OBJECT TRACKING IN A VIDEO STREAM

• US 20150206002A1
• Filed: 03/14/2013
• Published: 07/23/2015
• Est. Priority Date: 08/03/2012
• Status: Active Grant

• Current Assignee: Crunchfish Gesture Interaction AB
• Original Assignee: Crunchfish AB
• Inventors: Pontn, Fredrik
• Granted Patent: US 9,275,275 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06V 10/752 Contour matching
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

A computing device for tracking an object in an image stream, said computing device comprising a memory and a controller, wherein said controller is configured to: receive an image stream comprising at least a first and a previous image of an object to be tracked, determine contour lines in at least said first image, wherein said contour lines comprises a plurality of points, determine and assign at least one descriptor to each point, filter out points based on the descriptors, determine relative distances between each point in said first picture with each point in said previous picture, which points have not been filtered out; and determine a maximum occurrence for the relative distances, wherein the maximum occurrence corresponds to a movement of said object to be tracked in the plane. A movement in a direction parallel to the line of sight is determined from an average position, a relative distance and slopes of linear fittings for each point-component of the points in the two images.

Claims

1-22. -22. (canceled)

23. A computing device for tracking an object in an image stream, said computing device comprising a memory and a controller, wherein said controller is configured to:

receive an image stream comprising at least a first and a previous image of an object to be tracked;

determine at least one contour line in at least said first image, wherein said contour line comprises a plurality of points;

determine and assign at least one descriptor to each point;

filter out points based on the descriptors;

determine relative distances between each point in said first picture with each point in said previous picture, which points have not been filtered out; and

determine a maximum occurrence for the relative distances,

wherein the maximum occurrence corresponds to a movement of said object to be tracked.

24. The computing device of claim 23, wherein said controller is further configured to filter out points by filtering out points having descriptors that are non-descript.

25. The computing device of claim 23, wherein said controller is further configured to filter out points by filtering out points exhibiting a large movement, by comparing the descriptors of said first image with corresponding descriptors for points of said previous image.

26. The computing device of claim 25, wherein said controller is further configured to filter out points exhibiting a large movement and to determine the relative distances substantially simultaneously.

27. The computing device of claim 23, wherein said controller is further configured to filter out points belonging to stationary contour lines.

28. The computing device of claim 23, wherein said controller is further configured to filter out points that are unlikely to be part of the object to be tracked.

29. The computing device of claim 23, wherein said controller is further configured to determine and assign one descriptor to a point based on an angle of a normal to the corresponding point.

30. The computing device of claim 23, wherein said controller is further configured to determine and assign one descriptor to a point based on a curvature of the corresponding point, wherein the curvature is before and/or after the corresponding point.

31. The computing device of claim 30, wherein said controller is further configured to determine the curvature based on an angle of the normal of the corresponding point, an angle of the normal of a succeeding adjacent point and/or an angle of the normal of a preceding adjacent point and the distance between points.

32. The computing device of claim 23, wherein said controller is further configured to determine a second maximum occurrence for tracking a second object.

33. The computing device of claim 23, wherein said controller is further configured to:

determine a mean position of each point pair;

determine a relative distance for each point pair and determine a slope of a corresponding linear fitting of said relative distances versus said mean positions, and

determine a movement in a direction parallel with a line of sight based on the slope.

42. A computing device according to claim 23, wherein said computing device is a mobile communications terminal, an internet tablet, a laptop computer or a game console.

34. A computing device for tracking an object in an image stream, said computing device comprising a memory and a controller, wherein said controller is configured to:

receive a dataset comprising at least one point pair comprising a point in a first picture and a point in a previous picture;

determine a mean position of each point pair;

determine a relative distance for each point pair and determine a slope of a corresponding linear fitting of said relative distances versus said mean positions, and

determine a movement in a direction parallel with a line of sight based on the slope.

35. The computing device of claim 34, wherein said controller is further configured to determine said mean position, said relative distance and said slope based on rectangular coordinates.

36. The computing device of claim 34, wherein said controller is further configured to determine a focal point based on said linear fitting, said focal point identifying a center position of an object.

37. The computing device of claim 36, wherein said controller is further configured to determine the focal point for tracking a first object and to determine a second focal point for tracking a second object.

38. A method for use in a computing device for tracking an object in an image stream, said method comprising:

receiving an image stream comprising at least a first and a previous image of an object to be tracked;

determining at least one contour line in at least said first image, wherein said contour line comprises a plurality of points;

determining and assign at least one descriptor to each point;

filter out points based on the descriptors;

determining relative distances between each point in said first picture with each point in said previous picture, which points have not been filtered out; and

determining a maximum occurrence for the relative distances,

wherein the maximum occurrence corresponds to a movement of said object to be tracked.

40. A computer readable storage medium encoded with instructions that, when loaded and executed on a processor, causes the method according to claim 38 to be performed.

39. A method for use in a computing device for tracking an object in an image stream, said method comprising:

receiving a dataset comprising at least one point pair comprising a point in a first picture and a point in a previous picture;

determining a mean position of each point pair;

determining a relative distance for each point pair and determine a slope of a corresponding linear fitting of said relative distances versus said mean positions, and

determining a movement in a direction parallel with a line of sight based on the slope.

41. A computer readable storage medium encoded with instructions that, when loaded and executed on a processor, causes the method according to claim 39 to be performed.