Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
Response to Arguments
Applicant's arguments filed 07/08/2026 have been fully considered and a new ground of rejection is provided below. Some arguments regarding Kantorovich and Pysden are addressed below.
Applicant argues that Kantorovich does not teach a punching glove “for measuring punch force data developing during a punch” because Kantorovich relies on IMU sensors and converts acceleration data into an estimated force via a regression model. Applicant points to paragraph [0219] of Kantorovich, which states:
“If a load sensor is not present in gloves, then it is necessary to convert data received from e.g. IMU sensor present in gloves into a force.”
Applicant further asserts that “measuring” requires direct physical measurement by a load sensor and that mathematical estimation from IMU data is technically and physically distinct.
This argument is not persuasive. First, the claim language is “for measuring punch force data developing during a punch.” The term “measuring” is given its broadest reasonable interpretation consistent with the specification. The specification does not define “measuring” to exclude force values obtained by processing sensor data, nor does it limit the glove to a particular sensor type (load cell, piezoelectric, IMU-derived, etc.).
Second, Kantorovich itself expressly contemplates the presence of a load sensor in the glove. The language relied upon by Applicant is conditional (“If a load sensor is not present…”). The converse is therefore also disclosed: when a load sensor is present, force is obtained directly from that sensor. In addition, Kantorovich lists “force sensor” and “pressure sensor” among the sensors that may be associated with the glove ([0096], [0215]–[0217], [0223], [0284]). Thus, Kantorovich teaches both direct force sensing and IMU-based estimation. Either embodiment satisfies the broad claim language “measuring punch force data.”
Even if the claim were construed to require a direct load-sensor measurement, the combination with Devassy is unaffected because the primary reference already discloses the capability. The distinction drawn by Applicant between direct and estimated force, while technically real, does not create a patentable difference under the broadest reasonable interpretation of the claim language as written.
Applicant argues that Kantorovich relies on standard 2D pose tracking (OpenPose) and does not teach linking images from a plurality of cameras captured at the exact same point of time to calculate 3D trajectories of recognized body segments of both a first athlete and a second athlete.
This argument is addressed by the newly applied secondary reference Devassy (US 2022/0129669 A1). Devassy is directed to multi-camera 3D body-part labeling and performance metrics in combat sports (explicitly boxing with two athletes in a ring). Devassy teaches:
a plurality of image capture units (preferably at least four) positioned around the perimeter of the ring, each capturing simultaneous views of both athletes;
receipt of synchronized 2D image data and 3D depth data from the plurality of cameras at the same timestamp;
transformation of the multi-view data into a common reference frame; and
averaging of visible 3D body-part locations across views to produce accurate 3D poses and trajectories of the body segments of both athletes, while compensating for occlusions.
(See Devassy, [0002]-[0003], [0029]-[0030], [0124]-[0127], Figs. 15A–B and 16);
The combination of Kantorovich’s glove-force and rule-set evaluation unit with Devassy’s multi-camera synchronized 3D body-segment tracking of both athletes directly supplies the missing limitations. One of ordinary skill would have recognized that replacing or augmenting Kantorovich’s single-view or multi-view 2D pose estimation with Devassy’s more robust multi-view 3D reconstruction would improve the reliability of the positional data fed into the existing rule-set evaluation, particularly under the occlusion conditions common in combat sports.
Applicant contends that Kantorovich determines hits exclusively through probabilistic machine-learning classification or impact-wave heuristics, whereas the amended claim requires a deterministic geometric evaluation of whether a body segment of a first athlete is in a predetermined proximity to a body segment of a second athlete. Applicant further argues that modifying Kantorovich to perform the claimed geometric evaluation would change its principle of operation (MPEP § 2143.01) and that neither reference recognizes the problem of false-positive “phantom hits” solved by the proximity check.
These arguments are not persuasive for several reasons.
First, Devassy expressly teaches analysis of the 3D body-part locations of two athletes to determine “contact between objects/body parts” and related performance metrics such as energy transferred upon contact and “effective aggression” (landing punches). See Devassy, [0029]-[0030]. The detection of contact between body parts of two athletes in 3D space is the functional equivalent of evaluating whether one body segment is in a predetermined proximity to another. Once the 3D trajectories are available (as taught by Devassy), determining spatial proximity or contact is a straightforward geometric calculation that one of ordinary skill would understand how to implement.
