`
`
`
`UNITED STATES PATENT AND TRADEMARK OFFICE
`
`____________________
`
`BEFORE THE PATENT TRIAL AND APPEAL BOARD
`
`____________________
`
`SAMSUNG ELECTRONICS CO., LTD.; AND
`SAMSUNG ELECTRONICS AMERICA, INC.
`Petitioner
`
`v.
`
`IMAGE PROCESSING TECHNOLOGIES, LLC
`Patent Owner
`
`____________________
`
`Patent No. 8,989,445
`____________________
`
`PETITION FOR INTER PARTES REVIEW
`OF U.S. PATENT NO. 8,989,445
`
`
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`TABLE OF CONTENTS
`
`Contents
`INTRODUCTION ........................................................................................... 1
`
`I.
`
`II. MANDATORY NOTICES UNDER 37 C.F.R. § 42.8 ................................... 1
`
`III.
`
`PAYMENT OF FEES UNDER 37 C.F.R. § 42.15(a) .................................... 3
`
`IV. GROUNDS FOR STANDING ........................................................................ 3
`
`V.
`
`PRECISE RELIEF REQUESTED .................................................................. 3
`
`VI. LEGAL STANDARDS ................................................................................... 4
`
`A.
`
`B.
`
`C.
`
`Claim Construction ............................................................................... 4
`
`Level Of Ordinary Skill In The Art ....................................................... 4
`
`This Petition Is Not Redundant ............................................................. 5
`
`VII. OVERVIEW OF THE RELEVANT TECHNOLOGY AND ’445
`PATENT .......................................................................................................... 6
`
`VIII. DETAILED EXPLANATION OF GROUNDS ............................................ 13
`
`A. Overview Of Prior Art ......................................................................... 13
`
`1.
`
`2.
`
`3.
`
`Alton L. Gilbert et al., A Real-Time Video Tracking
`System, PAMI-2 No. 1 IEEE Transactions on Pattern
`Analysis and Machine Intelligence 47 (Jan. 1980)
`(“Gilbert”) (Ex. 1005) ............................................................... 13
`
`U.S. Patent 5,761,326 to Brady (Ex. 1007) .............................. 23
`
`Sylvia Gil, et al., Feature selection for object tracking in
`traffic scenes, SPIE Vol. 2344 Intelligent Vehicle
`Highway Systems (1994) (“Gil”) (Ex. 1019) ........................... 28
`
`4.
`
`U.S. Patent 5,150,432 to Ueno (Ex. 1021) ............................... 29
`
`IX. EXPLANATION OF GROUNDS FOR INVALIDITY ............................... 32
`
`i
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`A. Gilbert In View Of Brady Discloses Each Element Of
`Unchallenged Claims From Which Challenged Claims Depend ........ 32
`
`1.
`
`2.
`
`3.
`
`4.
`
`Reasons To Combine Gilbert And Brady ................................. 32
`
`Elements Incorporated Into Claims 2, 3, 5, 7, 8, 10-17,
`And 19 From Claims On Which These Claims Depend ........... 34
`
`Elements Incorporated Into Claims 26, 28, 29, And 30
`From Claims On Which These Claims Depend ....................... 39
`
`Gilbert And Brady Are Not Cumulative ................................... 42
`
`B.
`
`Ground 1: Gilbert In View Of Brady and Further In View Of
`Gil Renders Obvious Challenged Claims 2, 3, 5, 7, 8, 10-16,
`19-22, 26, and 30 ................................................................................. 43
`
`1.
`
`2.
`
`3.
`
`4.
`
`5.
`
`6.
`
`7.
