Video camera scene translation

Patent metadata

Field	Value
Publication number	US-10354144-B2
Application number	US-201615169111-A
Country	US
Kind code	B2
Filing date	May 31, 2016
Priority date	May 29, 2015
Publication date	Jul 16, 2019
Grant date	Jul 16, 2019

Abstract

This document describes systems, methods, devices, and other techniques for video camera scene translation. In some implementations, a computing device accesses a first video that shows a first 2D scene of an environment; defines a trip wire at a first position of the first 2D scene; obtains a 3D model of at least a portion of the environment shown in the first 2D scene; maps the trip wire from the first position of the first 2D scene to a first position of the 3D model that corresponds to the first position of the first 2D scene; accesses a second video that shows a second 2D scene of the environment; and projects the trip wire from the first position of the 3D model to a first position of the second 2D scene that corresponds to a same location in the environment as the first position of the first 2D scene.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
accessing, by a computing system, a first video that shows a first two-dimensional (2D) scene of a real-world environment, the first video captured by a first camera located in the real-world environment having a first field of view;
defining a trip wire for performing video analytics at a first position of the first 2D scene shown in the first video, wherein the trip wire is defined based on a user input that draws a line over the first video and that at least partially defines a zone of interest in the first 2D scene of the real-world environment;
generating, based on processing the first video using a three-dimensional (3D) model generator, a 3D model of at least a portion of the real-world environment that is shown in the first 2D scene of the first video;
mapping, by the computing system, the trip wire from the first position of the first 2D scene shown in the first video to a first position of the 3D model that corresponds to the first position of the first 2D scene;
after the trip wire that is defined based on the user input over the first video is mapped from the first position of the first 2D scene shown in the first video to the first position of the 3D model, determining, by the computing system, that a second video that shows a second 2D scene of the real-world environment has become available, the second video captured by a second camera having the second field of view;
projecting the trip wire from the first position of the generated 3D model to a first position of the second 2D scene that corresponds to a same location in the real-world environment as the first position of the first 2D scene, wherein projecting the trip wire includes adjusting an angle and a length of the line that at least partially defined the zone of interest in the first 2D scene to define a corresponding zone of interest in the second 2D scene; and
generating a user interface that includes the second 2D scene and the trip wire that has been projected to the first position of the second 2D scene, or performing video analytics on the second 2D scene using the trip wire that has been projected to the first position of the second 2D scene.

2. The method of claim 1 , wherein the defined trip wire is associated with one or more rules for performing video analytics.

3. The method of claim 2 , wherein the one or more rules for performing video analytics comprise counting a number of objects crossing the trip line.

4. The method of claim 1 , further comprising determining that the first camera has moved and has a second field of view that is different from the first field of view.

5. The method of claim 4 , wherein the first camera is at a fixed position in the environment and determining that the first camera has moved comprises determining that the first camera has one or more of (i) panned, (ii) tilted, and/or (iii) zoomed.

6. The method of claim 4 , wherein the first camera is mobile and determining that the first camera has moved comprises determining translations and rotations of the video camera.

7. The method of claim 4 , wherein determining that the first camera has moved comprises using one or more sensors to identify movement of the first camera.

8. The method of claim 4 , wherein determining that the first camera has moved comprises calculating a displacement between the first field of view and the second field of view.

9. The method of claim 4 , wherein determining that the first camera has moved comprises using one or more sensors to identify movement of the first camera and calculating a displacement between the first field of view and the second field of view.

10. The method of claim 1 , wherein the 3D model comprises (i) a ground plane of at least a portion of the real-world environment that is shown in the first 2D scene of the first video, and (ii) a first camera location relative to the ground plane.

11. The method of claim 1 , wherein the 3D model comprises a detailed 3D model of at least a portion of the real-world environment that is shown in the first 2D scene of the first video, wherein the detailed 3D model comprises objects and buildings in the portion of the real-world environment that is shown in the first 2D scene of the first video.

12. The method of claim 1 , wherein the defined trip wire comprises a line drawn in space relative to a ground plane of the portion of the real-world environment that is shown in the first 2D scene of the first video.

13. One or more non-transitory computer-readable media having instructions stored thereon that, when executed by one or more processors, cause performance of operations comprising:
accessing, by a computing system, a first video that shows a first two-dimensional (2D) scene of a real-world environment, the first video captured by a first camera located in the real-world environment having a first field of view;
defining a trip wire for performing video analytics at a first position of the first 2D scene shown in the first video, wherein the trip wire is defined based on a user input that draws a line over the first video and that at least partially defines a zone of interest in the first 2D scene of the real-world environment;
generating, based on processing the first video using a three-dimensional (3D) model generator, a 3D model of at least a portion of the real-world environment that is shown in the first 2D scene of the first video;
mapping, by the computing system, the trip wire from the first position of the first 2D scene shown in the first video to a first position of the 3D model that corresponds to the first position of the first 2D scene;
after the trip wire that is defined based on the user input over the first video is mapped from the first position of the first 2D scene shown in the first video to the first position of the 3D model, determining, by the computing system, that a second video that shows a second 2D scene of the real-world environment has become available, the second video captured by a second camera having the second field of view;
projecting the trip wire from the first position of the generated 3D model to a first position of the second 2D scene that corresponds to a same location in the real-world environment as the first position of the first 2D scene, wherein projecting the trip wire includes adjusting an angle and a length of the line that at least partially defined the zone of interest in the first 2D scene to define a corresponding zone of interest in the second 2D scene; and
generating a user interface that includes the second 2D scene and the trip wire that has been projected to the first position of the second 2D scene, or performing video analytics on the second 2D scene using the trip wire that has been projected to the first position of the second 2D scene.

14. A system, comprising:
one or more processing devices; and
one or more computer-readable media having instructions stored thereon that, when executed by the one or more processing devices, cause performance of operations comprising:
accessing, by a computing system, a first video that shows a first two-dimensional (2D) scene of a real-world environment, the first video captured by a first camera located in the real-world environment having a first field of view;
defining a trip wire for performing video analytics at a first position of the first 2D scene shown in the first video, wherein the trip wire is defined based on a user input that draws a line over the first video and that at least partially defines a zone of interest in the first 2D scene of the real-world environment;
generating, based on processing the firs

Assignees

• Accenture Global Solutions Ltd

Inventors

• Bataller Cyrille
• Astrom Anders
• Daniel Philippe

Classifications

• H04N7/181 Primary

  for receiving images from a plurality of remote sources · CPC title

• G06V20/49

  Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes · CPC title

• G06F18/2178

  based on feedback of a supervisor · CPC title

• G06T7/13

  Edge detection · CPC title

• G06F16/51

  Indexing; Data structures therefor; Storage structures · CPC title