Selective object detection

• US 9,449,510 B2
• Filed: 10/16/2015
• Issued: 09/20/2016
• Est. Priority Date: 11/15/2012
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Avigilon Analytics Corporation (Motorola Solutions, Inc.)
• Inventors: Saptharishi, Mahesh, Marman, Douglas H.
• Primary Examiner(s): Harold, Jefferey
• Assistant Examiner(s): Rahman, Mustafizur
• Application Number:
  US14/885,209
• Publication Number:
  US 20160034767A1
• Time in Patent Office: 340 Days
• Field of Search: 348/135, 348/143, 348/142, 348/149, 348/153, 348/154, 348/156, 348/158, 348/169, 348/222.1, 348/565, 382/103, 382/107, 382/154, 382/166, 382/282, 715/700, 715/764, 345/419, 345/652
• US Class Current: 1/1
• CPC Class Codes: G06T 15/08 Volume rendering
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 2207/30242 Counting objects in image
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• 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: G06T 7/215 Motion-based segmentation
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 20/49 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 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 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
• CPC Class Codes: G08B 13/2491 Intrusion detection systems, i.e. where the body of an intruder causes the interference with the electromagnetic field
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources
• CPC Class Codes: H04N 7/183 : for receiving images from a single remote source
• CPC Class Codes: H04N 7/188 : Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

Video analytics is used to track an object of interest represented in video data representing the field of view of a scene observed by a video camera. A multidimensional virtual beam is used to detect whether the tracked object of interest is continually present in a detection zone within the field view of the scene. An occurrence of an event is signaled when the tracked object of interest is continually present in the detection zone during a period beginning when the tracked object of interest enters the detection zone and ending when the tracked object of interest leaves the detection zone through the opposite side, after having completely crossed through the detection zone. Use of a virtual beam detection zone reduces false alarms as compared to the numbers of incidences of false alarms of traditional detection methods, while adding several features and benefits.

Claims

1. A method of monitoring whether an object of interest is passing through an area within a field of view of a scene observed by a video camera, the method comprising:

receiving video data representing the field of view of the scene observed by the video camera;

using video analytics to track the object of interest represented in the video data;

configuring a detection zone within the area, the detection zone including an entrance side and an exit side positioned opposite to each other and thereby defining opposite sides of the detection zone; and

signaling an occurrence of an event only when the tracked object of interest is continually present in the detection zone during a period beginning when the tracked object of interest enters the detection zone on the entrance side and ending when the tracked object of interest leaves the detection zone from the exit side and not signaling the occurrence of the event if the tracked object of interest entered or exited the detection zone in another manner.

2. The method of claim 1, in which the detection zone corresponds to an area or volume superimposed on a two-dimensional image represented by the video data.

3. The method of claim 1, in which the detection zone corresponds to an area or volume of space oriented in a three-dimensional representation of the scene observed by the video camera.

4. The method of claim 1, in which the signaling of an occurrence of an event is performed for an object of interest exhibiting a specified physical characteristic.

5. The method of claim 4, in which the physical characteristic comprises at least one of a color of the object of interest, shape of the object of interest, or a size of the object of interest.

6. The method of claim 4, in which the physical characteristic is a speed of motion of the object of interest.

7. The method of claim 6, wherein the object of interest is determined to be moving based on identifying pixel changes moving within the field of view.

8. The method of claim 4, in which the physical characteristic is a height of the object of interest.

9. The method of claim 4, in which the detection zone corresponds to a volume of space and thereby defines a virtual beam detection zone that is superimposed on an image represented by the video data, and in which the physical characteristic is a height of the object of interest within the virtual beam detection zone.

10. The method of claim 4, in which the detection zone corresponds to a volume of space and thereby defines a virtual beam detection zone that is superimposed on an image represented by the video data, and in which a height of the object of interest is capable of being configured by a height value set by a user.

11. The method of claim 4, wherein the received video data comprises color-based thermal temperature data of the field of view of the scene observed by the video camera, and wherein the physical characteristic comprises at least one specified color or at least one specified intensity of the at least one color.

12. The method of claim 11, wherein the at least one specified color or the at least one specified intensity of the at least one color indicates a malfunction in an electrical system.

13. The method of claim 1, in which the object of interest is of a specified type.

14. The method of claim 1, in which the object of interest is one of a number of objects of interest, and in which the signaling of an occurrence of an event is performed upon determination of a specified number of tracked objects of interest.

