Avian detection systems and methods

• US 10,275,679 B2
• Filed: 08/21/2015
• Issued: 04/30/2019
• Est. Priority Date: 08/21/2014
• Status: Active Grant

• Current Assignee: IdentiFlight International, LLC
• Original Assignee: IdentiFlight International, LLC
• Inventors: Jorquera, Carlos, Coppage, Aaron, DeSalvo, Jason, Luttrell, Ryan, Luttrell, Jason
• Primary Examiner(s): Rao, Anand S
• Application Number:
  US14/832,370
• Publication Number:
  US 20160055400A1
• Time in Patent Office: 1,348 Days
• CPC Class Codes: F03D 17/00 Monitoring or testing of wind motors, e.g. diagnostics testing during commissioning of wind motors F03D13/30
• CPC Class Codes: F03D 7/02 the wind motors having rotation axis substantially parallel to the air flow entering the rotor
• CPC Class Codes: F03D 7/0264 for stopping; controlling in emergency situations orientating out of wind F03D7/0208
• CPC Class Codes: F03D 80/00 Details, components or accessories not provided for in groups F03D1/00 - F03D17/00
• CPC Class Codes: F03D 80/10 Arrangements for warning air traffic
• CPC Class Codes: F05B 2270/8041 Cameras
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 7/13 Edge detection
• 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 7/74 involving reference images or patches
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19
• CPC Class Codes: G06V 20/00 Scenes; Scene-specific elements control of digital cameras H04N23/60
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: H04N 13/239 using two 2D image sensors having a relative position equal to or related to the interocular distance H04N13/243 takes precedence
• CPC Class Codes: H04N 23/51 Housings
• CPC Class Codes: H04N 23/69 Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming
• CPC Class Codes: H04N 23/698 for achieving an enlarged field of view, e.g. panoramic image capture
• CPC Class Codes: H04N 23/90 : Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
• CPC Class Codes: Y02E 10/72 : Wind turbines with rotation axis in wind direction

Abstract

Provided herein are detection systems and related methods for detecting moving objects in an airspace surrounding the detection system. In an aspect, the moving object is a flying animal and the detection system comprises a first imager and a second imager that determines position of the moving object and for moving objects within a user selected distance from the system the system determines whether the moving object is a flying animal, such as a bird or bat. The systems and methods are compatible with wind turbines to identify avian(s) of interest in airspace around wind turbines and, if necessary, take action to minimize avian strike by a wind turbine blade.

Claims

1. An avian detection system for detecting a flying avian in an airspace comprising:

a first imager having a wide field of view for detecting a moving object;

a second imager having a high zoom;

a positioner operably connected to the second imager for positioning the second imager to image the moving object detected by the first imager;

a processor operably connected to receive image data from the first imager, the second imager, or both to identify a moving object that is a flying avian based on said image data;

wherein the avian detection system provides substantially complete hemispherical coverage of said airspace surrounding the avian detection system.

2. The avian detection system of claim 1, comprising a plurality of said first imagers arranged in a spatial configuration to provide substantially complete hemispherical coverage.

3. The avian detection system of claim 1, wherein said first imager comprises a fish-eye lens or detector configured to image visual data from a substantially hemispherical surrounding airspace.

4. The avian detection system of claim 1, wherein the substantially complete hemispherical coverage provides coverage for a volume of airspace having a detection distance from said first imager that is greater than or equal to 0.6 km and less than or equal to 2 km.

5. The avian detection system of claim 4, having a detection efficiency for a selected avian species of interest that is greater than 96%.

6. The avian detection system of claim 5, having a percentage of false positives for said flying avian species of interest that is less than or equal to 5% for said volume of airspace.

7. The avian detection system of claim 5, wherein said avian species of interest comprises a golden eagle or an endangered flying avian species.

8. The avian detection system of claim 1, wherein said processor identifies an output of a subset of pixels of said first imager or said second imager corresponding to said moving object.

9. The avian detection system of claim 8, wherein said subset of pixels comprises neighboring pixels, directly adjacent pixels, or both.

10. The avian detection system of claim 8, wherein said output of said subset of pixels is an array of intensity values.

11. The avian detection system of claim 8, wherein said output of said subset of pixels is a time varying output.

12. The avian detection system of claim 8, wherein said processor analyzes said output of said subset of pixels to determine if said moving object is a said flying avian.

13. The avian detection system of claim 8, wherein said processor analyzes said output to identify the presence of one or more threshold identification attributes.

14. The avian detection system of claim 13, wherein said one or more threshold identification attributes is a boundary parameter.

