Method of operating three-dimensional video surveillance system

• US 9,483,698 B2
• Filed: 08/06/2014
• Issued: 11/01/2016
• Est. Priority Date: 08/08/2013
• Status: Active Grant

• Current Assignee: Huper Laboratories Co., Ltd.
• Original Assignee: Huper Laboratories Co., Ltd.
• Inventors: Tsai, Chih-Hsiang, Wang, Chao-Ming
• Primary Examiner(s): Patel, Nirav G
• Application Number:
  US14/452,533
• Publication Number:
  US 20150043777A1
• Time in Patent Office: 818 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G08B 13/19606 Discriminating between target movement or movement in an area of interest and other non-signicative movements, e.g. target movements induced by camera shake or movements of pets, falling leaves, rotating fan
• CPC Class Codes: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
• CPC Class Codes: G08B 13/19652 Systems using zones in a single scene defined for different treatment, e.g. outer zone gives pre-alarm, inner zone gives alarm

Abstract

A method includes generating a disparity map according to two sets of image data, identifying at least one object in the disparity map, mapping the at least one object onto a plane view, tracking at least one object on the plane view, and providing a robust algorithm about a cross-line time interval and a cross-line degree. The robust algorithm includes detecting whether the at least one object enters a predetermined region when the at least one object crosses a predetermined boundary.

Claims

1. A method of video surveillance, the method comprising:

generating a disparity map according to two sets of image data captured using a left camera and a right camera;

identifying at least one object in the disparity map;

mapping the at least one object onto a plane view, wherein the plane view has a three dimensional section of interest, a bottom area of the section of interest is enclosed by an artificial boundary and a physical boundary, the section of interest comprises a plurality of sub-sections each having cross-sectional areas identical to the bottom area, and a sum of heights of the sub-sections is equal to a height of the section of interest;

tracking the at least one object in the plane view to identify a height of each of the at least one object;

when detecting an object of the at least one object has crossed the artificial boundary, comparing a height of the object with at least one height range of at least one sub-section of the section of interest, and determining if the object has crossed a surface of each of the at least one sub-section according to a comparison result;

after determining the object has crossed the surface according to the comparison result, detecting number of components of the object crossing the surface, a direction the object crossing the surface, a ratio of a portion of the object crossing the surface to the object, and/or a period of time the object has crossed the surface;

comparing the ratio of the portion of the object crossing the surface to the object and a ratio threshold of the sub-section; and

determining the object has intruded the sub-section when the ratio of the portion of the object crossing the surface to the object is higher than the ratio threshold of the sub-section.

2. The method of claim 1, further comprising:

after determining the object has intruded the sub-section, detecting a direction the object retreats from the sub-section.

3. A method of a video surveillance, the method comprising:

generating a disparity map according to two sets of image data captured using a left camera and a right camera;

identifying at least one object in the disparity map;

mapping the at least one object onto a plane view, wherein the plane view has a three dimensional section of interest, a bottom area of the section of interest is enclosed by an artificial boundary and a physical boundary, the section of interest comprises a plurality of sub-sections each having cross-sectional areas identical to the bottom area, and a sum of heights of the sub-sections is equal to a height of the section of interest;

tracking the at least one object in the plane view to identify a height of each of the at least one object;

when detecting an object of the at least one object has crossed the artificial boundary, comparing a height of the object with at least one height range of at least one sub-section of the section of interest, and determining if the object has crossed a surface of each of the at least one sub-section according to a comparison result;

after determining the object has crossed the surface according to the comparison result, detecting number of components of the object crossing the surface, a direction the object crossing the surface, a ratio of a portion of the object crossing the surface to the object, and/or a period of time the object has crossed the surface;

comparing a period of time the object has crossed the surface and a time threshold of the sub-section; and

determining the object has intruded the sub-section when the period of time the object has crossed the surface is longer than the time threshold of the sub-section.

4. The method of claim 3, further comprising:

after determining the object has intruded the sub-section, detecting a direction the object retreats from the sub-section.

5. A method of video surveillance, the method comprising:

generating a disparity map according to two sets of image data captured using a left camera and a right camera;

identifying at least one object in the disparity map;

mapping the at least one object onto a plane view, wherein the plane view has a three dimensional section of interest, a bottom area of the section of interest is enclosed by an artificial boundary and a physical boundary, the section of interest comprises a plurality of sub-sections each having cross-sectional areas identical to the bottom area, and a sum of heights of the sub-sections is equal to a height of the section of interest;

tracking the at least one object in the plane view to identify a height of each of the at least one object;

when detecting an object of the at least one object has crossed the artificial boundary, comparing a height of the object with at least one height range of at least one sub-section of the section of interest, and determining if the object has crossed a surface of each of the at least one sub-section according to a comparison result;

after determining the object has crossed the surface according to the comparison result, detecting number of components of the object crossing the surface, a direction the object crossing the surface, a ratio of a portion of the object crossing the surface to the object, and/or a period of time the object has crossed the surface;

comparing number of components of the object crossing the surface and a number threshold of the sub-section; and

determining the object has intruded the sub-section when the number of components of the object crossing the surface is larger than the number threshold of the sub-section.

6. The method of claim 5, further comprising:

after determining the object has intruded the sub-section, detecting a direction the object retreats from the sub-section.