Shijun Sun

US Patent:

6480615, Nov 12, 2002

Filed:

Jun 15, 1999

Appl. No.:

09/333317

Inventors:

Shijun Sun - Seattle WA
Yongmin Kim - Seattle WA

Assignee:

University of Washington - Seattle WA

International Classification:

G06K 900

US Classification:

382103, 382107

Abstract:

The optical flow of an array of pixels in an image field is determined using adaptive spatial and temporal gradients. Artifacts are avoided for image objects which are moving smoothly relative to the image field background. Data from three image frames are used to determine optical flow. A parameter is defined and determined frame by frame which is used to determine whether to consider the data looking forward from frame k to k+1 or the data looking backward from frame k-1 to frame k in initializing spatial and or temporal gradients for frame k. The parameter identifies signifies the areas of occlusion, so that the gradients looking backward from frame k-1 to frame k can be used for the occluded pixel regions. The gradients looking forward are used in the other areas.

US Patent:

6535632, Mar 18, 2003

Filed:

Aug 30, 1999

Appl. No.:

09/386538

Inventors:

Hyun Wook Park - Seattle WA
Lakshmanan Gopishankar - Seattle WA
Shijun Sun - Seattle WA
Yongmin Kim - Seattle WA

Assignee:

University of Washington - Seattle WA

International Classification:

G06K 900

US Classification:

382164, 382162, 382165, 382167, 382173, 382205, 382254, 382260, 382266, 382282, 358515, 358520, 358538

Abstract:

Adaptive noise filtering is applied to an image frame of HSI data to reduce and more uniformly distribute noise while preserving image feature edges. An adaptive spatial filter includes a plurality of averaging kernels. An appropriate kernel is selected for each pixel for each of the hue and saturation components. A set of thresholds are defined for selecting the kernel for the hue component. Another set of thresholds are defined for selecting the kernel for the saturation component. The kernel for the saturation component is selected by comparing the intensity component to the saturation component thresholds. The kernel for the hue component is selected by comparing the product of intensity component and the saturation component to the hue component thresholds. A color gradient operation is applied to the filtered HSI data to aid in detecting image object boundaries. Object segmentation and other image processing techniques may be performed on the filtered HSI data.

US Patent:

6546117, Apr 8, 2003

Filed:

Jun 10, 1999

Appl. No.:

09/323501

Inventors:

Shijun Sun - Seattle WA
Yongmin Kim - Seattle WA

Assignee:

University of Washington - Seattle WA

International Classification:

G06K 900

US Classification:

382103, 382215

Abstract:

A system for image object tracking and segmentation, includes (i) a modified adaptive resonance theory-2 (M-ART2) model for detecting changes of scenes, (ii) a two-dimensional correlative autopredicitve search (2D CAPS) method for object tracking, (iii) a derivation of contour energy for use in modelling an object edge, and (iv) an active contour model with global relaxation for defining optimal image object boundaries. The modelled object boundary is derived from an edge potential energy calculation and a set of current edge points. For each edge point, several candidate data points are also selected. Rather than calculate an energy value for each potential contours, a solution is achieved by comparing energy differences along a travel path. The selected contour is built in steps. An optimal path is selected from the potential paths.

US Patent:

6584224, Jun 24, 2003

Filed:

Aug 23, 2001

Appl. No.:

09/938344

Inventors:

Shijun Sun - Seattle WA
HyunWook Park - Shoreline WA
Yongmin Kim - Seattle WA

Assignee:

University of Washington - Seattle WA

International Classification:

G06K 964

US Classification:

382217, 382181, 382209, 382218, 382278

Abstract:

A template is analyzed to determine a step size for searching within a search area. First, the template is padded with pixels to increase its size. Cross-correlation between the padded template and the original template leads to identification of an effective step size. Step sizes for each of horizontal and vertical axes are derived. Windows of the search area, selected based on the step size, then are tested in a fast search stage by correlating the template to the window. Any tested window which has a correlation coefficient exceeding a specific value is a local match. A full search of the vicinity of the local match then is performed for all potential windows within an area bounded by one step to either side of the local match along either axis. The location(s) corresponding to the highest correlation(s) exceeding the threshold value are matches.

US Patent:

6677868, Jan 13, 2004

Filed:

Dec 12, 2001

Appl. No.:

10/017838

Inventors:

Louis J. Kerofsky - Portland OR
Shijun Sun - Vancouver WA

Assignee:

Sharp Laboratories of America, Inc. - Camas WA

International Classification:

H03M 700

US Classification:

341107, 341 51, 341 67, 341 63

Abstract:

The compression efficiency of variable length coding is preserved by altering the syntax of a bit stream input to a variable length coder if the bit stream is likely to include a symbol with a high occurrence probability.

US Patent:

6678416, Jan 13, 2004

Filed:

Feb 8, 2000

Appl. No.:

09/500116

Inventors:

Shijun Sun - Seattle WA
Yongmin Kim - Seattle WA

Assignee:

University of Washington - Seattle WA

International Classification:

G06K 936

US Classification:

382235

Abstract:

A coarsely estimated object boundary is formed by a sequence of edge boundary points. A local affine transformation along the estimated object boundary is identified by analyzing edge energy of a current image frame. A sequence of edge boundary points which have edge energy change ratios exceeding a threshold value is identified as a local affine transformation. A refined estimate of the object boundary is determined for the local affine transformation using a local segmentation process based on a key contour point search strategy. End points of the contour are assumed to be known. An initial key contour point is derived from the coarsely estimate object boundary. Candidate key points then are derived and corresponding curves analyzed to select a curve as the improved estimated boundary for the local affine transformation. The curve having a minimum average edge energy change ratio is selected.

US Patent:

6731799, May 4, 2004

Filed:

Jun 1, 2000

Appl. No.:

09/587210

Inventors:

Shijun Sun - Seattle WA
Yongmin Kim - Seattle WA

Assignee:

University of Washington - Seattle WA

International Classification:

G06K 930

US Classification:

382173, 382190, 382242, 348142, 348155

Abstract:

Image data for an image frame are allocated among three groups. In one group are image data which are part of a derived motion boundary, along with image data which differ by at least a threshold amount from a corresponding point among normalized background data. In another group are image data which closely correspond to the normalized background image data. A third group includes the remaining pixels. An initial estimate for the object boundary is adjusted iteratively based on the groupings, followed by application of an active contour model.

US Patent:

6782052, Aug 24, 2004

Filed:

Mar 16, 2001

Appl. No.:

09/810349

Inventors:

Shijun Sun - Vancouver WA
Louis Kerofsky - Portland OR

Assignee:

Sharp Laboratories of America, Inc. - Camas WA

International Classification:

H04N 712

US Classification:

37524012

Abstract:

A method provides a fast motion search in advanced video signal coding systems based on a reference-frame prediction and a block-mode prediction so that a motion search of each block mode and each reference frame is not required. A reference frame prediction f , spaced from the current frame by âpâ number of frames, is determined by: p=min(n , p +max(a,b,c,d)); wherein p is a pre-chosen positive integer, n is the total number of reference frames, wherein A, B, C, and D are image blocks adjacent to a searched block, and wherein the reference image blocks have been chosen from reference frames f , f , f and f. The search is conducted within frames f to f , which is a subset of all the n reference frames, so that the total computational burden is significantly decreased with respect to prior art searches. The mode frequency prediction is based on the frequencies of the block modes: F =Âmin(F , F , F , F ); wherein is a positive parameter less than 1. The block-mode selection is then conducted using the mode-frequency prediction.