Method, system and apparatus for processing an image

Patent metadata

Field	Value
Publication number	US-9996752-B2
Application number	US-201615251933-A
Country	US
Kind code	B2
Filing date	Aug 30, 2016
Priority date	Aug 30, 2016
Publication date	Jun 12, 2018
Grant date	Jun 12, 2018

Abstract

A method and system associated with a camera view of a moving-object in a scene. The method comprises detecting and tracking the moving object over multiple video frames, estimating an orientation of the moving object in each of the video frames, and constructing a cost map from the estimated orientations over the multiple video frames for finding a minimum cost path over the cost map. The Method also comprises determining regularized orientation estimates of the moving-object from the minimum cost path, and locating the vanishing point of the camera view based on an axis of the moving-object from the minimum cost path, the axis formed by using the regularized orientation estimates.

First claim

The claims defining the invention are as follows:

1. A method associated with a camera view of a moving object in a scene, the method comprising:
detecting and tracking the moving object over multiple video frames;
estimating an orientation of the moving object in each of the video frames;
constructing a cost map from the estimated orientations over the multiple video frames for finding a minimum cost path over the cost map;
determining regularized orientation estimates of the moving object from the minimum cost path; and
locating the vanishing point of the camera view based on an axis of the moving object from the minimum cost path, wherein the axis formed uses the regularized orientation estimates.

2. The method according to claim 1 , wherein the vanishing point is a vertical vanishing point and the formed axis is a vertical axis.

3. The method according to claim 1 , wherein the vanishing point is a horizontal vanishing point and the formed axis is a horizontal axis.

4. The method according to claim 1 , wherein estimating the orientation includes estimating the orientation from a major axis of a foreground region of the moving object.

5. The method according to claim 1 , wherein estimating the orientation includes estimating the orientation from a peak of a gradient orientation histogram over a bounding box associated with the moving object.

6. The method according to claim 1 , wherein estimating the orientation includes estimating the orientation from an axis of symmetry of a cost map determined over a bounding box associated with the moving object.

7. The method according to claim 2 , further comprising rotating a graphical representation of the moving object to an upright location based on the vertical vanishing point.

8. The method according to claim 1 , further comprising detecting a change in the vanishing point over a period of time to assess tamper of a camera imaging the scene.

9. The method according to claim 2 , further comprising stabilizing the video frames captured by a camera imaging the scene using the vertical vanishing point.

10. The method according to claim 1 , wherein an object in the scene is identified in one video frame, the method further comprising re-identifying the moving object in a subsequent video frame based on a variation pattern of the regularized orientation estimate.

11. A non-transitory computer readable storage medium having a computer program recorded therein, wherein the computer program is executable by a computer apparatus to make the computer apparatus perform a method associated with a camera view of a moving object in a scene, the method comprising:
detecting and tracking the moving object over multiple video frames;
estimating an orientation of the moving object in each of the video frames;
constructing a cost map from the estimated orientations over the multiple video frames for finding a minimum cost path over the cost map;
determining regularized orientation estimates of the moving object from the minimum cost path; and
locating the vanishing point of the camera view based on an axis of the moving object from the minimum cost path, wherein the axis formed uses the regularized orientation estimates.

12. A system comprising:
a memory for storing data and a computer program;
a processor coupled to the memory for executing the computer program, wherein the computer program is executable by a computer apparatus to make the computer apparatus perform a method associated with a camera view of a moving object in a scene, the method comprising:
detecting and tracking the moving object over multiple video frames;
estimating an orientation of the moving object in each of the video frames;
constructing a cost map from the estimated orientations over the multiple video frames for finding a minimum cost path over the cost map;
determining regularized orientation estimates of the moving object from the minimum cost path; and
locating the vanishing point of the camera view based on an axis of the moving object from the minimum cost path, wherein the axis formed uses the regularized orientation estimates.

13. An apparatus to perform a method associated with a camera view of a moving object in a scene, the apparatus comprising:
a detecting and tracking unit configured to detect and track the moving object over multiple video frames;
an estimating unit configured to estimate an orientation of the moving object in each of the video frames;
a constructing unit configured to construct a cost map from the estimated orientations over the multiple video frames for finding a minimum cost path over the cost map;
a determining unit configured to determine regularized orientation estimates of the moving object from the minimum cost path; and
a locating unit configured to locate the vanishing point of the camera view based on an axis of the moving object from the minimum cost path, wherein the axis formed uses the regularized orientation estimates.

Assignees

• Canon Kk

Inventors

• Pham Quang Tuan
• Taylor Geoffrey Richard

Classifications

• G06V20/52

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

• G06T7/80 Primary

  Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration · CPC title

• G06K9/4671

  Physics · mapped topic

• G06T7/0085

  Physics · mapped topic

• G06K9/00771 Primary

  Physics · mapped topic