and does not have many limitations of standard image processing, including sensitivity to the surface type and size of the objects.
Keywords:
Depth estimation
Image processing
Integral imaging
3D reconstruction
SURF features
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W