Unknown Object Classification Through Signal Transform Set
AssigneeThe Government of the United States, as represented by the Secretary of the Army
InventorRobert Diienno
Life of this patent
Estimating the term…
Abstract
Various embodiments are described that relate to classification of an unknown object. A time series signal associated with an unknown object can be obtained from a sensor. The time series signal can be subjected to a transform set, such as a Fourier transform and a discrete cosine transform, to produce a transform outcome. Based, at least in part, on the transform outcome, the unknown object can be classified.
Claims20
An unknown object classification system that is at least partially hardware, the system comprising:
- a reception component configured to receive a time series signal associated with an unknown object, with the time series signal supplying information on a color;
- a transform component configured to perform a transform set upon the time series signal to produce a transform result set;
- and
- a classification component configured to classify the unknown object based, at least in part, on the transform result set.
An unknown object classification system that is at least partially hardware, the system comprising:
- a reception component configured to receive a time series signal associated with an unknown object, with the time series signal supplying information on a color;
- a transform component configured to perform a transform set upon the time series signal to produce a transform result set;
- and
- a classification component configured to classify the unknown object based, at least in part, on the transform result set,
- where the transform set comprises a first transform and a second transform,
- where the transform set result set comprises a first transform result and a second transform result,
- where the first transform is a Fourier transform that produces a Fourier transform result that functions as the first transform result,
- where the second transform is a discrete cosine transform that produces a discrete cosine transform result that functions as the second transform result,
- where the time series signal is a first time series signal,
- where the color is a first color,
- where the transform result set is a first transform result set,
- where the reception component is configured to receive a second time series signal associated with the unknown object, with the second time series signal supplying information on a second color;
- where the transform component is configured to perform the transform set upon the second time series signal to produce a second transform result set,
- where the classification component is configured to classify the unknown object based, at least in part, on the first transform result set and the second transform result set, and
- where the second color is different from the first color.
An unknown object classification system that is at least partially hardware, the system comprising:
- a reception component configured to receive a time series signal associated with an unknown object, with the time series signal supplying information on a color;
- a transform component configured to perform a transform set upon the time series signal to produce a transform result set;
- and
- a classification component configured to classify the unknown object based, at least in part, on the transform result set,
- where the transform set comprises a first transform and a second transform,
- where the transform set result set comprises a first transform result and a second transform result,
- where the first transform is a Fourier transform that produces a Fourier transform result that functions as the first transform result,
- where the second transform is a discrete cosine transform that produces a discrete cosine transform result that functions as the second transform result, and
- where the color is gray.
Dependencies are inferred from the claim text.