`
`Reasons To Combine Gilbert With Brady And Further
`With Gil ..................................................................................... 43
`
`Claim 2: “The process of claim 1, wherein the input
`signal is smoothed based on information for the plurality
`of pixels in the first frame and the plurality of pixels in
`the second frame” ...................................................................... 45
`
`Claim 3: “The process of claim 1, wherein the first frame
`is adjacent the second frame in the input signal” ..................... 47
`
`Elements Incorporated Into Claims 5, 7, And 8 As
`Claims Dependent From A Dependent Claim: “The
`process of claim 1, further comprising displaying an
`outline associated with the target at a display location
`based on the target location” [4] ............................................... 48
`
`Claim 5: “The process of claim 4, wherein displaying the
`outline includes adjusting a size of the outline” ....................... 50
`
`Claim 7: “The process of claim 4, wherein the outline is a
`box” ........................................................................................... 51
`
`Claim 8: “The process of claim 7, wherein the box is a
`rectangle” .................................................................................. 52
`
`
`
`
`
`-ii-
`
`
`
`

`

`8.
`
`9.
`
`Petition for Inter Partes Review
`Patent No. 8,989,445
`Claim 10: “The process of claim 1, further comprising
`determining a target speed” ...................................................... 53
`
`Claim 11: “The process of claim 10, wherein determining
`the target speed includes determining a direction using a
`first matrix and a magnitude using a second matrix” ............... 54
`
`10. Claim 12: “The process of claim 1, further comprising
`generating multiple histograms in multiple domains for
`determining a movement of the target” .................................... 56
`
`11. Claim 13: “The process of claim 1, further comprising
`identifying a non-moving area in the first and second
`frames of the input signal and forming a signal
`corresponding to a spatial position of the non-moving
`area within the first and second frames” ................................... 57
`
`12. Claim 14: “The process of claim 1, wherein generating
`the histogram based on classification values of the
`plurality of pixels in the first frame includes identifying a
`rectangular area within the first frame that defines the
`plurality of pixels” .................................................................... 59
`
`13. Claim 15: “The process of claim 14, further comprising
`increasing a size of the rectangular area” ................................. 59
`
`14. Claim 19: “The process of claim 1, further comprising
`actuating a servomotor in a camera based on adjusting
`the target location” .................................................................... 60
`
`15. Claim 20 .................................................................................... 61
`
`16. Claim 21: “The process of claim 20, wherein adjusting
`the camera includes actuating a servomotor” ........................... 66
`
`17. Claim 22: “The process of claim 20, wherein determining
`movement of the target includes identifying an edge of
`the target in the first and second frames” ................................. 67
`
`18. Claim 26: “The image processing system of claim 24,
`wherein the processing system is further configured to
`adjust a size of the outline based on the histogram based
`
`
`
`
`
`-iii-
`
`
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`on the first frame and the histogram based on the second
`frame” ........................................................................................ 69
`
`19. Claim 30: “The image processing system of claim 24,
`further comprising a servomotor configured to adjust the
`camera, and wherein the processing system is further
`configured to adjust the camera based on the adjusted
`target location” .......................................................................... 70
`
`C.
`
`Ground 2: Gilbert In View Of Brady and Further In View Of
`Ueno Renders Obvious Challenged Claims 16, 17, and 23 ................ 71
`
`1.
`
`2.
`
`3.
`
`4.
`
`Reasons To Combine Gilbert With Brady And Further
`With Ueno ................................................................................. 71
`
`Claim 16: “The process of claim 1, wherein identifying
`the target from the histogram generated based on the first
`frame includes receiving an input designating a position
`for the target” ............................................................................ 75
`
`Claim 17: “The process of claim 16, wherein receiving
`the input designating the position for the target includes
`receiving a user input, and further comprising
`determining, based on the updated histogram, an updated
`position for the target” .............................................................. 76
`
`Claim 23: “The process of claim 20, wherein the target is
`a face”........................................................................................ 77
`
`D. Ground 3: Gilbert In View Of Brady and Further In View Of
`Ueno And Gil Renders Obvious Challenged Claims 28 and 29 ......... 78
`
`1.
`
`2.
`
`3.
`
`Reasons To Combine Gilbert With Brady And Further
`With Ueno and Gil .................................................................... 78
`
`Claim 28: “The image processing system of claim 24,
`wherein the processing system is further configured to
`receive a user input to designate a center position for the
`target” ........................................................................................ 78
`
`Claim 29: “The image processing system of claim 28,
`wherein the processing system is further configured to
`
`
`
`
`
`-iv-
`
`
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`determine updated center position for the target based on
`the histogram generated based on the first frame and the
`histogram generated based on the second frame” ..................... 79
`
`X.