15. The avian detection system of claim 14, wherein said boundary parameter corresponds to an edge boundary signature characteristic of said flying avian.

16. The avian detection system of claim 15, wherein said edge boundary signature is identified by determining an intensity gradient of said output of said subset of pixels.

17. The avian detection system of claim 16, wherein said edge boundary signature is identified by comparing said intensity gradient to one or more reference values.

18. The avian detection system of claim 15, wherein said edge boundary signature corresponds to an edge straightness parameter.

19. The avian detection system of claim 18, wherein said output is identified as corresponding to an artificial object for said edge straightness parameter indicative of an artificially constructed straight line.

20. The avian detection system of claim 15, wherein said edge boundary signature corresponds to a flying avian.

21. The avian detection system of claim 15, wherein said edge boundary signature corresponds to a threatened or endangered avian species of interest.

22. The avian detection system of claim 13, wherein said one or more threshold identification attributes is a time evolution parameter.

23. The avian detection system of claim 22, wherein said time evolution parameter corresponds to a time evolution signature characteristic of movement of said flying avian.

24. The avian detection system of claim 13, wherein said one or more threshold identification attributes is a color parameter.

25. The avian detection system of claim 24, wherein said color parameter corresponds to a color signature characteristic of said flying avian.

26. The avian detection system of claim 13, wherein upon identification of the presence of said one or more threshold identification attributes, said processor analyzes said output of said subset of pixels to determine one or more avian identification parameters.

27. The avian detection system of claim 26, wherein said processor compares said output of said subset of pixels to one or more reference values in a reference image database to determine if said moving object is a said flying avian.

28. The avian detection system of claim 26, wherein said processor compares said output of said subset of pixels to reference values to determine one or more avian identification parameters selected from the group consisting of size, speed, wing span, wing shape, color, boundary shape, geometry, light intensity, and flight trajectory.

29. The avian detection system of claim 17, wherein said reference values are provided in a reference image database or determined using one or more reference image algorithms.

30. The avian detection system of claim 8, wherein said processor analyzes said output of said subset of pixels via a pattern recognition algorithm.

31. The avian detection system of claim 30, wherein said pattern recognition algorithm identifies said subset of pixels as a species of said flying avian.

32. The avian detection system of claim 31, wherein said avian species comprises a threatened or endangered raptor species.

33. The avian detection system of claim 8, wherein the processor analyzes said output of said subset of pixels from a plurality of frames of said image data, wherein said subset of pixels spatially moves with time and said movement with time is used to determine a trajectory of said output of said subset of pixels.

34. The avian detection system of claim 33, wherein said trajectory comprises positions, distances, velocities, directions or any combination thereof at a plurality of times.

35. The avian detection system of claim 34, further comprising determining a predictive trajectory corresponding to a future time interval.

36. The avian detection system of claim 30, wherein said pattern recognition algorithm comprises a database of physical parameters associated with a flying avian species of interest, and the processor compares a physical parameter determined from said first imager or said second imager to a corresponding physical parameter from said database of physical parameters to filter out moving objects that are not a flying avian or are not a flying avian species of interest.

37. The avian detection system of claim 36, wherein said flying avian of interest is an endangered raptor species or a golden eagle.

38. The avian detection system of claim 1, wherein said processor filters moving objects that do not correspond to an avian species of interest.

39. The avian detection system of claim 1, wherein said first imager has a horizontal and vertical field of view that is selected from a range that is greater than or equal to 60°

and less than or equal to 120° and

/or a resolution that is selected from a range that is greater than or equal to 8″

per pixel and less than or equal to 14″

per pixel.

40. The avian detection system of claim 1, wherein said second imager has a resolution that is selected from a range that is greater than or equal to 1 cm per pixel and less than or equal to 4 cm per pixel and/or said high zoom is selected from a range that is greater than or equal to 10×

and less than or equal to 1000×

.

41. The avian detection system of claim 1, wherein a plurality of first imagers are arranged in distinct alignment directions to provide full 360°

hemispherical coverage by the plurality of first imagers fields of view up to and including a vertical alignment direction.

42. The avian detection system of claim 41, wherein a moving object is continuously identified for object movement from a first imager field of view to a spatially adjacent second imager field of view.

43. The avian detection system of claim 1, wherein said first imager, said second imager, or both said first and the second imagers detect a wavelength range corresponding to light in the visible or infra-red spectrum.

44. The avian detection system of claim 43, wherein the wavelength range is in the infra-red for identification in low-light or adverse weather conditions.

