Object detection apparatus, object detection method, computer program product, and moving object
AssigneeKabushiki Kaisha Toshiba
InventorDaisuke Kobayashi
Life of this patent
Estimating the term…
Abstract
An object detection apparatus includes a calculation section, a first generation section, and a second generation section. The calculation section calculates a plurality of first feature maps from an input image. The first generation section generates a spatial attention map for which a higher first weighted value is defined for an element having a higher relation in terms of a first space on the basis of the first feature maps. The second generation section generates a plurality of second feature maps by performing weighting on each of the first feature maps in accordance with the first weighted value indicated for the spatial attention map. A detection section detects an object included in an input image by using the second feature maps.
Claims11
An object detection apparatus comprising:
- a hardware processor configured to:
- calculate a plurality of first feature maps from an image, at least one feature map having a different amount of an element included in an input image than at least one other feature map from the plurality of first feature maps;
- generates a plurality of first combination maps by subjecting each element group of the first feature maps to a linear embedding process;
- generate a spatial attention map for which a higher first weighted value is defined for a spatial attention map element comprising a higher direction relation in terms of a first space defined by a positional direction in the first feature maps and a relational direction between the first feature maps than a weighted value defined for another spatial attention map element, based at least in part on the first feature maps and the plurality of first combination maps;
- generate a plurality of second feature maps by performing weighting on each of the first feature maps in accordance with a first weighted value indicated for the spatial attention map;
- and
- detect an object included in the input image by using the second feature maps.
An object detection method performed by a computer, the method comprising:
- calculating a plurality of first feature maps from an image, at least one feature map having a different amount of an element included in an input image than at least one other feature map from the plurality of first feature maps;
- generating a plurality of first combination maps by subjecting each element group of the first feature maps to a linear embedding process;
- generating a spatial attention map for which a higher first weighted value is defined for a spatial attention map element comprising a higher relation in terms of a first space defined by a positional direction in the first feature maps and a relational direction between the first feature maps than a weighted value defined for another spatial attention map element, based at least in part on the first feature maps and the plurality of first combination maps;
- generating a plurality of second feature maps by performing weighting on each of the first feature maps in accordance with a first weighted value indicated for the spatial attention map;
- and
- detecting an object included in the input image by using the second feature maps.
A computer program product having a non-transitory computer readable medium comprising instructions, wherein the instructions, when executed by a computer, cause the computer to perform:
- calculating a plurality of first feature maps from an image, at least one feature map having a different amount of an element included in an input image than at least one other feature map from the plurality of first feature maps;
- generating a plurality of first combination maps by subjecting each element group of the first feature maps to a linear embedding process;
- generating a spatial attention map for which a higher first weighted value is defined for a spatial attention map element comprising a higher relation in terms of a first space defined by a positional direction in the first feature maps and a relational direction between the first feature maps than a weighted value defined for another spatial attention map element, based at least in part on the first feature maps and the plurality of first combination maps;
- generating a plurality of second feature maps by performing weighting on each of the first feature maps in accordance with a first weighted value indicated for the spatial attention map;
- and
- detecting an object included in the input image by using the second feature maps.
Dependencies are inferred from the claim text.