15. The method of claim 1, further comprising monitoring an output signal of an external sensor, and in which the signaling of an occurrence of an event is performed upon indication of a predetermined value of the output signal of the external sensor.

16. The method of claim 1, in which the object of interest is one of multiple objects of interest, and further comprising performing a count of the multiple objects of interest.

17. The method of claim 16, in which the multiple objects of interest are people present in a retail establishment, and further comprising using a count of the people to monitor retail establishment customer traffic patterns.

18. The method of claim 16, in which the multiple objects of interest are vehicles present in a specified region of vehicle travel, and further comprising using a count of the vehicles to monitor vehicle traffic patterns in the specified region.

19. The method of claim 1, further comprising assigning the detection zone to follow the tracked object of interest as it moves at least within the field of view of the scene observed by the video camera.

20. The method of claim 19, in which the scene observed by the video camera is a vehicle parking site and the tracked object of interest is a vehicle.

21. The method of claim 19, in which the scene observed by the video camera is a hospital facility and the tracked object of interest is a person or hospital equipment.

22. The method of claim 1, in which the object of interest is of a specified type, and further comprising automatically assigning the detection zone to encompass the specified object of interest when it appears in the field of view of the scene observed by the video camera.

23. The method of claim 22, further comprising:

storing metadata associated with and identifying the object of interest; and

tracking the object of interest across multiple video cameras based on the stored metadata.

24. The method of claim 22, wherein the video analytics is used to track multiple objects of interest, the method further comprising:

storing metadata associated with behavior patterns of the multiple object of interest; and

identifying at least one irregular behavior pattern based on the stored metadata.

25. The method of claim 1, in which one of the entrance and exit sides of the detection zone is configured to be a certain distance from a ground reference to enable detection of a particular portion of the object of interest.

26. The method of claim 1, wherein the detection zone is configured to correspond to a volume at least partially surrounding the object of interest.

27. The method of claim 1, further comprising;

configuring a second detection zone, the second detection zone including a second entrance side and a second exit side; and

signaling an occurrence of a second event when the tracked object of interest or another tracked object of interest is continually present in the detection zone during a second period beginning when the tracked object of interest or the another tracked object of interest enters the detection zone on the second entrance side and ending when the tracked object of interest or the another tracked object of interest leaves the detection zone from the second exit side.

28. The method of claim 1, wherein at least one of the entrance side or the exit side comprises at least one of an arc, a circle, a dome, a sphere, a straight line, a pyramid, a box, or a hexagon.

29. The method of claim 27, wherein the second entrance side comprises the exit side, and wherein the second exit side comprises the entrance side.

30. The method of claim 1, wherein configuring the detection zone further comprises determining a distance been the entrance side and the exit side.

31. The method of claim 30 wherein the distance between the entrance side and the exit side is lengthened to reduce a likelihood of occurrence of false alarms.

32. The method of claim 30, wherein the distance between the entrance side and the exit side is shortened to increase a sensitivity of detection.

33. The method of claim 30, wherein the distance between the entrance side and the exit side is adjusted based on a second distance between the camera and the detection zone.

34. The method of claim 33, wherein the scene observed by the video camera comprises a three-dimensional representation of the scene, and wherein the second distance is between a horizon identified in the three-dimensional representation of the scene and the detection zone.

35. The method of claim 1, wherein configuring the detection zone further comprises selecting a height of the detection zone, wherein the height of the detection zone is selected based on a second distance between the camera and the detection zone.

36. The method of claim 1, further comprising aligning the detection zone with at least one location within the scene observed by the video camera.

37. The method of claim 36, wherein the scene observed by the video camera comprises a three-dimensional representation of the scene, and wherein the at least one location comprises three-dimensional coordinates.

38. The method of claim 37, wherein aligning the detection zone with the at least one location is based on user input.

39. The method of claim 38, wherein aligning the detection zone with the at least one location comprises using video analytics to generate a ground plane model or identifying a horizon and aligning the detection zone with the ground plane model or the horizon.

40. The method of claim 39, wherein generating the ground plane model comprises determining an angle of the ground plane.

41. The method of claim 1, further comprising:

configuring a time allowed for the tracked object of interest to pass through the detection zone, wherein signaling the occurrence of the event is performed based on a comparison of the period and the time allowed for the tracked object of interest to pass through the detection zone.

42. The method of claim 41, wherein configuring the time allowed for the tracked object of interest to pass through the detection zone comprises setting a range of times corresponding to a range of speeds of the tracked object of interest.

43. The method of claim 42, wherein configuring the time allowed is based on user input.

44. The method of claim 42, wherein configuring the time allowed is based on user selection of a speed or the range of speeds of the tracked object of interest.