Second, the principle of operation of Kantorovich is automated, objective quantification and scoring of combat-sports actions by fusing force data with body-position data under stored rules. Adding a more accurate geometric proximity check derived from multi-view 3D data does not change that principle; it merely improves the quality of one of the inputs (the body-segment / positional data) that the evaluation unit already uses. The overall architecture involving glove force, body-segment data and rule set for automatic score remains the same. MPEP § 2143.01 does not prohibit improvements that enhance accuracy or reliability within the same overall principle of operation.
Third, the motivation to combine is clear and does not rely on hindsight. Both references operate in the identical field of automated analysis of combat sports. Kantorovich already fuses force and pose data to decide whether a score should be awarded. Devassy provides a superior method of obtaining accurate 3D body-segment data for two athletes and of detecting contact between those body segments. One of ordinary skill seeking to reduce false-positive scores caused by force data alone or by occluded single-view pose estimates would have been motivated to incorporate Devassy’s multi-view 3D contact analysis into Kantorovich’s existing evaluation framework. The predictable result is a system that awards a score only when both the measured punch force and a geometrically confirmed proximity/contact between the relevant body segments satisfy the rule set—precisely the claimed invention.
Applicant’s remaining arguments concerning lack of formal scoring, lack of motivation, and hindsight are likewise unpersuasive. The rejection has been updated to rely on both Devassy and Pysden. Pysden supplies an explicit electronic scoring machine and rule sets that convert force and location data into formal point or damage values with fully automatic output ([0109], [0139]–[0150]). One of ordinary skill, starting from Kantorovich’s force-plus-pose evaluation framework, would have been motivated to incorporate (1) Devassy’s multi-camera synchronized 3D tracking and proximity/contact evaluation to obtain more reliable hit determinations, and (2) Pysden’s dedicated scoring machine and formal point-based rule sets to convert those high-confidence determinations into standardized, referee-free scores. All three references operate in the identical field of automated objective scoring and analysis of martial arts and combat sports. The combination yields the predictable result of more accurate geometric hit verification paired with formal automatic score output.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 11-15, 17-22 are rejected under 35 U.S.C. 103 as being unpatentable over Kantorovich (US 2021/0001174 A1) in view of Devassy (US 2022/0129669 A1) and further in view of Pysden (US 2012/0203361 A1).
11. Kantorovich discloses a system (Figs. 1-3) for automated score awarding (via hit counter, performance metrics, or insights that function as scores) in combat sports (e.g., martial arts), [0001], [0089]–[0090], [0210], comprising:
at least one punching glove for measuring punch force data developing during a punch (sensors located in the fighter’s glove, including force sensor, pressure sensor, and load-sensor embodiments; force data collected and used for scoring/insights), [0096], [0215]–[0217], [0219], [0223], [0284];
a plurality of cameras for capturing images of a first athlete and a second athlete (video cameras and depth cameras above the fighting area that capture the fighters; the system tracks the position of the fighters (plural) and distinguishes between them, e.g., by clothing color or pose data), [0101], [0114], [0174], and related discussion of cameras monitoring the fighting area containing both athletes;
a body segment recognition module connected to the … cameras for determining body segment data of the … athlete from the images captured by the … cameras (pose estimation via OpenPose or similar algorithms that recognize anatomical points and body segments of the fighters), [0173]–[0174], [0325];
a rule set module, in which a rule set of a predetermined combat sport is stored, wherein the rule set provides a score for a punch with a predetermined minimum punch force at a predetermined position of body segment data (classification models/rules stored in the processing unit that define valid scoring events requiring minimum force/impact and correct anatomical target position; outcomes such as hit/block/miss), [0041]–[0045], [0210], [0252], [0322], [0326];
an evaluation unit, which is connected to the punching glove for receiving the punch force data, which is connected to the body segment recognition module for receiving the body segment data, and which is connected to the rule set module for receiving the at least one rule set; wherein the evaluation unit is configured to output a score fully automatically at an output when both the punch force measured by the punching glove and the body segment data determined by the body segment recognition module result in a score according to the rule set (processing unit/server connected to the glove sensors, camera/pose module, and rule/classification models; outputs a hit-counter increment, performance metric, or equivalent score fully automatically only when the dual conditions of force threshold and positional requirement are met), [0046]–[0050], [0210], [0252], [0322], [0326].