`
`CONCLUSION .............................................................................................. 80
`
`
`
`
`
`
`
`-v-
`
`
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`LIST OF EXHIBITS1
`
`1001
`1002
`1003
`1004
`1005
`
`1006
`1007
`1008
`1009
`
`1010
`
`1011
`1012
`1013
`1014
`1015
`1016
`1017
`1018
`1019
`
`U.S. Patent No. 8,989,445 (“the ’445 Patent”)
`Declaration of Dr. John C. Hart
`Curriculum Vitae for Dr. John C. Hart
`Prosecution File History of U.S. Patent No. 8,989,445
`Alton L. Gilbert et al., A Real-Time Video Tracking System,
`PAMI-2 No. 1 IEEE Transactions on Pattern Analysis and
`Machine Intelligence 47 (Jan. 1980) (“Gilbert”)
`Reserved
`U.S. Patent 5,761,326 (“Brady”)
`Reserved
`D. Trier, A. K. Jain and T. Taxt, “Feature Extraction Methods
`for Character Recognition-A Survey”, Pattern Recognition, vol.
`29, no. 4, 1996
`M. H. Glauberman, “Character recognition for business
`machines,” Electronics, vol. 29, pp. 132(136), Feb. 1956
`Declaration of Gerard P. Grenier (authenticating Ex. 1005)
`Reserved
`Reserved
`Reserved
`Reserved
`Reserved
`Reserved
`Reserved
`Sylvia Gil, et al., Feature selection for object tracking in traffic
`scenes, SPIE Vol. 2344 Intelligent Vehicle Highway Systems
`(1994) (“Gil”)
`U.S. Patent No. 5,911,012 (“Bernard”)
`1020
`U.S. Patent 5,150,432 (“Ueno”)
`1021
`Reserved
`1022
`Reserved
`1023
`
`
` 1
`
` Citations to non-patent publications are to the original page numbers of the
`
`publication, and citations to U.S. patents are to column:line number of the patents.
`
`vi
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`Declaration of E. Pepper Authenticating Ex. 1019
`
`1024
`
`vii
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`I.
`
`INTRODUCTION
`
`Samsung Electronics Co., Ltd. and Samsung Electronics America, Inc.
`
`(collectively, “Petitioner”) request inter partes review (“IPR”) of Claims 2, 3, 5, 7,
`
`8, 10-17, 19-23, 26, and 28-30 of U.S. Patent No. 8,989,445 (“the ’445 Patent”;
`
`Ex. 1001), which, on its face, is assigned to Image Processing Technologies, LLC
`
`(“Patent Owner”). This Petition presents several non-cumulative grounds of
`
`invalidity that the U.S. Patent and Trademark Office (“PTO”) did not consider
`
`during prosecution. These grounds are each likely to prevail, and this Petition,
`
`accordingly, should be granted on all grounds and the challenged claims should be
`
`cancelled.
`
`II. MANDATORY NOTICES UNDER 37 C.F.R. § 42.8
`Real Parties-in-Interest: Petitioner identifies the following real parties-in-
`
`interest: Samsung Electronics Co., Ltd.; Samsung Electronics America, Inc.
`
`Related Matters: Patent Owner has asserted the ’445 Patent against
`
`Petitioner in Image Processing Technologies LLC v. Samsung Elecs. Co., No.
`
`2:16-cv-00505-JRG (E.D. Tex.). Patent Owner has also asserted U.S. Patent Nos.
`
`6,959,293; 7,650,015; 8,805,001; 8,983,134; and 6,717,518 in that action.
`
`Petitioner is concurrently filing IPR petitions for all of these asserted patents, as
`
`well as an additional petition challenging the ’445 Patent. Petitioner has
`
`previously filed the following IPR petitions against the ’445 Patent and the first
`
`1
`
`

`

`four patents listed above:
`
`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`IPR2017-00357 against the ’445 Patent, filed 11/30/2016.
