Detecting Target Objects in a 3D Space

Abstract

Search points in a search space may be projected onto images from cameras imaging different parts of the search space. Subimages, corresponding to the projected search points, may be selected and processed to determine if a target object has been detected. Based on subimages in which target objects are detected, as well as orientation data from cameras capturing images from which the subimages were selected, positions of the target objects in the search space may be determined.

1 . A method comprising:
 determining, based on images from a plurality of cameras positioned to image portions of a search space, subimages indicating detection of an unmanned aerial vehicle (UAV) in the search space, wherein at least two cameras, of the plurality of cameras, are separated by a distance of at least 100 meters, and wherein the search space covers an area of at least 10,000 square meters;   determining, based on the subimages indicating detection of the UAV in the search space, a position of the UAV in the search space; and   outputting information indicating the position of the UAV.   
     
     
         2 . The method of  claim 1 , wherein each camera, of the plurality of cameras, corresponds to a field of view (FOV), wherein at least a portion of the FOVs are smaller than the search space, and wherein each camera, of the plurality of cameras, is capable of moving independently of the other cameras of the plurality of cameras. 
     
     
         3 . The method of  claim 1 , further comprising:
 assigning a subset of a plurality of search points to the UAV;   determining, based on the position of the UAV, search point spatial positions in the search space for the search points of the subset;   determining, without regard to the position of the UAV, search point spatial positions in the search space for remaining search points of the plurality of search points;   selecting, from additional images from the plurality of cameras and based on the plurality of search points, additional subimages; and   determining, based on at least a portion of the additional subimages, a second position of the UAV in the search space.   
     
     
         4 . The method of  claim 1 , wherein the determining the subimages comprises selecting subimages based on projections, of randomly selected search point spatial positions in the search space, onto the images. 
     
     
         5 . The method of  claim 1 , further comprising:
 performing, based on the information indicating the position of the UAV, one or more countermeasures to disable or destroy the UAV.   
     
     
         6 . The method of  claim 1 , further comprising:
 selecting, for each search point spatial position of a plurality of search point spatial positions, a random location in the search space.   
     
     
         7 . The method of  claim 1 , further comprising:
 ignoring, based on a determination that at least one subimage comprises at least one of a man-made object or a natural object, the at least one subimage.   
     
     
         8 . A computing device comprising:
 one or more processors; and   memory storing instructions that, when executed by the one or more processors, cause the computing device to:
 determine, based on images from a plurality of cameras positioned to image portions of a search space, subimages indicating detection of an unmanned aerial vehicle (UAV) in the search space, wherein at least two cameras, of the plurality of cameras, are separated by a distance of at least 100 meters, and wherein the search space covers an area of at least 10,000 square meters; 
 determine, based on the subimages indicating detection of the UAV in the search space, a position of the UAV in the search space; and 
 output information indicating the position of the UAV. 
   
     
     
         9 . The computing device of  claim 8 , wherein each camera, of the plurality of cameras, corresponds to a field of view (FOV), wherein at least a portion of the FOVs are smaller than the search space, and wherein each camera, of the plurality of cameras, is capable of moving independently of the other cameras of the plurality of cameras. 
     
     
         10 . The computing device of  claim 8 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
 assign a subset of a plurality of search points to the UAV;   determine, based on the position of the UAV, search point spatial positions in the search space for the search points of the subset;   determine, without regard to the position of the UAV, search point spatial positions in the search space for remaining search points of the plurality of search points;   select, from additional images from the plurality of cameras and based on the plurality of search points, additional subimages; and   determine, based on at least a portion of the additional subimages, a second position of the UAV in the search space.   
     
     
         11 . The computing device of  claim 8 , wherein the instructions, when executed by the one or more processors, cause the computing device to determine the subimages by selecting subimages based on projections, of randomly selected search point spatial positions in the search space, onto the images. 
     
     
         12 . The computing device of  claim 8 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
 perform, based on the information indicating the position of the UAV, one or more countermeasures to disable or destroy the UAV.   
     
     
         13 . The computing device of  claim 8 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
 select, for each search point spatial position of a plurality of search point spatial positions, a random location in the search space.   
     
     
         14 . The computing device of  claim 8 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
 ignore, based on a determination that at least one subimage comprises at least one of a man-made object or a natural object, the at least one subimage.   
     
     
         15 . A non-transitory computer-readable medium comprising instructions that, when executed, cause a computing device to:
 determine, based on images from a plurality of cameras positioned to image portions of a search space, subimages indicating detection of an unmanned aerial vehicle (UAV) in the search space, wherein at least two cameras, of the plurality of cameras, are separated by a distance of at least 100 meters, and wherein the search space covers an area of at least 10,000 square meters;   determine, based on the subimages indicating detection of the UAV in the search space, a position of the UAV in the search space; and   output information indicating the position of the UAV.   
     
     
         16 . The non-transitory computer-readable medium of  claim 15 , wherein each camera, of the plurality of cameras, corresponds to a field of view (FOV), wherein at least a portion of the FOVs are smaller than the search space, and wherein each camera, of the plurality of cameras, is capable of moving independently of the other cameras of the plurality of cameras. 
     
     
         17 . The non-transitory computer-readable medium of  claim 15 , wherein the instructions, when executed, cause the computing device to:
 assign a subset of a plurality of search points to the UAV;   determine, based on the position of the UAV, search point spatial positions in the search space for the search points of the subset;   determine, without regard to the position of the UAV, search point spatial positions in the search space for remaining search points of the plurality of search points;   select, from additional images from the plurality of cameras and based on the plurality of search points, additional subimages; and   determine, based on at least a portion of the additional subimages, a second position of the UAV in the search space.   
     
     
         18 . The non-transitory computer-readable medium of  claim 15 , wherein the instructions, when executed, cause the computing device to determine the subimages by selecting subimages based on projections, of randomly selected search point spatial positions in the search space, onto the images. 
     
     
         19 . The non-transitory computer-readable medium of  claim 15 , wherein the instructions, when executed, cause the computing device to:
 perform, based on the information indicating the position of the UAV, one or more countermeasures to disable or destroy the UAV.   
     
     
         20 . The non-transitory computer-readable medium of  claim 15 , wherein the instructions, when executed, cause the computing device to:
 select, for each search point spatial position of a plurality of search point spatial positions, a random location in the search space.   
     
     
         21 . The non-transitory computer-readable medium of  claim 15 , wherein the instructions, when executed, cause the computing device to:
 ignore, based on a determination that at least one subimage comprises at least one of a man-made object or a natural object, the at least one subimage.