However, Kantorovich does not explicitly teach the body segment recognition module being configured to link images of the plurality of cameras that were captured at the same point of time, wherein the determined body segment data comprises 3D trajectories of recognized body segments; and the system being configured to use the body segment data to determine that a hit has occurred by evaluating whether a body segment of a first athlete is in a predetermined proximity to a body segment of a second athlete.
Devassy teaches a multi-camera system for combat sports (boxing with two athletes) that provides: the body segment recognition module configured to link images of the plurality of cameras that were captured at the same point of time, wherein the determined body segment data comprises 3D trajectories of recognized body segments (receives synchronized 2D image data and 3D depth data from the plurality of cameras at the same timestamp; transforms the multi-view data into a common reference frame; averages visible 3D body-part locations across views to produce accurate 3D poses and trajectories of both athletes while compensating for occlusions), [0002]-[0003], [0124]-[0127], Figs. 15A–B and 16;
and analysis of the resulting 3D body-part data to determine contact / proximity between body parts of the two athletes (performance metrics include “contact between objects/body parts,” energy transferred upon contact, and effective aggression such as landing punches), [0029]-[0030].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Kantorovich’s system by incorporating Devassy’s technique of linking images from the plurality of cameras that were captured at the same point of time in order to generate 3D trajectories of the body segments of both athletes, and by using those 3D trajectories to evaluate whether a body segment of one athlete is in predetermined proximity/contact with a body segment of the other athlete. Kantorovich already uses camera-derived body-segment/pose data as one of the two required inputs to its rule-based evaluation unit and already employs a plurality of cameras covering both fighters. Devassy provides a more robust multi-view method of processing that same camera data to obtain true 3D trajectories and to verify actual spatial interaction between the two athletes. One of ordinary skill would have been motivated to make this modification in order to improve the accuracy and occlusion resistance of the body-segment data fed into Kantorovich’s existing evaluation unit, thereby reducing false-positive hit determinations that can occur with 2D or single-view pose estimation in the close-quarters environment of combat sports. This is a predictable enhancement of an existing multi-camera pose-based scoring system.
The combination of Kantorovich and Devassy teaches the dual-condition evaluation (measured force and geometrically confirmed body-segment proximity) but does not explicitly teach converting the resulting hit determinations into formal point-based or damage-value scores using a dedicated scoring machine.
Pysden teaches an electronic scoring system for martial arts that includes a dedicated scoring machine and rule sets that convert force and location data into formal point or damage values and automatically award those scores ([0109], [0139]–[0150]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify the Kantorovich– Devassy combination by incorporating Pysden’s dedicated scoring machine and formal point-based / damage-value rule sets. The Kantorovich– Devassy combination already produces high-confidence determinations that a valid hit has occurred (measured force + 3D proximity-confirmed contact). Pysden provides a known, mature architecture for converting precisely such force-and-location hit data into standardized, fully automatic combat-sport scores. One of ordinary skill would have been motivated to make this further modification in order to achieve fully objective, referee-free formal scoring output, which is the explicit goal of both Kantorovich (automated insights/metrics) and Pysden (electronic scoring). This is a predictable application of a known scoring-machine technique to an improved hit-detection platform.
12. Kantorovich, Devassy, and Pysden disclose the system according to claim 11, further comprising a scoring counter system, which is connected to the evaluation unit for receiving the scores output by the evaluation unit, and a video verification system connected to the at least one camera, wherein the video verification system is configured to output the images captured by the at least one camera of a period of time to be verified, and a score of the scoring counter system is updatable or correctable, respectively, after verification on the video verification system, Kantorovich [0200]–[0210]; Pysden [0109], [0139]–[0150].
