Device and method for detecting regions in an image
AssigneeSony Corporation
InventorPingshan LI
Life of this patent
Estimating the term…
Abstract
Various aspects of a device and method for detection of regions based on sensor data for autofocus are disclosed herein. In accordance with an embodiment, the method includes receipt of a depth of filed (DOF) information of a scene viewed using an image-capturing device of the electronic device. The one or more images of the scene are segmented into a plurality of candidate segmented regions based on the received DOF information. One of the plurality of candidate segmented regions is determined as a region-of-interest to autofocus on the determined candidate segmented region.
Claims23
An electronic device comprising:
- an image capturing device configured to receive a scene;
- and
- one or more circuits configured to:
- receive depth of field (DOF) information of the scene;
- segment at least one image of said scene into a plurality of candidate segmented regions based on said DOF information;
- determine a first candidate segmented region of said plurality of candidate segmented regions as a region-of-interest to autofocus on said first candidate segmented region;
- generate a saliency map for said at least one image of said scene based on an optical flow technique;
- and
- overlap said saliency map with each of said plurality of candidate segmented regions for said determination of said first candidate segmented region as said region-of-interest.
(canceled)
(canceled)
A method, comprising:
- receiving, via an image capturing device, a scene;
- receiving, by one or more circuits of an electronic device, depth of field (DOF) information of the scene;
- segmenting, by said one or more circuits, at least one image of said scene into a plurality of candidate segmented regions based on said DOF information;
- determining, by said one or more circuits, a first candidate segmented region of said plurality of candidate segmented regions as a region-of-interest to autofocus on said first candidate segmented region;
- generating, by said one or more circuits, a saliency map for said at least one image of said scene based on an optical flow technique;
- and
- overlapping, by said one or more circuits, said saliency map with each of said plurality of candidate segmented regions for said determination of said first candidate segmented region as said region-of-interest.
(canceled)
(canceled)
Dependencies are inferred from the claim text.