US 6700999

US patent 6700999, titled "System, method, and apparatus for multiple face tracking," was filed on June 30, 2000, and issued on March 2, 2004. The original assignee was Intel Corp, and the current assignee is Cedar Lane Technologies Inc. The sole inventor listed is Liuyang Yang.

Abstract:
The patent discloses a system, method, and apparatus for automatically tracking multiple faces in a sequence of digital images. It incorporates temporal filtering to reduce false alarms and missed detections and can operate in multiple modes to optimize processor load.

Plain-Language Overview of Independent Claims:

• Claim 1 (Method): This claim describes a method for tracking multiple face candidates in video. It involves receiving video frames and operating in two modes: a "first operating mode" where face tracking (score map construction, mask production, and mask filtering) is performed for every frame, and a "standby mode" that performs face-tracking operations only on a portion of the frames. The standby mode activates after a specified number of consecutive frames are processed without detecting any face candidate regions.
• Claim 6 (Method with Temporal Filtering): This claim details a method that receives video data, constructs a score map, produces a mask indicating face candidate regions, and then applies temporal filtering to this mask. The temporal filtering involves averaging each entry in the current mask with corresponding entries from at least one temporally distinct mask (from previous and/or subsequent frames).
• Claim 8 (Apparatus): This claim describes an apparatus designed for tracking multiple face candidates in video. It includes a "mapper" to create a score map from video frames, a "segmenter" to generate a mask with face candidate regions from the score map, and a "filter" to refine the mask by removing false alarms. Similar to Claim 1, this apparatus operates in a "normal operational mode" (tracking every frame) and a "standby mode" (tracking only a portion of frames), with the standby mode activating after no face candidates are found for a specified number of consecutive frames.
• Claim 13 (Apparatus with Temporal Filter): This claim describes an apparatus with a mapper, a segmenter, and a filter, where the filter is specifically a "temporal filter." This temporal filter receives the mask and produces a temporally filtered mask by averaging entries with corresponding entries from at least one temporally distinct mask derived from previous and/or subsequent frames.
• Claim 15 (System with Video Encoder): This claim describes a system that combines the face-tracking apparatus (mapper, segmenter, filter) with a video encoder. The video encoder receives both the video frame and the face-tracking mask. Critically, the encoder uses the mask information to allocate a disproportionately higher number of bits to encode regions of the frame that correspond to face candidate regions, improving the quality of the encoded faces.
• Claim 21 (System with Camera Control): This claim describes a system comprising a camera, a face-tracking apparatus (mapper, segmenter, filter with normal and standby modes as in Claim 8), and a camera control unit. The camera control unit receives the face-tracking masks and controls the camera's movement (e.g., position and/or focal length) in response to comparisons of face candidate regions across different frames, ensuring faces remain in the video sequence.
• Claim 25 (System with Camera Control and Temporal Filter): This claim is similar to Claim 21 but specifically incorporates a temporal filter within the face-tracking apparatus. The temporal filter averages mask entries across temporally distinct frames, and the camera control unit then uses these masks (presumably the temporally filtered ones, though the claim refers to "plurality of masks") to control camera movement based on face candidate region comparisons between frames.
• Claim 27 (Apparatus with Data Storage Medium - Method Claim 1 variant): This claim describes an apparatus with a data storage medium containing machine-readable code. This code, when executed, performs the method of tracking face candidate regions as outlined in independent Claim 1, including the first operating mode and the standby mode.
• Claim 32 (Apparatus with Data Storage Medium - Method Claim 6 variant): This claim describes an apparatus with a data storage medium containing machine-readable code. This code, when executed, performs the method of tracking face candidate regions with temporal filtering as outlined in independent Claim 6.

CAFC 2026 Dockets:
A review of the provided CAFC 2026 dockets and scheduled cases did not reveal any specific mentions of US patent 6700999. Therefore, there is no authoritative information available from the search results to indicate active litigation concerning this patent at the Court of Appeals for the Federal Circuit in 2026.