45. The method of claim 1, wherein signaling the occurrence of the event is performed when a trajectory of the tracked object of interest is associated with irregular activity.

46. The method of claim 1, wherein the video analytics is used to track multiple objects of interest, and wherein signaling the occurrence of the event is performed when a threshold number of the multiple objects at least one of enter the detection zone, are continuously present in the detection zone, or leave the detection zone within a second period of time.

47. The method of claim 46, wherein within the second period of time comprises concurrently.

48. The method of claim 46, further comprising adjusting the threshold number based on a comparison of the period for at least one of the multiple objects of interest and a second period.

49. The method of claim 1, further comprising:

identifying a second object of interest;

associating the detection zone with the second object of interest.

50. The method of claim 49, wherein identifying the second object of interest is based on at least one of radio frequency identification (RFID), radio triangulation, or global positioning system (GPS) data.

51. The method of claim 49, wherein associating the detection zone with the second object of interest comprises associating the detection zone with the second object of interest such that the detection zone follows the second object of interest as it moves.

52. The method of claim 1, further comprising:

selecting the object of interest for tracking based on at least one of an ambient light level associated with the field of view of the scene, a time of day, or one or more prior detected objects or events.

53. The method of claim 1, wherein the tracked object of interest is part of another object.

54. The method of claim 53, wherein the tracked object of interest comprises a license plate, or a portion of a human body.

55. The method of claim 1, wherein the field of view of the scene observed by the video camera comprises a fence or wall, and wherein configuring the detection zone comprises positioning the entrance side below the exit side on the fence or the wall to detect a person climbing the fence or the wall.

56. The method of claim 55, wherein configuring the detection zone further comprises positioning the entrance side a first distance away from the exit side, the first distance selected to be equal to or greater than at least one dimension of the tracked object of interest.

57. The method of claim 1, wherein the field of view of the scene observed by the video camera comprises a corridor or virtual corridor, and wherein configuring the detection zone comprises positioning the entrance side a first distance away from the exit side, the first distance selected to only signal the occurrence of the event when the tracked object of interest travels the first distance.

58. The method of claim 1, wherein the field of view of the scene observed by the video camera comprises a doorway, and wherein configuring the detection zone comprises selecting one of a height of the detection zone or a vertical position of the detection zone relative to the doorway to only signal the occurrence of the event for objects exceeding the height or the vertical position.

59. The method of claim 1, wherein the tracked object of interest is one of a number of tracked objects of interest, wherein the method further comprises:

determining if one of the objects of interest is left within the detection zone or whether one of the objects of interest is removed from the detection zone.

60. The method of claim 59, further comprising associating each of the objects of interest with a unique object ID, and wherein the determining further comprises tracking each of the objects of interest using the unique object ID.

61. The method of claim 1, wherein the specified physical characteristic of the tracked object of interest is identified, at least in part, using geometric calibration based on a size of the tracked object of interest.

62. A video surveillance system comprising:

at least one video camera configured to monitor whether an object of interest is passing through a detection zone within a field of view of a scene observed by the at least one video;

a computer system connected to the at least one video camera, and wherein the computer system further comprises;

memory; and

a processor, wherein the memory comprises instructions, that when executed by the processor, cause the processor to;

receive video data representing the field of view of the scene observed by the video camera;

track the object of interest represented in the video data;

configure the detection zone, the detection zone including an entrance side and an exit side positioned opposite to each other and thereby defining opposite sides of the detection zone; and

signal an occurrence of an event only when the tracked object of interest is continually present in the detection zone during a period beginning when the tracked object of interest enters the detection zone on the entrance side and ending when the tracked object of interest leaves the detection zone from the exit side and not signaling the occurrence of the event if the tracked object of interest entered or exited the detection zone in another manner.

63. A non-transitory computer readable medium storing instruction, that when executed by a processor, cause the processor to perform the operations of:

receiving video data representing a field of view of a scene observed by at least one video camera;

using video analytics to track an object of interest represented in the video data;

configuring a detection zone, the detection zone including an entrance side and an exit side positioned opposite to each other and thereby defining opposite sides of the detection zone; and

signaling an occurrence of an event only when the tracked object of interest is continually present in the detection zone during a period beginning when the tracked object of interest enters the detection zone on the entrance side and ending when the tracked object of interest leaves the detection zone from the exit side and not signaling the occurrence of the event if the tracked object of interest entered or exited the detection zone in another manner.