`
`IPR2017-01212 against the ’445 Patent, filed 3/30/2017.
`
`IPR2017-00336 against U.S. Patent No. 6,959,293, filed 11/29/2016.
`
`IPR2017-00347 against U.S. Patent No. 8,805,001, filed 11/29/2016.
`
`IPR2017-00355 against U.S. Patent No. 7,650,015, filed 11/30/2016.
`
`IPR2017-00353 against U.S. Patent No. 8,983,134, filed 11/30/2016.
`
`IPR2017-01190 against U.S. Patent No. 6,717,518, filed 3/29/2017.
`
`IPR2017-01189 against U.S. Patent No. 6,959,293, filed 3/30/2017.
`
`Lead and Back-Up Counsel:
`
`• Lead Counsel: John Kappos (Reg. No. 37,861), O’Melveny & Myers
`
`LLP, 610 Newport Center Drive, 17th Floor, Newport Beach,
`
`California 92660. (Telephone: 949-823-6900; Fax: 949-823-6994;
`
`Email: jkappos@omm.com)
`
`• Backup Counsel: Nicholas J. Whilt (Reg. No. 72,081), Brian M. Cook
`
`(Reg. No. 59,356), O’Melveny & Myers LLP, 400 S. Hope Street, Los
`
`Angeles, CA 90071. (Telephone: 213-430-6000; Fax: 213-430-6407;
`
`Email: nwhilt@omm.com, bcook@omm.com)
`
`Service Information: Samsung consents to electronic service by email to
`
`IPTSAMSUNGOMM@OMM.COM. Please address all postal and hand-delivery
`
`2
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`correspondence to lead counsel at O’Melveny & Myers LLP, 610 Newport Center
`
`Drive, 17th Floor, Newport Beach, California 92660, with courtesy copies to the
`
`email address identified above.
`
`III. PAYMENT OF FEES UNDER 37 C.F.R. § 42.15(a)
`The Office is authorized to charge an amount in the sum of $26,200 to
`
`Deposit Account No. 50-2862 for the fee set forth in 37 C.F.R § 42.15(a), and any
`
`additional fees that might be due in connection with this Petition.
`
`IV. GROUNDS FOR STANDING
`Petitioner certifies that the ’445 Patent is available for IPR and Petitioner is
`
`not barred or estopped from requesting IPR on the grounds identified herein.
`
`V.
`
`PRECISE RELIEF REQUESTED
`
`Petitioner respectfully requests review of Claims 2, 3, 5, 7, 8, 10-17, 19-23,
`
`26, and 28-30 (the “Challenged Claims”) of the ’445 Patent, and cancellation of
`
`these claims, based on the grounds listed below:
`
`• Ground 1: Claims 2, 3, 5, 7, 8, 10-15, 19-22, 26, and 30 are obvious
`
`under 35 U.S.C. § 103(a) over Gilbert in view of Brady and further in
`
`view of Gil;
`
`• Ground 2: Claims 16, 17, and 23 are obvious under 35 U.S.C. §
`
`103(a) over Gilbert in view of Brady and further in view of Ueno;
`
`• Ground 3: Claims 28 and 29 are obvious under 35 U.S.C. § 103(a)
`
`3
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`over Gilbert in view of Brady and further in view of Ueno and further
`
`in view of Gil.
`
`A detailed mapping of Gilbert, Brady, Gil, and Ueno to the Challenged Claims of
`
`the ’445 Patent is also provided, which shows that Grounds 1-3 teach or suggest
`
`every feature recited in the Challenged Claims. Ex. 1002, ¶183.
`
`VI. LEGAL STANDARDS
`A. Claim Construction
`The ’445 Patent will expire on July 22, 2017—within 18 months of the
`
`Notice of Filing Date. Thus, for purposes of this proceeding, Petitioner has
`
`interpreted each claim term according to its plain and ordinary meaning under
`
`Phillips v. AWH Corp., 415 F.3d. 1303, 1316 (Fed. Cir. 2005). For purposes of
`
`invalidity raised in this proceeding, petitioner does not believe any term needs an
`
`explicit construction.
