FAST COMPUTATION OF KERNEL DESCRIPTORS

• US 20140099033A1
• Filed: 10/04/2013
• Published: 04/10/2014
• Est. Priority Date: 10/05/2012
• Status: Active Grant

• Current Assignee: Raytheon BBN Technologies Corp. (Rtx Corporation)
• Original Assignee: Raytheon BBN Technologies Corp. (Rtx Corporation)
• Inventors: Prasad, Rohit, Natarajan, Premkumar, Natarajan, Pradeep, Wu, Shuang
• Granted Patent: US 9,330,332 B2
• Time in Patent Office: Days
• US Class Current: 382/205
• CPC Class Codes: G06F 18/2135 based on approximation criteria, e.g. principal component analysis

Abstract

An approach to computation of kernel descriptors is accelerated using precomputed tables. In one aspect, a fast algorithm for kernel descriptor computation that takes O(1) operations per pixel in each patch, based on pre-computed kernel values. This speeds up the kernel descriptor features under consideration, to levels that are comparable with D-SIFT and color SIFT, and two orders of magnitude faster than STIP and HoG3D. In some examples, kernel descriptors are applied to extract gradient, flow and texture based features for video analysis. In tests of the approach on a large database of internet videos used in the TRECVID MED 2011 evaluations, the flow based kernel descriptors are up to two orders of magnitude faster than STIP and HoG3D, and also produce significant performance improvements. Further, using features from multiple color planes produces small but consistent gains.

Claims

1. A method for processing images comprising:

reading a plurality of stored kernel tables, each kernel table representing a mapping from a corresponding feature to a vector of values;

accepting images for processing, and identifying a plurality of patches within said images;

computing a feature vector F(P) for each patch P of the plurality of patches, including computing one or more summations over locations z in the patch P of terms, each term being a product of terms including a term obtained by a lookup in a corresponding kernel table according to the location z and/or an attribute of the patch P at the location z; and

processing the images according to the computed feature vectors for the plurality of patches.

2. The method of claim 1 wherein F(P) approximates kernel descriptor based on a plurality of kernels.

3. The method of claim 2 wherein F(P) equals or approximates a sum of a form

4. The method of claim 1 wherein processing the images comprises computing similarities between patches as combinations of the computed feature vectors for the patches.

5. The method of claim 1 wherein the images are frames of a video, and wherein at least some of the patches are formed from multiple frames.

6. A method for image processing comprising:

reading a plurality of stored kernel tables, each kernel table representing a mapping from a corresponding feature to a vector of values;

accepting images for processing, and identifying patches within said images;

repeatedly computing similarities between pairs of patches for images being processed, computation of a similarity between a patch P and a patch Q comprises

computing for patch P one or more summations over locations z in the patch P of terms, each term being a product of terms including a term obtained by a lookup in a corresponding kernel table according to the location z and/or an attribute of the patch P at the location z,

computing for patch Q one or more summations over locations z in the patch Q of terms, each term being a product of terms including a term obtained by a lookup in a corresponding kernel table according to the location z and/or an attribute of the patch Q at the location z, and

combining the sums of the one or more summations for P and one or more summations for Q to determine a kernel descriptor similarity between P and Q; and

providing a result of processing the images determined using the computed similarities between the patches.

7. The method of claim 6 further comprising precomputing the kernel tables prior to accepting the images for processing.

8. Software stored on a non-transitory computer-readable medium comprising instructions for causing a processor to:

read a plurality of stored kernel tables, each kernel table representing a mapping from a corresponding feature to a vector of values;

accept images for processing, and identifying a plurality of patches within said images;

compute a feature vector F (P) for each patch P of the plurality of patches, including computing one or more summations over locations z in the patch P of terms, each term being a product of terms including a term obtained by a lookup in a corresponding kernel table according to the location z and/or an attribute of the patch P at the location z; and

process the images according to the computed feature vectors for the plurality of patches.

9. Software stored on a non-transitory computer-readable medium comprising instructions for causing a processor to:

read a plurality of stored kernel tables, each kernel table representing a mapping from a corresponding feature to a vector of values;

accept images for processing, and identifying patches within said images;

repeatedly compute similarities between pairs of patches for images being processed, computation of a similarity between a patch P and a patch Q comprises

computing for patch P one or more summations over locations z in the patch P of terms, each term being a product of terms including a term obtained by a lookup in a corresponding kernel table according to the location z and/or an attribute of the patch P at the location z,

computing for patch Q one or more summations over locations z in the patch Q of terms, each term being a product of terms including a term obtained by a lookup in a corresponding kernel table according to the location z and/or an attribute of the patch Q at the location z, and

combining the sums of the one or more summations for P and one or more summations for Q to determine a kernel descriptor similarity between P and Q; and

provide a result of processing the images determined using the computed similarities between the patches.