Avian detection systems and methods
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.
1. A method of detecting a flying object in an airspace volume, the method comprising the steps of:
imaging the airspace with a plurality of first imagers connected to a tower,
wherein the plurality of first imagers are arranged in fixed and distinct alignment directions to provide substantially complete hemispherical coverage of the airspace volume that surrounds the tower;
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;
positioning a second imager to obtain a high-resolution image of the moving object of interest;
obtaining one or more identification parameters for the moving object of interest from the high-resolution image and/or from an image from the plurality of first imagers;
comparing the one or more identification parameters to a corresponding one or more reference identification parameters to identify the moving object of interest as an avian or an artificially-constructed object;
thereby detecting the flying object in the airspace volume.
2. The method of claim 1 , wherein the first imagers are wide-field-of-view (WFOV) cameras and the second imager comprises a stereo imager connected to the tower by a positioner.
3. The method of claim 2 , further comprising the step of determining with the stereo imager the distance from the tower of the moving object of interest.
4. The method of claim 1 , wherein the airspace volume has a volume that is greater than or equal to 0.45 km 3 and less than or equal to 16.8 km 3 .
5. The method of claim 1 , wherein the threshold identification attributes are initially obtained at a distance from the first imagers of between 0.5 km and 1.6 km.
6. The method of claim 1 , wherein the airspace volume is characterized by an ellipsoid shape.
7. The method of claim 6 , wherein the airspace volume is around an airport runway with a major axis of the ellipsoid arranged in a direction of the airport runway.
8. The method of claim 1 , further comprising the step of arranging at least two detection systems, each detecting system comprising independent plurality of the first imagers and the second imager, wherein the two detection systems together provide coverage of the substantially complete hemispherical airspace volume.
9. The method of claim 1 , further comprising the steps:
providing an image or image data from the plurality of first imagers and/or the second imager to a processor; and
identifying the moving object as the artificially-constructed flying object or the flying avian from the processor.
10. The method of claim 9 , further comprising the step of identifying an output of a subset of pixels of said first imager or said second imager corresponding to said moving object having a boundary parameter or pixel pattern indicative of an artificially-constructed object or a flying avian.
11. The method of claim 10 , wherein said output of said subset of pixels is an array of intensity values and/or is a time varying output.
12. The method of claim 10 , wherein said processor analyzes said output of said subset of pixels, using one or multiple algorithms in combination, such as pattern recognition, edge detection and/or boundary parameter analysis, to determine if said moving object is a flying artificially-constructed object.
13. The method of claim 10 , wherein said boundary parameter corresponds to an edge boundary signature that is:
straight or smooth for the artificial object; or
that is not highly straight or smooth for the avian.
14. The method of claim 1 , 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.
15. The method of claim 1 , wherein the airspace volume is positioned to surround a wind turbine, the method further comprising the steps of:
identifying the moving object as an avian of interest;
implementing an action implementation for the avian of interest that is at risk of striking a moving blade of the wind turbine.
16. The method of claim 15 , wherein the action implementation comprises decreasing a velocity of the wind turbine blades or stopping wind turbine blades.
17. The method of claim 15 , wherein the action implementation occurs before the avian of interest is within 800 m of the wind turbine.
18. The method of claim 15 , wherein the avian of interest is an endangered, threatened, or otherwise of commercial or environmental interest, avian.
19. The method of claim 15 , wherein the implementing step occurs for the flying object that is a threatened or an endangered species having a predicted trajectory that will likely result in wind turbine blade impact.
20. The method of claim 19 , wherein the action implementation is selected from the group consisting of:
an alarm;
an alert to an operator;
a count;
an active avoidance measure; and
a decrease or stop to a wind turbine blade speed.
21. A detection system for detecting a flying object in an airspace volume comprising:
a plurality of first imagers that are fixably positioned in each of a plurality of distinct alignment directions, each of the plurality of first imagers having a wide field of view for detecting a moving object in the airspace volume, wherein the plurality of first imagers are arranged in a spatial configuration to provide coverage of the airspace volume that surrounds the detection system and the airspace volume has a volume of between 0.45 km 3 and 16.8 km 3 ;
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 plurality of first imagers,
wherein the positioner moves an alignment direction of the second imager based on an output from at least one of the plurality of first imagers; and
a processor operably connected to the plurality of first imagers and the second imager receive image data from the plurality of first imagers, the second imager, or both to identify the moving object that is an artificially-constructed flying object or a flying avian based on said image data.
22. The method of claim 1 , wherein the reference identification parameters are obtained from a machine learning application that continuously improves an avian characterization as more reference images are obtained and characterized.
23. The method of claim 19 , further comprising the steps of:
identifying the avian of interest as having:
a position that is within an actionable distance; or
within a detection distance and having a trajectory toward the wind turbine blade;
wherein, for the identified avian of interest having the position that is within the actionable distance or within the detection distance and having the trajectory toward the wind turbine blade, implementing the action implementation comprising a speed decrease or stop of the wind turbine blade to minimize risk of the avian of interest striking the wind turbine blade.