US 10,872,400 B1Granted

Spectral selection and transformation of image frames

AssigneeVulcan Inc.

InventorMichael Persiantsev

Life of this patent

Estimating the term…

Loading patent…

Abstract

An image comprising a set of pixels is obtained and a dominant hue is determined. A color value of individual pixels in a subset of the set of pixels that fall within the hue range is modified to produce a first transformed image. A filter is applied to the first transformed image or an image derived from the first transformed image to reduce spatial high frequency noise and derive a low frequency image. A high frequency image is generated based on the first transformed image and the low frequency image. Whether the high frequency image depicts the object at a target image frequency is determined based on specified criteria for an object, and if the high frequency image corresponds to the target image frequency, the high frequency image is stored.

Claims21

Dependent claims

A computer-implemented method, comprising:

obtaining an image frame of a sequence of image frames, the image frame comprising a set of pixels that includes digital representations of a first object and a second object, the first object being one of a set of objects of interest associated with specified criteria;
determining, based at least in part on a frequency of occurrence of hues in the set of pixels, a dominant hue of the set of pixels;
determining, based at least in part on the dominant hue, a range of hues to modify, the range of hues including the dominant hue;
modifying a color characteristic of each pixel in a subset of the set of pixels that fall within the range of hues to produce a spectrally transformed image;
generating a spatially transformed image by iteratively:
applying a high frequency reduction function to the spectrally transformed image or an image derived from the spectrally transformed image to derive a low frequency image;
generating, based at least in part on differences between the low frequency image and the spectrally transformed image or the image derived from the spectrally transformed image, a high frequency image;
and
determining whether the high frequency image is the spatially transformed image based at least in part on whether the high frequency image:
includes a representation of the first object;
and
excludes any representation of the second object;
identifying representations of one or more objects matching the specified criteria in the spatially transformed image, the representations of the one or more objects including the representation of the first object;
and
outputting information that includes locations of the representations of the one or more objects in the spatially transformed image.

12 more elements

A system, comprising:

one or more processors;
and
memory including executable instructions that, if executed by the one or more processors, cause the system to:
obtain an image comprising a set of pixels;
determine a dominant hue of the set of pixels;
determine, based at least in part on the dominant hue, a hue range;
modify a luminosity or saturation value of individual pixels in a subset of the set of pixels that fall within the hue range to produce a first transformed image;
apply a filter to the first transformed image or an image derived from the first transformed image to derive a low frequency image;
generate, based at least in part on the first transformed image and the low frequency image, a high frequency image;
determine, based at least in part on specified criteria for an object, whether the high frequency image depicts the object at a target image frequency;
and
if the high frequency image corresponds to the target image frequency, store the high frequency image.

9 more elements

A non-transitory computer-readable storage medium having stored thereon executable instructions that, if executed by one or more processors of a computer system, cause the computer system to at least:

obtain an image comprising a set of pixels that includes representations of a first object and a second object;
determine a dominant hue of the set of pixels;
determine, based at least in part on the dominant hue, a hue range that includes the dominant hue;
modify a characteristic of individual pixels in a subset of the set of pixels that fall within the hue range to produce a first transformed image;
remove details in the first transformed image to produce a second transformed image;
generate, based at least in part on the first transformed image and the second transformed image, a third transformed image that includes the details;
determine, based at least in part on criteria associated with the first object, that the third transformed image:
includes a representation of the first object;
and
excludes a representation of the second object;
and
identify representations of one or more objects matching the criteria in the third transformed image.

9 more elements

Dependencies are inferred from the claim text.