Back to results
US 11,900,529 B2Granted
Image processing apparatus and method for generation of a three-dimensional model used for generating a virtual viewpoint image
AssigneeCanon Kabushiki Kaisha
InventorMitsuru Maeda
Life of this patent
Estimating the term…
Abstract
An image processing apparatus includes an acquisition unit configured to acquire a three-dimensional shape data of an object based on images captured by a plurality of cameras, a generation unit configured to generate information based on a relationship between the three-dimensional shape data acquired by the acquisition unit and positions of the plurality of cameras, and a correction unit configured to correct the three-dimensional shape data based on the information generated by the generation unit.
Claims13
An image processing apparatus comprising:
- one or more memories storing instructions;
- and
- one or more processors executing the instructions to:
- obtain three-dimensional shape data which represents a three-dimensional shape of an object based on images captured in a plurality of directions and which includes a plurality of elements;
- determine whether a target element included in the plurality of elements of the obtained three-dimensional shape data is surrounded by other elements included in the plurality of elements of the obtained three-dimensional shape data;
- generate three-dimensional shape data based on the determination;
- and
- generate information for specifying which camera captures a region corresponding to an element included in the generated three-dimensional shape data,
- whether the target element included in the plurality of elements of the obtained three-dimensional shape data is surrounded by other elements included in the plurality of elements of the obtained three-dimensional shape data is determined by determining whether the target element included in the plurality of elements of the obtained three-dimensional shape data is an element to which all of the positions adjacent are occupied by other elements included in the plurality of elements of the obtained three-dimensional shape data,
- in a case where it is determined that all of the positions adjacent to the target element are occupied by other elements included in the plurality of elements of the obtained three-dimensional shape data, the three-dimensional shape data which represents the three-dimensional shape of the object and which does not include the target element is generated,
- wherein the number of all of positions is 26.
8 more elements
An image processing method comprising:
- obtaining three-dimensional shape data which represents a three-dimensional shape of an object based on images captured in a plurality of directions and which includes a plurality of elements;
- determining whether a target element included in the plurality of elements of the obtained three-dimensional shape data is surrounded by other elements included in the plurality of elements of the obtained three-dimensional shape data;
- generating three-dimensional shape data based on the determination;
- and
- generating information for specifying which camera captures a region corresponding to an element included in the generated three-dimensional shape data,
- whether the target element included in the plurality of elements of the obtained three-dimensional shape data is surrounded by other elements included in the plurality of elements of the obtained three-dimensional shape data is determined by determining whether the target element included in the plurality of elements of the obtained three-dimensional shape data is an element to which all of the positions adjacent are occupied by other elements included in the plurality of elements of the obtained three-dimensional shape data,
- in a case where it is determined that all of the positions adjacent to the target element are occupied by other elements included in the plurality of elements of the obtained three-dimensional shape data, the three-dimensional shape data which represents the three-dimensional shape of the object and which does not include the target element is generated,
- wherein the number of all of positions is 26.
5 more elements
A non-transitory computer readable storage medium storing a program for causing a computer to execute an image processing method, the image processing method comprising:
- obtaining three-dimensional shape data which represents a three-dimensional shape of an object based on images captured in a plurality of directions and which includes a plurality of elements;
- determining whether a target element included in the plurality of elements of the obtained three-dimensional shape data is surrounded by other elements included in the plurality of elements of the obtained three-dimensional shape data;
- generating three-dimensional shape data based on the determination;
- and
- generating information for specifying which camera captures a region corresponding to an element included in the generated three-dimensional shape data,
- whether the target element included in the plurality of elements of the obtained three-dimensional shape data is surrounded by other elements included in the plurality of elements of the obtained three-dimensional shape data is determined by determining whether the target element included in the plurality of elements of the obtained three-dimensional shape data is an element to which all of the positions adjacent are occupied by other elements included in the plurality of elements of the obtained three-dimensional shape data,
- in a case where it is determined that all of the positions adjacent to the target element are occupied by other elements included in the plurality of elements of the obtained three-dimensional shape data, the three-dimensional shape data which represents the three-dimensional shape of the object and which does not include the target element is generated,
- wherein the number of all of positions is 26.
5 more elements
Dependencies are inferred from the claim text.