Detecting target objects in a 3D space
AssigneeScience Applications International Corporation
InventorsStephen Eric Bramlett, Michael Harris Rodgers
Life of this patent
Estimating the term…
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.
Claims23
A method comprising:
- determining, based on a plurality of search point spatial positions distributed throughout a three-dimensional search space, and from images from a plurality of cameras positioned to image different portions of the search space, a set of subimages corresponding to at least a portion of the search point spatial positions;
- determining, from the set of subimages, a first plurality of subimages to ignore based on a determination that a search point image position, associated with each of the first plurality of subimages, is within a predetermined distance of an edge of an image;
- determining, from a portion of the set of subimages that remains after ignoring the first plurality of subimages, a second plurality of subimages comprising a target object image;
- determining whether two subimages, of the second plurality of subimages comprising a target object image, comprise target object images corresponding to a same target object;
- determining, based on the second plurality of subimages comprising a target object image and based on a determination of whether the two subimages comprise target object images corresponding to a same target object, positions of target objects in the search space;
- and
- outputting information indicating the positions of the target objects.
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 a plurality of search point spatial positions distributed throughout a three-dimensional search space, and from images from a plurality of cameras positioned to image different portions of the search space, a set of subimages corresponding to at least a portion of the search point spatial positions;
- determine, from the set of subimages, a first plurality of subimages to ignore based on a determination that a search point image position, associated with each of the first plurality of subimages, is within a predetermined distance of an edge of an image;
- determine, from a portion of the set of subimages that remains after ignoring the first plurality of subimages, a second plurality of subimages comprising a target object image;
- determine whether two subimages, of the second plurality of subimages comprising a target object image, comprise target object images corresponding to a same target object;
- determine, based on the second plurality subimages comprising a target object image and based on a determination of whether the two subimages comprise target object images corresponding to a same target object, positions of target objects in the search space;
- and
- output information indicating the positions of the target objects.
A non-transitory computer-readable medium comprising instructions that, when executed, cause a computing device to:
- determine, based on a plurality of search point spatial positions distributed throughout a three-dimensional search space, and from images from a plurality of cameras positioned to image different portions of the search space, a set of subimages corresponding to at least a portion of the search point spatial positions;
- determine, from the set of subimages, a first plurality of subimages to ignore based on a determination that a search point image position, associated with each of the first plurality of subimages, is within a predetermined distance of an edge of an image;
- determine, from a portion of the set of subimages that remains after ignoring the first plurality of subimages, a second plurality of subimages comprising a target object image;
- determine whether two subimages, of the second plurality of subimages comprising a target object image, comprise target object images corresponding to a same target object;
- determine, based on the second plurality of subimages comprising a target object image and based on a determination of whether the two subimages comprise target object images corresponding to a same target object, positions of target objects in the search space;
- and
- output information indicating the positions of the target objects.
Dependencies are inferred from the claim text.