`
`Level Of Ordinary Skill In The Art
`
`B.
`One of ordinary skill in the art at the time of the alleged invention of the
`
`’445 Patent would have had either (1) a Master’s Degree in Electrical Engineering
`
`or Computer Science or the equivalent plus at least a year of experience in the field
`
`of image processing, image recognition, machine vision, or a related field or (2) a
`
`Bachelor’s Degree in Electrical Engineering or Computer Science or the equivalent
`
`plus at least three years of experience in the field of image processing, image
`
`4
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`recognition, machine vision, or a related field. Additional education could
`
`substitute for work experience and vice versa. Ex. 1002, ¶¶51-53.
`
`C. This Petition Is Not Redundant
`This Petition is not redundant to the concurrently filed petition challenging
`
`the ’445 Patent IPR2017-01212, as this Petition relies on entirely different prior art
`
`and, as a result, the arguments presented in this Petition are substantially different
`
`than those made in the concurrent petition. This Petition is also not redundant to
`
`earlier filed IPR2017-00357 (the “’357 Petition”) pertaining to the ’445 Patent.
`
`First, this Petition is necessitated because after Samsung filed the ’357 Petition,
`
`Patent Owner moved to add new claims to its infringement contentions that were
`
`originally served August 16, 2016, over three months earlier in the EDTX
`
`litigation. The motion for leave to amend was granted February 28, 2017. Thus,
`
`Samsung promptly prepared and filed this second Petition to address the newly-
`
`added claims. See, e.g., Microsoft Corp. v. Proxyconn, Inc., Case No. IPR2013-
`
`00109, slip op., 3 (P.T.A.B. Feb. 25, 2014) (Paper 15) (instituting IPR because
`
`additional claims asserted in concurrent district court litigation). Samsung has also
`
`included any remaining, unchallenged, claims in this Petition as a protective
`
`measure against IPT continuing to assert new claims in the district court litigation.
`
`See Silicon Labs. Inc. v. Cresta Tech. Corp., Case No. IPR2015-00615, slip op. 24
`
`(P.T.A.B. Aug. 14, 2015) (Paper 9) (instituting where petitioner filed to “challenge
`
`5
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`the remaining claims that the Patent Owner may likely assert in the district court
`
`case”).
`
`Second, this petition raises new arguments not raised in the ’357 Petition.
`
`See id. For example, this Petition seeks institution on all new claims that were not
`
`the subject of the ’357 Petition. See, e.g., Cepheid v. Roche Molecular Sys., Inc.,
`
`Case No. IPR2015-00881 (P.T.A.B. Sept. 17, 2015) (Paper 9). This Petition does
`
`not seek institution on any claim that was the subject of the earlier ’357 Petition.
`
`Because these new claims have different scope, this Petition raises new arguments
`
`to address new limitations. Moreover, all grounds are new—although this Petition
`
`relies on certain references applied in the ’357 Petition, each ground incorporates
`
`at least one additional reference to address the limitations of the newly-added
`
`claims. Facebook, Inc. v. TLI Commc’ns, LLC, Case No. IPR2015-00778, Paper
`
`17, 26-27 (P.T.A.B. Aug. 28, 2015) (instituting where prior art and arguments were
`
`not substantially similar to previous petitions).