13. Kantorovich, Devassy, and Pysden disclose the system according to claim 12, wherein the video verification system is connected to the evaluation unit and wherein the evaluation unit is configured to output a signal for verifying an action of the first athlete or the second athlete to the video verification system when only a predetermined punch force or only a predetermined position of body segment data according to the rule set of the predetermined combat sport is present, Kantorovich [0149]–[0152], [0200]–[0210].
14. Kantorovich, Devassy, and Pysden disclose the system according to claim 11, wherein at least two rule sets of respectively different combat sports are stored in the rule set module and the rule set module has an interface for selecting the rule set used by the evaluation unit, Kantorovich [0089], [0252], [0322], [0326].
15. Kantorovich, Devassy, and Pysden disclose the system according to claim 11, wherein the body segment recognition module is configured to recognize anatomical points on the first athlete and the second athlete recognized in the images for determining the body segment data and to connect the body segment data by means of segments, Kantorovich [0173]–[0174], [0325]; Devassy [0030], [0126]-[0131], Fig. 16.
17. Kantorovich, Devassy, and Pysden disclose the system according to claim 11, wherein the punching glove is further configured to record speed data and/or acceleration data, wherein the system further comprises a technique recognition module, which is connected to the punching glove for receiving the speed data and/or acceleration data and which is connected to the body segment recognition module for receiving the body segment data, wherein the technique recognition module is configured to recognize a technique of the first athlete or second athlete from the body segment data in combination with the speed data and/or acceleration data, wherein the evaluation unit is connected to the technique recognition module and takes the recognized technique into account in the score awarding, Kantorovich [0096], [0215]–[0217], [0223], [0270], [0284].
18. Kantorovich, Devassy, and Pysden disclose the system according to claim 17, wherein the recognized technique comprises a punch technique determined by the speed data and/or acceleration data and/or an overall movement technique recognized by the body segment data, Kantorovich [0270].
19. Kantorovich, Devassy, and Pysden disclose the system according to claim 11, further comprising a machine learning module, which is connected to the evaluation unit, the punching glove, the body segment recognition module, and/or the technique recognition module, wherein the machine learning module comprises an interface for receiving feedback regarding a score and/or a technique and is configured to adapt an evaluation logic of the evaluation unit and/or of the technique recognition module or to generate a new rule set for the rule set module Kantorovich, [0149], [0165], [0173]–[0174], [0220].
20. Kantorovich, Devassy, and Pysden disclose the system according to claim 11, wherein the evaluation unit is configured to output combat statistics, the technique recognition module is configured to output technique statistics, the punching glove is configured to output technique intensity data, the body segment recognition module is configured to output a technique animation and/or kinematic analysis data, and the cameras are configured to output visual data, Kantorovich [0110], [0164], Figs. 3 & 8; Devassy [0030].
21. Kantorovich, Devassy, and Pysden disclose the system according to claim 11, wherein the at least one camera comprises four cameras, Devassy [0126]; Kantorovich [0036]–[0039], [0194].
22. Kantorovich, Devassy, and Pysden disclose the system according to claim 15, wherein the anatomical points include joint points and wherein the segments include at least ten, at least fifteen, or at least twenty segments, Kantorovich [0038]–[0040], [0101], [0174]–[0175]; Devassy [0073], [0128], (504: Fig. 5), Fig. 16.
Filing of New or Amended Claims
The examiner has the initial burden of presenting evidence or reasoning to explain why persons skilled in the art would not recognize in the original disclosure a description of the invention defined by the claims. See Wertheim, 541 F.2d at 263, 191 USPQ at 97 (“[T]he PTO has the initial burden of presenting evidence or reasons why persons skilled in the art would not recognize in the disclosure a description of the invention defined by the claims.”). However, when filing an amendment an applicant should show support in the original disclosure for new or amended claims. See MPEP § 714.02 and § 2163.06 (“Applicant should specifically point out the support for any amendments made to the disclosure.”). Please see MPEP 2163 (II) 3. (b)
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Correspondence
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SENG H LIM whose telephone number is (571)270-3301. The examiner can normally be reached Monday-Friday (9-5).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Xuan Thai can be reached at (571) 272-7147. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Seng H Lim/Primary Examiner, Art Unit 3715
Prosecution Insights