45. The avian detection system of claim 1, configured to simultaneously identify a plurality of moving objects.

46. The avian detection system of claim 1 used to decrease incidence of avian kills by a wind turbine.

47. The avian detection system of claim 46, wherein said avian is a raptor.

48. The avian detection system of claim 47, wherein said raptor is a golden eagle.

49. The avian detection system of claim 46, comprising a plurality of said first imagers arranged in a spatial configuration to provide the substantially complete hemispherical coverage, wherein one of said first imagers is oriented in an upward direction to cover a region of airspace above the wind turbine.

50. The avian detection system of claim 1, further comprising a controller operably connected to the processor to provide an action implementation.

51. The avian detection system of claim 50, wherein the action implementation is selected from the group consisting of an alarm, an alert to an operator, a count, an active avoidance measure, or a decrease or stop to a wind turbine blade speed when the avian detection system identifies a flying avian that is a threatened or an endangered species having a predicted trajectory in a wind turbine surrounding airspace that will otherwise likely result in wind turbine blade impact.

52. The avian detection system of claim 1, for counting a number of flying avians within said airspace surrounding said avian detection system over a time period.

53. The avian detection system of claim 1 that is stationary.

54. The avian detection system of claim 1 that is mounted to a moving vehicle.

55. The avian detection system of claim 1, wherein said positioner comprises a motorized pan and tilt head connected to said second imager for moving an alignment direction of said second imager based on an output from said first imager.

56. The avian detection system of claim 1, wherein said first imager, said second imager, or both said first and second imagers are cameras.

92. The avian detection system of claim 1, wherein the second imager comprises a stereo imager comprising a pair of second imagers each independently having a high zoom.

93. The avian detection system of claim 1, wherein the second imager comprises a stereo imager comprising a pair of second imagers each independently having a high zoom, said avian detection system further comprising:

at least three wide field of view systems, each providing a field of view between 120° and

140°

;

a ground enclosure containing ancillary equipment electrically connected to said imagers by cables that run through an inner passage within the tower; and

a lightning mitigation system extending from the tower top, wherein the imagers are positioned so as to image airspace around the tower without optical obstruction by the lightning mitigation system.

57. An avian detection system for detecting a flying avian in an airspace comprising:

a first imager having a wide field of view for detecting a moving object;

a stereo imager comprising a pair of second imagers each independently having a high zoom;

a positioner operably connected to the stereo imager for positioning said stereo imager to image said moving object detected by the first imager; and

a processor operably connected to receive image data from said first imager, said stereo imager, or both and to determine a position and trajectory of said moving object, thereby identifying a moving object that is a flying avian based on image data from the first imager, the second imager, or both the first and second imager.

58. The avian detection system of claim 57, providing substantially complete hemispherical coverage of an airspace surrounding the avian detection system.

59. The avian detection system of claim 57, further comprising a plurality of first imagers, a plurality of stereo imagers, or a plurality of first imagers and a plurality of stereo imagers, wherein each of the said imagers are aligned in distinct alignment directions to provide substantially complete hemispherical coverage of airspace surrounding said avian detection system.

60. The avian detection system of claim 57, wherein said processor is wirelessly connected to the imagers.

61. The avian detection system of claim 57, wherein said processor is hard wired to obtain image data output from the first imager, the second imager, or the stereo imager.

62. The avian detection system of claim 57, further comprising:

a plurality of wide field of view systems, wherein said plurality of wide field of view systems in combination provides 360°

imaging coverage around said avian detection system.

63. The avian detection system of claim 62, further comprising:

a tower interface for connecting each of the wide field of view systems and the stereo imager system to a tower.

64. The avian detection system of claim 63, further comprising a substrate having a top surface and a bottom surface, wherein said positioner connects said stereo imager system to said substrate top surface and said wide field of view system is connected to said substrate bottom surface.

65. The avian detection system of claim 63, wherein said tower interface further comprises:

a central interface portion for supporting said stereo imager system and connecting to a top portion of a tower; and

outer support struts for supporting the wide field of view systems.

94. The avian detection system of claim 57, comprising:

at least three wide field of view systems, each providing a field of view between 120° and

140°

;

a ground enclosure containing ancillary equipment electrically connected to said imagers by cables that run through an inner passage within the tower; and

a lightning mitigation system extending from the tower top, wherein the imagers are positioned so as to image airspace around the tower without optical obstruction by the lightning mitigation system.

