# US 2014/0153784 A1 · Spatio-temporal confidence maps

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2014/0153784 A1
- Document ID: US20140153784A1
- Status: Published application
- Kind: A1
- Application number: 14/057,917
- Filed: 2013-10-18
- Published: 2014-06-05
- Earliest claimed: 2012-10-18
- Assignees: Thomson Licensing
- Applicants: Thomson Licensing
- Inventors: Dirk GANDOLPH; Joern Jachalsky; Wolfram Putzke-Roeming; Markus Schlosser
- Web page: https://patentgrep.com/patent/US20140153784A1

## CPC

- G06T 7/269: using gradient-based methods
- G06T 7/215: Motion-based segmentation
- G06T 7/593: from stereo images
- G06T 2207/10021: Stereoscopic video; Stereoscopic image sequence
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method and an apparatus for generating a confidence map for a disparity map associated to a set of two or more images are described. Motion between at least two subsequent sets of two or more images is determined. Based on the determined motion information static and dynamic regions in the images of the sets of two or more images are detected and separated. A disparity change between a disparity value determined for a static region of a current image and a motion compensated disparity value of a previous image is determined. The result of the determination is taken into account for generating or refining a confidence map.

## Claims

### Claim 1

A method for generating a confidence map for a disparity map associated to a sequence of sets of two or more images, the method comprising the steps of:
determining motion between at least two subsequent sets of two or more images;
detecting and separating static and dynamic regions in the images of the sets of two or more images based on the determined motion information;
determining a disparity change between a disparity value determined for a static region of a current image and a motion compensated disparity value of a previous image; and
taking the result of the determining step into account for generating or refining a confidence map.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the motion between at least two subsequent sets of two or more images is described by optical flow maps.

### Claim 3 (depends on 1)

The method according to claim 1, wherein a confidence value for a static region is increased if the disparity change determined for the static region is below a threshold.

### Claim 4 (depends on 1)

The method according claim 1, wherein the confidence map is refined by applying a filter to the confidence values of the confidence map.

### Claim 5 (depends on 4)

The method according to claim 4, wherein output confidence values of the filter are controlled by the determined disparity change and input confidence values.

### Claim 6 (depends on 5)

The method according to claim 5, wherein the filter primarily modifies those confidence values whose figures are located in center of a value range of the confidence values.

### Claim 7 (depends on 5)

The method according to claim 5, wherein the filter modifies all confidence values equally without preference.

### Claim 8

An apparatus for generating a confidence map for a disparity map associated to a sequence of sets of two or more images, wherein the apparatus comprises:
a motion determining unit configured to determine motion between at least two subsequent sets of two or more images;
a region detector and separator configured to detect and separate static and dynamic regions in the images of the sets of two or more images based on the determined motion information;
a determining unit configured to determine a disparity change between a disparity value determined for a static region of a current image and a motion compensated disparity value of a previous image; and
a confidence map generator configured to take the result obtained by the determining unit into account for generating or refining a confidence map.