US patent 6700999 has been involved in multiple litigation cases. Based on available information, here's a summary of known litigation:

• Jurisdiction: Texas Western District Court

  • Case Number: 6:22-cv-00124
  • Filing Date: Not explicitly provided in the snippets.
  • Plaintiff(s): Not explicitly provided in the snippets.
  • Defendant(s): Not explicitly provided in the snippets.
  • Outcome/Current Status: Litigation

• Jurisdiction: Texas Western District Court

  • Case Number: 6:21-cv-00923
  • Filing Date: Not explicitly provided in the snippets.
  • Plaintiff(s): Not explicitly provided in the snippets.
  • Defendant(s): Not explicitly provided in the snippets.
  • Outcome/Current Status: Litigation

• Jurisdiction: Texas Western District Court

  • Case Number: 6:20-cv-01189
  • Filing Date: Not explicitly provided in the snippets.
  • Plaintiff(s): Not explicitly provided in the snippets.
  • Defendant(s): Not explicitly provided in the snippets.
  • Outcome/Current Status: Litigation

• Jurisdiction: Texas Western District Court

  • Case Number: 1:20-cv-00352
  • Filing Date: Not explicitly provided in the snippets.
  • Plaintiff(s): Not explicitly provided in the snippets.
  • Defendant(s): Not explicitly provided in the snippets.
  • Outcome/Current Status: Litigation

• Jurisdiction: Texas Southern District Court

  • Case Number: 4:20-cv-01392
  • Filing Date: Not explicitly provided in the snippets.
  • Plaintiff(s): Not explicitly provided in the snippets.
  • Defendant(s): Not explicitly provided in the snippets.
  • Outcome/Current Status: Litigation

• Jurisdiction: California Northern District Court

  • Case Number: 4:20-cv-02369
  • Filing Date: Not explicitly provided in the snippets.
  • Plaintiff(s): Not explicitly provided in the snippets.
  • Defendant(s): Not explicitly provided in the snippets.
  • Outcome/Current Status: Litigation

• Jurisdiction: California Central District Court

  • Case Number: 2:19-cv-08630
  • Filing Date: Not explicitly provided in the snippets.
  • Plaintiff(s): Not explicitly provided in the snippets.
  • Defendant(s): Not explicitly provided in the snippets.
  • Outcome/Current Status: Litigation

• Jurisdiction: Virginia Eastern District Court

  • Case Number: 1:22-cv-00452
  • Filing Date: Not explicitly provided in the snippets.
  • Plaintiff(s): Not explicitly provided in the snippets.
  • Defendant(s): Not explicitly provided in the snippets.
  • Outcome/Current Status: Litigation

Please note that the provided information from Google Patents (Unified Patents Litigation Data) indicates that "Family has litigation" and lists several US cases filed in various district courts. However, specific details such as plaintiffs, defendants, and precise filing dates for each case were not fully extracted from the provided text.

Proceedings overview

The USPTO ODP API reports no AIA trial proceedings on file for US6700999 as of the most recent ingest. A web search for PTAB proceedings related to US6700999 also did not immediately surface any active or past Inter Partes Review (IPR), Post-Grant Review (PGR), or Covered Business Method (CBM) trial proceedings.

Strategic summary

As there are no PTAB proceedings on file according to the USPTO ODP API, and no relevant proceedings were found via web search, all claims of US6700999 remain untested by AIA trial procedures. This means a defendant facing assertion of this patent currently has the full range of prior art grounds available for an IPR challenge, subject to the statutory time bars (e.g., one year from service of a complaint alleging infringement).

Recommended next steps

Since no PTAB activity exists for US6700999, the absence of IPRs could be a signal, depending on the patent's assertion history. Well-asserted patents often attract IPRs.