`
`VII. OVERVIEW OF THE RELEVANT TECHNOLOGY AND ’445
`PATENT
`
`The ’445 Patent’s purported invention relates to identifying and tracking a
`
`target in an input signal using one or more histograms derived from an image
`
`frame in a video signal. See Ex. 1001, Claim 1; Ex. 1002, ¶32. Video image
`
`processing and the use of histograms to identify and track targets, and to derive
`
`other information from a video signal were well known at the time the asserted
`
`6
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`patents were filed. Ex. 1002, ¶¶24-33, 49-50, 55, 70-71, 80-81, 83. An input
`
`signal used in the purported invention has “a succession of frames, each frame
`
`having a succession of pixels.” Ex. 1001, 3:34-37; Ex. 1002, ¶34. The ’445 Patent
`
`teaches a process for smoothing the input signal on a pixel-by-pixel basis using a
`
`time constant that is modified depending on whether there is significant variation
`
`between such a pixel and the same pixel in a previous frame. Ex. 1001, 4:62-5:3;
`
`Ex. 1002, ¶34. The ’445 Patent then constructs a histogram “showing the
`
`frequency of pixels meeting a certain characteristic or characteristics. Ex. 1002,
`
`¶35. These characteristics are used to form histograms are referred to as
`
`“domains” in the ’445 Patent. Ex. 1002, ¶35. The ’445 Patent teaches that “the
`
`domains are preferably selected from the group consisting of i) luminance, ii)
`
`speed (V), iii) oriented direction (DI), iv) time constant (CO), v) hue, vi)
`
`saturation, and vii) first axis (x(m)), and viii) second axis (y(m)).” Ex. 1001, 4:9-
`
`13; Ex. 1002, ¶35. Figure 11 shows histogram processors that can create
`
`histograms in various domains:
`
`7
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`The histograms include a plurality of “classes” within a given domain. Ex.
`
`1002, ¶36. Figure 14a (and its accompanying description) illustrates an example of
`
`“classes” within a domain:
`
`
`
`8
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`
`
`FIG. 14a shows an example of the successive classes C1
`
`C2…Cn−1 Cn, each representing a particular velocity,
`
`for a hypothetical velocity histogram, with their being
`
`categorization for up to 16 velocities (15 are shown) in
`
`this example. Also shown is envelope 38, which is a
`
`smoothed representation of the histogram.
`
`Ex. 1001, 20:51-56; Ex. 1002, ¶¶36-38. The ’445 Patent then uses the histograms
`
`to identify a target in the input signal. For example, one embodiment of the ’445
`
`Patent performs “automatic framing of a person…during a video conference.” Ex.
`
`1001, 22:6-8 and Figure 15:
`
`9
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`
`
`The system constructs histograms in the X and Y domains counting the
`
`number of pixels where the differences in luminance between successive frames
`
`are above certain threshold values. Ex. 1001, 22:47-57, 10:35-63; Ex. 1002, ¶39.
`
`Figures 16 and 17 show camera setup and the histogram constructed using this
`
`method:
`
`Ex. 1001, Fig. 16
`
`
`
`Ex. 1001, Fig. 17
`
`
`
`10
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`In addition, the system may also be used to automatically track a target by “a
`
`spotlight or a camera. Using a spotlight the invention might be used on a
`
`helicopter to track a moving target on the ground, or to track a performer on a stage
`
`during an exhibition. The invention would similarly be applicable to weapons
`
`targeting systems.” Ex. 1001, 23:38-43; Ex. 1002, ¶40. It does this by
`
`determining the center of the target. Ex. 1002, ¶41.
`
`Once the center of the target is determined, the center is used to adjust the
`
`camera or spotlight to be directed to the moving target, for example using
`
`servomotors:
`
`Having acquired the target, controller 206 controls
`
`servomotors 208 to maintain the center of the target in
`
`the center of the image…It will be appreciated that as the
`
`target moves, the targeting box will move with the target,
`
`constantly adjusting the center of the targeting box based
`
`upon the movement of the target, and enlarging and
`
`reducing the size of the targeting box. The targeting box
`
`may be displayed on monitor 212, or on another monitor
`
`as desired to visually track the target.
`
`Ex. 1001, 25:10-24; Ex. 1002, ¶¶41-45. Figure 23 shows an example of the
`
`targeting box in a frame:
`
`11
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`Ex. 1001 at Fig. 23
`
`
`
`The ’445 Patent also teaches that a user may provide computer input, such as
`
`a mouse, to select a specific target. Ex. 1002, ¶46. “The pixel position [selected
`
`by the user] is then used as a starting position for tracking the target.” Ex. 1001,
`
`23:65-24:3. In this mode of operation the system will process the pixels
`
`immediately adjacent to the starting pixel in successively larger areas surrounding
`
`the starting pixel until the edge of the target is determined and the entire target is
`
`within the tracking box. The progression from Figure 21 to Figure 23
`
`demonstrates this process:
`
`
`
`12
`
`

`

`
`
`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`
`
`Similarly, the ’445 Patent teaches a method by which the system will
`
`“process pixels only within a user-defined area.” Ex. 1001, 21:14-26; Ex. 1002,
`
`¶47-48. For example, the system can receive user input instructing it to “process
`
`pixels only in a defined rectangle by setting the XMIN and XMAX, and YMIN and
`
`YMAX values as desired.” Id.
