UNIFIED SYSTEM AND METHOD FOR ANIMAL BEHAVIOR CHARACTERIZATION FROM TOP VIEW USING VIDEO ANALYSIS

• US 20090296992A1
• Filed: 02/03/2009
• Published: 12/03/2009
• Est. Priority Date: 11/24/2000
• Status: Active Grant

• Current Assignee: Clever Sys Incorporated
• Original Assignee: Clever Sys Incorporated
• Inventors: Zhang, Yi, Wolf, Wayne, Liang, Yiqing, Crnic, Linda S, Kobla, Vikrant, Bai, Xuesheng, Wilks, Stan L.
• Granted Patent: US 7,817,824 B2
• Time in Patent Office: Days
• US Class Current: 382/110
• CPC Class Codes: A01K 1/031 Cages for laboratory animals; Cages for measuring metabolism of animals
• CPC Class Codes: A01K 29/005 Monitoring or measuring activity, e.g. detecting heat or mating
• CPC Class Codes: A61B 2503/40 Animals
• CPC Class Codes: A61B 2503/42 for laboratory research
• CPC Class Codes: A61B 5/1113 Local tracking of patients, e.g. in a hospital or private home
• CPC Class Codes: A61B 5/1116 Determining posture transitions
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/1128 using image analysis A61B5/1127 takes precedence
• CPC Class Codes: A61B 5/4094 Diagnosing or monitoring seizure diseases, e.g. epilepsy
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• 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 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training
• CPC Class Codes: G16H 40/67 for remote operation

Abstract

In general, the present invention is directed to systems and methods for finding the position and shape of an animal using video. The invention includes a system with a video camera coupled to a computer in which the computer is configured to automatically provide animal segmentation and identification, animal motion tracking (for moving animals), animal feature points and segments identification, and behavior identification. In a preferred embodiment, the present invention may use background subtraction for animal identification and tracking, and a combination of decision tree classification and rule-based classification for feature points and segments and behavior identification. Thus, the present invention is capable of automatically monitoring a video image to identify, track and classify the actions of various animals and the animal'"'"'s movements within the image. The image may be provided in real time or from storage. The invention is particularly useful for monitoring and classifying animal behavior for testing drugs and genetic mutations, but may be used in any of a number of other surveillance applications.

Claims

1-41. -41. (canceled)

42. A method for characterizing animal behavior, comprising:

segregating images of an animal from video images of the animal in a behavioral analysis apparatus, wherein the video images are taken only from a top view;

identifying at least one body part of the animal based on the images taken from a top view;

identifying a center of mass of the animal based on the images taken from a top view; and

characterizing behavior of the animal using the at least one body part and the center of mass of the animal.

43. The method of claim 42, wherein segregating images of an animal from video images includes subtracting a background image from a video image containing an image of an animal.

44. The method of claim 42, wherein characterizing behavior of the animal includes comparing a location of the at least one body part of the animal and a location of the center of mass of the animal to pre-trained behavior models.

45. The method of claim 42, wherein characterizing behavior of the animal includes comparing a location of the at least one body part of the animal and a location of the center of mass of the animal to predefined rules.

46. The method of claim 42, wherein characterizing the behavior of the animal includes determining the location of the at least one body part of the animal in relation to a user-defined virtual zone.

47. The method of claim 42, wherein characterizing the behavior of the animal includes determining the location of the center of mass of the animal in relation to a user-defined virtual zone.

48. The method of claim 42, wherein the at least one body part is a head.

49. The method of claim 42, wherein the at least one body part is a tail.

50. The method of claim 42, wherein the at least one body part is a waist.

51. The method of claim 42, wherein the at least one body part is a fore body.

52. The method of claim 42, wherein the at least one body part is a hind body.

53. The method of claim 42, wherein the behavior analysis apparatus is an open field apparatus.

54. The method of claim 42, wherein the behavior analysis apparatus is a maze apparatus.

55. The method of claim 42, wherein the behavior analysis apparatus includes recognition objects.

56. The method of claim 42, wherein the behavior analysis apparatus includes a fear chamber.

57. A method for characterizing animal behavior, comprising:

segregating images of an animal from video images of the animal in a behavioral analysis apparatus, wherein the video images are taken only from a top view;

identifying at least one body part of the animal based on the images taken from a top view;

identifying a center of mass of the animal based on the images taken from a top view; and

detecting behavioral events of the animal using the at least one body part and the center of mass of the animal.