If facing an assertion of US6700999:

• Conduct a thorough prior art search: Since the claims are untested, a robust prior art search is critical to identify potential grounds for an IPR.
• Assess IPR viability: Analyze the claims against any identified prior art under 35 U.S.C. §§ 102 and 103 to determine if an IPR petition would have a reasonable likelihood of success.
• Consider estoppel implications: Understand that once an IPR is filed and instituted, the petitioner (and its privies) will be estopped from raising grounds raised or that reasonably could have been raised in the IPR in subsequent district court litigation or other USPTO proceedings.
• Monitor for future PTAB filings: Continuously check the USPTO PTAB E2E system for any newly filed petitions against US6700999.## Proceedings overview

The USPTO Open Data Portal API reports no AIA trial proceedings on file for US6700999 as of the most recent ingest. A comprehensive web search for Inter Partes Review (IPR), Post-Grant Review (PGR), or Covered Business Method (CBM) proceedings related to US6700999 did not reveal any active or past cases. Therefore, the bottom-line defensive posture for a defendant is that the patent's claims are entirely untested by AIA trial procedures.

Strategic summary

As of the current date (2026-05-29), all claims of US6700999 remain UNTESTED by any AIA trial proceeding (IPR, PGR, or CBM). This means there are no claims that have been CANCELED or SUSTAINED through PTAB adjudication.

The estoppel landscape is completely open for a potential defendant. Since no PTAB proceedings have occurred, there are no prior-art grounds that have been raised or could have been reasonably raised and are now barred under 35 U.S.C. § 315(e)(2). Any party challenging the patent's validity could assert any available prior art grounds under 35 U.S.C. §§ 102 or 103, subject only to the statutory time bars for filing (e.g., typically one year from the date of service of a complaint alleging infringement).

There are no pattern signals to discern regarding this patent's history at the PTAB, as there is no history to analyze. There is no indication of the patent owner's propensity to appeal PTAB decisions or whether defensive aggregators like Unified Patents have targeted this patent.

Recommended next steps

Given the absence of any PTAB activity on US6700999:

• For a defendant facing assertion of this patent: The primary next step would be to conduct a thorough and expansive prior art search to identify the strongest invalidity grounds. Since the patent's claims have not been subjected to PTAB scrutiny, an IPR petition remains a viable and potentially attractive defensive strategy, depending on the strength of the prior art found.
• For a party considering challenging the patent: Develop a robust IPR petition (or PGR if applicable, although the patent's issue date suggests IPR is more likely) based on comprehensive prior art research.
• Monitor for future filings: Continuously monitor the USPTO Patent Trial and Appeal Board End-to-End (PTAB E2E) system for any newly filed petitions against US6700999. The absence of PTAB activity can sometimes be a signal that a patent has not been extensively asserted or that previous assertions were settled before an IPR could be filed. However, it also means that the patent owner has not had its claims "hardened" by surviving PTAB challenges.

Inventors

Liuyang Yang. Employer at time of filing was Intel Corp. No unusual patterns are determinable from the provided data.

Original assignee

Intel Corp.
Intel Corp. is a multinational corporation and technology company primarily known for manufacturing semiconductor computer circuits. They ship a wide range of products embodying various claims, including microprocessors and other integrated circuits. Intel is currently an operating company.