`
`VIII. DETAILED EXPLANATION OF GROUNDS
`A. Overview Of Prior Art
`1.
`Alton L. Gilbert et al., A Real-Time Video Tracking System,
`PAMI-2 No. 1 IEEE Transactions on Pattern Analysis and
`Machine Intelligence 47 (Jan. 1980) (“Gilbert”) (Ex. 1005)
`
`The ’445 Patent’s purported invention relates to a process of identifying a
`
`target in digitized visual input by using histograms of pixel characteristics and
`
`tracking the target. However, researchers at U.S. Army White Sands Missile
`
`Range, New Mexico, in collaboration with New Mexico State University, Las
`
`Cruces, had already developed a system that utilizes histograms to identify and
`
`13
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`track targets, and they published their findings in January 1980, more than 17 years
`
`before the earliest effective filing date of the ’445 Patent. Ex. 1002, ¶55-70; Ex.
`
`1011.
`
`The article, entitled “A Real-Time Video Tracking System,” published in
`
`IEEE Transactions on Pattern Analysis and Machine Intelligence in January 1980
`
`(“Gilbert”), qualifies as prior art under pre-AIA § 102(b). Gilbert describes “a
`
`system for missile and aircraft identification and tracking…applied in real time to
`
`identify and track objects.” Ex. 1002, ¶56; Ex. 1005, 47. Gilbert was not of record
`
`and was not considered during prosecution of the ’445 Patent. The Gilbert system
`
`includes an image processing system comprising a Video Processor, a Projection
`
`Processor, a Tracker Processor, and a Control Processor as shown in Figure 1,
`
`reproduced below. Ex. 1005, 48.
`
`
`
`14
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`The Video Processor receives an input of digitized video signal comprising
`
`60 fields/s. Ex. 1002, ¶57; Ex. 1005,Gilbert at 48. Each field (half of an interlaced
`
`frame) consists of a succession of n X m pixels:
`
`As the TV camera scans the scene, the video signal is
`
`digitized at m equally spaced points across each
`
`horizontal scan. During each video field, there are n
`
`horizontal scans which generate an n X m discrete matrix
`
`representation at 60 fields/s [i.e., 30 frames/s].
`
`Ex. 1005, 48.
`
`The Video Processor calculates histograms of pixel intensity in each region
`
`of a tracking window (background region, plume region, and target region) in the
`
`256 gray-level classes of the intensity domain. Id. at 49 (“As each pixel in the
`
`region is processed, one (and only one) element of H is incremented as h[x(j)]  h
`
`[x(j)] + 1. When the entire region has been scanned, h contains the distributions of
`
`pixels over intensity and is referred to as the feature histogram of the region R.”);
`
`see also Ex. 1002, ¶¶58-63, Fig. 2 (below).
`
`15
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`
`
`Although Gilbert uses histograms in the intensity domain as examples, it
`
`also notes that other “features that can be functionally derived from relationship
`
`between pixels, e.g., texture, edge, and linearity measure” may be used. Ex. 1005,
`
`48; Ex. 1002, ¶59.
`
`Each feature histogram is normalized to a probability density function and a
`
`“linear recursive estimator and predictor [10] is utilized to establish learned
`
`estimates of the density functions. Letting H(i|j) represent the learned estimate of a
`
`density function for the ith field using the sampled density functions hi(x) up to the
`
`jth field, we have the linear estimator H(i|i)=ω H(i|i- 1)+(1 - ω)hi(x) and linear
`
`predictor H(i + 1|i) = 2H(i|i) - H(i - 1|i - 1).” Id., 49. Ex. 1002, ¶¶58-63.
