IMAGE FEATURE IDENTIFICATION AND MOTION COMPENSATION APPARATUS, SYSTEMS, AND METHODS
First Claim
1. An apparatus, comprising:
- a discrete cosine transform (DCT) coder to perform a DCT operation on a set of luminance values associated with a block of pixels selected from an image to obtain a DCT coefficient matrix; and
a feature extraction module operatively coupled to the DCT coder to perform operations on a plurality of DCT coefficients selected from low-frequency bands of the DCT coefficient matrix to derive a value of an image feature strength metric associated with the block of pixels.
2 Assignments
0 Petitions
Accused Products
Abstract
Apparatus, systems, and methods disclosed herein may estimate the magnitude of relative motion between a scene and an image capture device used to capture the scene. Some embodiments may utilize discrete cosine transform and/or Sobel gradient techniques to identify one or more blocks of pixels in an originating calibration image frame. Matching blocks of pixels may be located in a successive calibration image frame. Motion vectors originating at one calibration frame and terminating at the other calibration frame may be calculated. The magnitude of relative motion derived thereby may be used to adjust image capture parameters associated with the image capture device, including exposure settings.
-
Citations
21 Claims
-
1. An apparatus, comprising:
-
a discrete cosine transform (DCT) coder to perform a DCT operation on a set of luminance values associated with a block of pixels selected from an image to obtain a DCT coefficient matrix; and a feature extraction module operatively coupled to the DCT coder to perform operations on a plurality of DCT coefficients selected from low-frequency bands of the DCT coefficient matrix to derive a value of an image feature strength metric associated with the block of pixels. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system, comprising:
-
an image sensor array (ISA) to detect luminance incident to a set of ISA elements and to transform the luminance to create a set of luminance values associated with a pixel representation of an image; a discrete cosine transform (DCT) coder coupled to the ISA to perform a DCT operation on a subset of the set of luminance values to obtain a DCT coefficient matrix, wherein the subset is associated with a block of pixels selected from the image; a feature extraction module coupled to the DCT coder to perform operations on a plurality of DCT coefficients selected from low-frequency bands of the DCT coefficient matrix to derive a value of an image feature strength metric associated with the block of pixels; and target matching logic coupled to the feature extraction module to correlate an image feature as selected from at least one of a first image or a database to an instance of the image feature as searched for in a target image. - View Dependent Claims (10, 11, 12, 13, 14, 15)
-
-
16. A method, comprising:
-
performing a discrete cosine transform (DCT) operation on a set of luminance values associated with a block of pixels selected from an image to obtain a DCT coefficient matrix; and performing a mathematical calculation on a plurality of DCT coefficients selected from low-frequency bands of the DCT coefficient matrix to derive a value of an image feature strength metric associated with the block of pixels. - View Dependent Claims (17, 18, 19, 20, 21)
-
Specification