Back to results
US 8,712,145 B2Granted
Depth estimation apparatus and method
AssigneeSamsung Electronics Co., Ltd.
InventorsAron Baik, Yong Ju Jung, Ji Won Kim
Life of this patent
Estimating the term…
Abstract
A depth estimation apparatus is provided. The depth estimation apparatus may estimate a depth value of at least one pixel composing an input video based on feature information about at least one feature of the input video, a position of the at least one pixel, and a depth relationship among the at least one pixel and neighboring pixels.
Claims19
A depth estimation apparatus, comprising:
- a processor;
- a feature information extraction unit to extract feature information about at least one feature of an input video;
- and
- a depth estimation unit to estimate a depth value of at least one pixel of the input video,
- wherein the depth estimation unit comprises:
- a first depth determination unit to determine a first depth value of the at least one pixel based on the feature information;
- a second depth determination unit to determine a second depth value of the at least one pixel based on a position of the at least one pixel;
- and
- a depth selection unit to select the estimated depth value from at least one predetermined candidate depth value, based on the first depth value, the second depth value, and a third depth value of a neighboring pixel neighboring the at least one pixel, and
- wherein at least one of the feature information extraction unit and the depth estimation unit use the processor to perform the extracting or estimating.
7 more elements
A depth estimation apparatus, comprising:
- a processor;
- a feature information extraction unit to extract feature information about at least one feature of an input video;
- a depth estimation unit to distinguish at least one pixel of the input video according to at least one block of the input video with plural pixels, and estimate a depth value of the at least one block;
- and
- an up-scaling unit to up-scale a depth map, which stores the estimated depth value, for the at least one pixel,
- wherein the depth estimation unit comprises:
- a first depth determination unit to determine a first depth value of the at least one block based on the feature information;
- a second depth determination unit to determine a second depth value of the at least one block based on a position of the at least one block;
- and
- a depth selection unit to select the estimated depth value from at least one predetermined candidate depth value, based on the first depth value, the second depth value, and a third depth value of a neighboring block neighboring the at least one block, and
- wherein at least one of the feature information extraction unit, the depth estimation unit, and the up-scaling unit use the processor to perform the extracting, estimating, or up-scaling.
8 more elements
A depth estimation method, comprising:
- extracting feature information about at least one feature of an input video;
- and
- estimating a depth value of at least one pixel of the input video,
- wherein the estimating comprises:
- determining a first depth value of the at least one pixel based on the feature information;
- determining a second depth value of the at least one pixel based on the position of the at least one pixel;
- and
- selecting the estimated depth value of the at least one pixel from at least one predetermined candidate depth value, based on the first depth value, the second depth value, and a third depth value of a neighboring pixel neighboring the at least one pixel.
5 more elements
A non-transitory computer-readable recording medium comprising computer readable code to control at least one processing device to implement a depth estimation method, the method comprising:
- extracting feature information about at least one feature of an input video;
- and
- estimating a depth value of at least one pixel of the input video,
- wherein the estimating comprises:
- determining a first depth value of the at least one pixel based on the feature information;
- determining a second depth value of the at least one pixel based on the position of the at least one pixel;
- and
- selecting the estimated depth value of the at least one pixel from at least one predetermined candidate depth value, based on the first depth value, the second depth value, and a third depth value of a neighboring pixel neighboring the at least one pixel.
5 more elements
Dependencies are inferred from the claim text.