66. A method of detecting a flying avian in an airspace, the method comprising the steps of:

imaging the airspace surrounding an imaging system;

obtaining one or more threshold identification attributes for an output of a subset of pixels from the imaging step;

analyzing the one or more threshold identification attributes to identify a moving object of interest;

obtaining one or more avian identification parameters for the moving object of interest;

comparing the one or more avian identification parameters to a corresponding one or more reference avian identification parameters to identify the moving object of interest as an avian of interest; and

implementing an action implementation for the avian of interest;

wherein the method detects the flying avian of interest within the airspace having a volume equivalent to an average-equivalent hemisphere with an average radius selected from a range that is greater than or equal to 0.5 km and less than or equal to 1.2 km.

67. The method of claim 66, wherein the imaging step comprises identifying an output of a subset of pixels that is an array of light intensity values.

68. The method of claim 66, wherein the imaging comprises obtaining a wide field of view with a first imager and optically zooming in on the moving object of interest with a second imager, wherein the second imager is used to determine a distance of the moving object of interest from the imaging system.

69. The method of claim 66, for detecting an avian species that is a raptor.

70. The method of claim 66, wherein the imaging step further comprises obtaining a plurality of images at different times and determining a trajectory of the output of the subset of pixels.

71. The method of claim 68, wherein the distance is determined using a stereo imager that is positioned to image the moving object.

72. The method of claim 69, wherein the analyzing step is via a pattern recognition algorithm.

73. The method of claim 66, wherein the one or more threshold identification attributes is selected from the group consisting of distance, trajectory, boundary parameter, boundary shape, edge boundary characteristic, pixel spacing, pixel intensity, pixel color, intensity gradient, time evolution parameter, and any combination thereof.

74. The method of claim 73, wherein the one or more threshold identification attributes is a boundary parameter.

75. The method of claim 74, further comprising the step of comparing the boundary parameter to an edge boundary signature characteristic of a flying avian.

76. The method of claim 74, further comprising the step of identifying a moving object as corresponding to an artificially-constructed object by identifying at least a portion of the boundary parameter as having a shape indicative of an artificially-constructed object.

77. The method of claim 76, wherein the boundary parameter comprises an edge straightness parameter indicative of the artificially constructed object.

78. The method of claim 66, wherein the one or more avian identification parameters is selected from the group consisting of size, speed, wing span, avian posture or ratio of wing span width to height or vice versa (w/h or h/w), wing shape, color, boundary shape, geometry, light intensity, flight trajectory, and a temperature or a heat signature.

79. The method of claim 66, wherein the avian species of interest is a threatened species, an endangered species, or a migratory bird.

80. The method of claim 79, wherein the threatened or endangered species is a raptor.

81. The method of claim 66, wherein the comparing step comprises a pattern recognition algorithm.

82. The method of claim 66, having a detection sensitivity that is greater than 96% and a false positive detection that is less than 5% for a threatened species, endangered species, or a species of interest for the airspace corresponding to a maximum distance from the imaging system that is greater than 0.6 km and less than 1.2 km.

83. The method of claim 66, further comprising the step of obtaining a predictive trajectory of the flying avian.

84. The method of claim 83, used with a wind turbine, the method further comprising the steps of:

decreasing a blade wind turbine speed or stopping movement of the blade turbine to minimize or avoid risk of blade strike by the avian having the predictive trajectory that would otherwise likely result in blade strike of the avian.

85. The method of claim 84, wherein the avian is a species that is a threatened or endangered species.

86. The method of claim 85, wherein the threatened or endangered species is defined under the Endangered Species Act of U.S. law.

87. The method of claim 84, wherein the avian is a golden eagle.

88. The method of claim 84, wherein the blade wind turbine speed is not decreased for an avian species that is identified as not an avian species of interest, thereby maximizing wind turbine efficiency.

89. The method of claim 66, wherein the implementing an action step comprises one or more of:

providing an alert to a person;

emitting an alarm;

triggering a count event;

triggering a deterrent to encourage movement of the flying avian out of the airspace surrounding the first imager;

recording an image or video of the avian flying through the airspace surrounding the first imager;

or decreasing or stopping a wind turbine blade speed.

90. The method of claim 89, further comprising the step of defining an action implementation airspace having an average action distance that is less than the average-equivalent radius of the substantially hemispherical airspace surrounding the imaging system, wherein the action implementation is implemented for a flying avian that is:

within the substantially hemispherical airspace and having a trajectory toward the action implementation airspace;

or

within the action implementation airspace.

91. The method of claim 84, further comprising the step of turbine masking for an image of a flying avian in an optical region containing a moving turbine blade, thereby improving detection.