Method and apparatus for performing privacy masking by reflecting characteristic information of objects

Patent metadata

Field	Value
Publication number	US-12597183-B2
Application number	US-202318223279-A
Country	US
Kind code	B2
Filing date	Jul 18, 2023
Priority date	Mar 9, 2018
Publication date	Apr 7, 2026
Grant date	Apr 7, 2026

Abstract

An image masking method is provided. The method includes: extracting an object from an image; obtaining characteristic information about the extracted object by analyzing the extracted object; determining whether the extracted object is a masking target according to an input setting value or the obtained characteristic information; and performing masking such that the obtained characteristic information is reflected on the extracted object, in response to determining that the extracted object is the masking target among a plurality of objects extracted from the input image, wherein the setting value is set by an input designating at least a partial region in the input image, and wherein in the determining whether the extracted object is the masking target, an object positioned in the at least a partial region is determined as the masking target among the extracted objects.

First claim

What is claimed is:

1 . An image masking method of a surveillance system in which a processor and a memory are included and an operation is controlled by the processor, the image masking method comprising:
designating a partial region to be masked in an input image through a user interface, the partial region having a fixed size at a fixed position within the input image; designating a sensitivity with respect to the partial region to be masked through the user interface; extracting an object from the input image; obtaining characteristic information including motion information about the extracted object by analyzing the extracted object; and performing masking on the extracted object, in response to determining the extracted object is a dynamic object which has the motion information, wherein the performing masking on the extracted object includes performing masking on the extracted object, when both a first condition that the extracted object is positioned in the designated partial region and a second condition that the extracted object meets the designated sensitivity are satisfied, wherein as the sensitivity decreases, a monitoring function is enhanced and as the sensitivity increases, a privacy protection function is enhanced, and wherein, when the extracted object is located outside the designated partial region, no masking is performed regardless of the designated sensitivity, and when the extracted object enters the designated partial region, the object is only then masked.

2 . The image masking method of claim 1 , wherein a result of the masking is different according to the sensitivity, for each masking area with a center on the extracted object.

3 . The image masking method of claim 2 , wherein the partial region for the extracted object decreases toward the extracted object as the sensitivity decreases.

4 . The image masking method of claim 1 , wherein the obtained characteristic information further includes a silhouette according to shape information about the extracted object.

5 . The image masking method of claim 4 , wherein the silhouette changes according to a change in a contour of the extracted object.

6 . The image masking method of claim 5 , wherein an interior of the silhouette is filled with a pre-selected color or pattern to match a corresponding person.

7 . The image masking method of claim 1 , wherein the obtained characteristic information is a characteristic information for monitoring the extracted object.

8 . The image masking method of claim 7 , wherein in the performing masking on the extracted object, the obtained characteristic information is reflected on the extracted object.

9 . The image masking method of claim 7 , wherein the obtained characteristic information further includes information about at least one of color, shape, motion, identity, position.

10 . The image masking method of claim 1 , wherein the performing the masking comprises:
generating a masking object by reflecting the obtained characteristic information; and performing the masking on the extracted object determined as a masking target using the masking object.

11 . The image masking method of claim 10 , wherein the masking object is an avatar on which the obtained characteristic information is reflected.

12 . The image masking method of claim 11 , wherein at least one of a face, a hair, a top, a bottom, a gender, and an age of the avatar is determined according to the obtained characteristic information.

13 . A camera device including an input/output interface configured to capture an image and at least one processor, the camera device comprising:
a user interface configured to designate a partial region to be masked in the input image and a sensitivity with respect to the partial region to be masked, based on a user input, the partial region having a fixed size at a fixed position within the input image; an object extractor configured to extract an object from the image; an object analyzer configured to obtain information including characteristic information about the object by analyzing the extracted object; an object determiner configured to determine the extracted object is a dynamic object which has motion information; and an object processor configured to perform masking on the extracted object, in response to determining the extracted object is the dynamic object which has the motion information, wherein the performing masking on the extracted object includes performing masking on the extracted object when both a first condition that the extracted object is positioned in the designated partial region and a second condition that the extracted object meets the designated sensitivity are satisfied, and wherein as the sensitivity decreases, a monitoring function is enhanced and as the sensitivity increases, a privacy protection function is enhanced, and wherein, when the extracted object is located outside the designated partial region, no masking is performed regardless of the designated sensitivity, and when the extracted object enters the designated partial region, the object is only then masked.

Assignees

• Hanwha Techwin Co Ltd
• Hanwha Vision Co Ltd

Inventors

• Choi Jin Hyuk
• Jeong Song Taek
• Song Jae Cheon

Classifications

• G06T11/10

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

• G06V2201/07

  Target detection · CPC title

• G06V10/235

  based on user input or interaction · CPC title