Apparatus and a method for artificial intelligence
AssigneeNokia Technologies Oy
InventorsEmre Aksu, Miska Hannuksela, Jonne Juhani Mäkinen, Juha-Pekka Hippeläinen
Life of this patent
Estimating the term…
Abstract
The embodiments relate to a method comprising receiving visual data in a file format compatible with ISO base media file format; processing the visual data to detect one or more content elements; storing the detected one or more content elements and information on the used process as a metadata; and including the metadata to the media file in association with the visual data. The embodiments also relate to a technical equipment for implementing the method.
Claims20
A method, comprising:
- receiving a visual data in a container file, wherein the container file is compatible with a container file format;
- processing the visual data by using a plurality of processes to detect one or more content elements;
- storing, the detected one or more content elements and information on the plurality of processes used to detect said one or more content elements, as a metadata;
- indicating dependencies between the plurality of processes by using a first indication and a second indication, wherein the first indication represents an item which requires one or more inputs, and wherein the second indication represents items comprising said one or more inputs;
- and
- including the metadata in the container file associated with the visual data.
An apparatus comprising at least one processor;
- and at least one memory including computer program code;
- the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to perform:
- receive visual data in a container file, wherein the container file is compatible with a container file format;
- process the visual data by means of a plurality of processes to detect one or more content elements;
- store the detected one or more content elements and information on used processes to detect said one or more content elements as a metadata;
- indicate dependencies between various processes, a first and second indication, where the first indication represents an item which requires one or more inputs, and where the second indication represents items comprising said one or more inputs;
- and
- include the metadata to the container file in association with the visual data.
A Computer program product comprises at least one non-transitory computer-readable storage medium having computer executable program code instructions stored therein, the computer executable program code instructions comprising program code instructions configured, upon execution, to:
- receive a visual data in a container file, wherein the container file is compatible with a container file format;
- process the visual data by using a plurality of processes to detect one or more content elements;
- store, the detected one or more content elements and information on the plurality of processes used to detect said one or more content elements, as a metadata;
- indicate dependencies between the plurality of processes by using a first indication and a second indication, wherein the first indication represents an item which requires one or more inputs, and wherein the second indication represents items comprising said one or more inputs;
- and
- include the metadata in the container file associated with the visual data.
Dependencies are inferred from the claim text.