`
`These learned density functions derived from histogram statistics are used as
`
`classification thresholds to classify pixels in the target region as target,
`
`background, or plume:
`
`Assuming equal a priori probabilities and equal
`
`misclassification costs, the classification rule decides that
`
`16
`
`

`

`a given pixel feature x is a background pixel if
`
`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`
`
`HBi(x)>HT
`
`
`
`i(x) and HBi(x)>HPi(x), a target pixel if HT
`
`
`
`i(x)
`
`
`
`>HBi(x) and HT
`
`
`
`i(x) >HPi(x), or a plume pixel if
`
`
`
`
`
`
`
`HPi(x)>HBi(x) and HPi(x)>HT
`
`i(x).
`
`The results of this decision rule are stored in a high-speed
`
`classification memory during the vertical retrace period.
`
`With the pixel classification stored in the classification
`
`memory, the real-time pixel classification is performed
`
`by simply letting the pixel intensity address the
`
`classification memory location containing the desired
`
`classification.
`
`Id., 50.
`
`This identification process may be done for one target/plume/background
`
`set, or two different target/plume/background sets simultaneously. Ex. 1005, 48
`
`(“Although one tracking window is satisfactory for tracking missile targets with
`
`plumes, two windows are used to provide additional reliability and flexibility for
`
`independently tracking a target and plume, or two targets.”); Ex. 1002, ¶60-63.
`
`The Tracker Processor then uses the target classification results to track the
`
`target:
`
`17
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`[T]he tracking processor extracts the important inputs,
`
`classifies the current tracking situation, and establishes
`
`an appropriate tracking strategy to control the tracking
`
`optics for achieving the goals of the tracking system.
`
`Id., 51. In particular:
`
`The tracker processor establishes a confidence weight for
`
`its inputs, computes boresight and zoom correction
`
`signals, and controls the position and shape of the target
`
`tracking window to implement an intelligent tracking
`
`strategy.
`
`Id., 52. The tracking window data is then fed back to the Video Processor:
`
`Outputs to Video Processor: 1) tracking window size, 2)
`
`tracking window shape, and 3) tracking window position.
`
`. . . The outputs to the video processor define the size,
`
`shape, and position of the tracking window. These are
`
`computed on the basis of the size and shape of the target
`
`image and the amount of jitter in the target image
`
`location.
`
`Id. Ex. 1002, ¶63. The size, shape, and position of the tracking window, in turn,
`
`control which pixels are included in each of the BR, PR, and TR histograms of
`
`18
`
`

`

`pixel intensity that are acquired by the Video Processor:
`
`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`The tracking window frame is partitioned into a
`
`background region (BR) and a plume region (PR). The
`
`region inside the frame is called the target region (TR) as
`
`shown in Fig. 2. During each field, the feature histograms
`
`are accumulated for the three regions of each tracking
`
`window.
`
`Id., 48. Thus, the statistical data derived from the intensity histograms is used to
`
`control the location and size of the tracking windows, which, in turn, select which
`
`pixels will be included in each intensity histogram. See Ex. 1002, Hart Decl. ¶¶58-
`
`63.
`
`A Projection Processor creates projections using only the pixels identified
`
`for inclusion. Ex. 1002, ¶57. Although these projections are not explicitly referred
`
`to by Gilbert as projection histograms, reference to Figure 4 of Gilbert (annotated
`
`below) clearly shows four different projection histograms formed using the target
`
`pixels:
`
`19
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`
`
`
`Ex. 1002, ¶¶64-65. These Figure 4 projections will be referred to as projection
`
`histograms throughout this petition. Ex. 1002, ¶65.
`
`The Projection Processor then identifies the target location, orientation, and
`
`structure using the projection histograms:
`
`The target location, orientation, and structure are
`
`characterized by the pattern of 1 entries in the binary
`
`picture matrix, and the target activity is characterized by
`
`20
`
`

`

`Petition for Inter Partes Review
`Patent No. 8,989,445
`a sequence of p