58. The method of claim 57, wherein detecting behavior events includes comparing a location of the at least one body part of the animal and a location of the center of mass of the animal to pre-trained behavior models.

59. The method of claim 57, wherein detecting behavioral events includes comparing a location of the at least one body part of the animal and a location of the center of mass of the animal to predefined rules.

60. The method of claim 57, wherein detecting behavioral events includes detecting a turning ratio of the animal by taking a ratio of a path length traveled over a number of turns, wherein a turn is counted when the animal makes a turn larger than ninety degrees when the animal travels one body length.

61. The method of claim 57, wherein detecting behavioral events includes detecting sniffing behavior of the animal by detecting when the animal'"'"'s nose is in contact with a recognition object in the behavioral analysis apparatus.

62. The method of claim 57, wherein detecting behavioral events includes detecting stretch-and-attend by detecting the animal'"'"'s approach to an object with fore body stretched and then lowered, followed by retraction of the fore body.

63. The method of claim 57, wherein detecting behavioral events includes detecting stay-across-areas by detecting the animal'"'"'s partial incursions into a zone of the behavioral analysis apparatus.

64. The method of claim 57, wherein detecting behavioral events includes detecting head dipping by detecting the animal'"'"'s exploratory movement of its head over an edge of the behavioral analysis apparatus.

65. The method of claim 57, wherein detecting behavioral events includes detecting freezing by detecting an absence of movement of the animal'"'"'s body for a period of time.

66. The method of claim 57, wherein detecting behavioral events includes detecting locomoting by detecting movement of the animal within the behavioral analysis apparatus.

67. The method of claim 57, wherein detecting behavioral events includes detecting transgressing behavior by detecting movement of the animal from a defined zone within the behavioral analysis apparatus to another defined zone within the behavioral analysis apparatus.

68. The method of claim 57, wherein detecting behavioral events includes calculating a proximity score by determining a distance of the animal from a goal at predetermined time intervals.

69. The method of claim 57, wherein detecting behavioral events includes determining heading errors by detecting when the animal is moving away from a goal.

70. The method of claim 57, wherein the at least one body part is a head.

71. The method of claim 57, wherein the at least one body part is a tail.

72. The method of claim 57, wherein the at least one body part is a waist.

73. The method of claim 57, wherein the at least one body part is a fore body.

74. The method of claim 57, wherein the at least one body part is a hind body.

75. A computer-readable medium including instructions for performing:

segregating images of an animal from video images of the animal in a behavioral analysis apparatus, wherein the video images are taken only from a top view;

identifying at least one body part of the animal based on the images taken from a top view;

identifying a center of mass of the animal based on the images taken from a top view; and

characterizing behavior of the animal using the at least one body part and the center of mass of the animal.

76. The computer-readable medium of claim 75, wherein characterizing behavior of the animal includes comparing a location of the at least one body part of the animal and a location of the center of mass of the animal to pre-trained behavior models.

77. The computer-readable medium of claim 75, wherein characterizing behavior of the animal includes comparing a location of the at least one body part of the animal and a location of the center of mass of the animal to predefined rules.

78. The computer-readable medium of claim 75, wherein the at least one body part is a head.

79. The computer-readable medium of claim 75, wherein the at least one body part is a tail.

80. The computer-readable medium of claim 75, wherein the at least one body part is a waist.

81. The computer-readable medium of claim 75, wherein the at least one body part is a fore body.

82. The computer-readable medium of claim 75, wherein the at least one body part is a hind body.