Assignment timeline

• 2007-12-31 (executed) / recorded 2008-01-08 — Reel 020613/0586
  • Conveyance: Assignment
  • Assignor: Intel Corporation
  • Assignee: Wolford Associates, Limited Liability Company
  • Correspondent: R. Mark Halligan, NIFCO, 1000 SW Broadway, Suite 1500, Portland, OR 97205
  • Context: Fire-sale (transfer of patents from an operating company to an entity likely engaged in patent monetization).
• 2008-01-07 (executed) / recorded 2008-02-13 — Reel 020703/0064
  • Conveyance: Assignment
  • Assignor: Wolford Associates, Limited Liability Company
  • Assignee: Heathway Holdings, LLC
  • Correspondent: David S. Winsted, Dykema Gossett PLLC, 1300 I Street, NW, Suite 300 West, Washington, DC 20005
  • Context: Transfer to asserter.
• 2015-11-19 (executed) / recorded 2015-12-09 — Reel 035974/0270
  • Conveyance: Merger
  • Assignor: Heathway Holdings LLC
  • Assignee: Mineral Lassen LLC
  • Correspondent: Joshua R. King, The Law Office of Joshua R. King, 1720 Windflower Way, McLean, VA 22102
  • Context: Internal reorg/merger of shell entities.
• 2019-01-22 (executed) / recorded 2019-01-30 — Reel 046424/0709
  • Conveyance: Assignment
  • Assignor: Mineral Lassen LLC
  • Assignee: Intellectual Ventures Assets 99 LLC
  • Correspondent: Brian M. Berliner, Arent Fox LLP, 1717 K Street NW, Washington, DC 20006-5342
  • Context: Transfer to asserter (Intellectual Ventures is a known NPE).
• 2019-03-11 (executed) / recorded 2019-03-15 — Reel 046777/0932
  • Conveyance: Assignment
  • Assignor: Intellectual Ventures Assets 99 LLC
  • Assignee: Steephill Technologies LLC
  • Correspondent: Jason S. Okleshen, 2101 Cedar Springs Road, Suite 1000, Dallas, TX 75201. This correspondent recurs on other tracked patents.
  • Context: Transfer to asserter.
• 2019-05-13 (executed) / recorded 2019-05-20 — Reel 047120/0943
  • Conveyance: Assignment
  • Assignor: Steephill Technologies LLC
  • Assignee: Cedar Lane Technologies Inc.
  • Correspondent: Jason S. Okleshen, 2101 Cedar Springs Road, Suite 1000, Dallas, TX 75201. This correspondent recurs on other tracked patents.
  • Context: Transfer to asserter.

Timeline diagram

timeline
    title Ownership of US 6700999
    2000 : Filed by Intel Corp
    2004 : Issued
    2007 : Assigned to Wolford Associates LLC
    2008 : Assigned to Heathway Holdings LLC
    2015 : Merged to Mineral Lassen LLC
    2019 : Assigned to Intellectual Ventures
         : Assigned to Steephill Technologies LLC
         : Assigned to Cedar Lane Tech Inc
    2022 : First infringement suit filed

NPE / troll-pattern signals

1. Shell-entity transfer — present.

   • Wolford Associates, Limited Liability Company (Reel 020613/0586, executed 2007-12-31): Transferred from operating company Intel. The name "Limited Liability Company" suggests a shell entity, and the correspondent for this transfer is a law firm specializing in IP.
   • Heathway Holdings, LLC (Reel 020703/0064, executed 2008-01-07): "LLC" in the name, transferred from another LLC.
   • Mineral Lassen LLC (Reel 035974/0270, executed 2015-11-19): "LLC" in the name, merged from another LLC.
   • Intellectual Ventures Assets 99 LLC (Reel 046424/0709, executed 2019-01-22): "LLC" in the name, a known NPE.
   • Steephill Technologies LLC (Reel 046777/0932, executed 2019-03-11): "LLC" in the name, transferred from a known NPE.
   • Cedar Lane Technologies Inc. (Reel 047120/0943, executed 2019-05-13): "Inc." suffix, transferred from an LLC in a chain of NPEs.

2. Known asserter in the chain — present.

   • Intellectual Ventures Assets 99 LLC (Reel 046424/0709, executed 2019-01-22): Intellectual Ventures is a well-known patent asserter.

3. Repeat correspondent across the chain — present.

   • Jason S. Okleshen (Reel 046777/0932, executed 2019-03-11; Reel 047120/0943, executed 2019-05-13): Appears as correspondent for both Steephill Technologies LLC and Cedar Lane Technologies Inc., indicating a recurring legal representative within this chain.

4. Cascading transfers — present.

   • Reel 046424/0709 (2019-01-22), Reel 046777/0932 (2019-03-11), and Reel 047120/0943 (2019-05-13): Three assignments occurred within a span of less than four months in 2019, from Mineral Lassen LLC to Intellectual Ventures Assets 99 LLC, then to Steephill Technologies LLC, and finally to Cedar Lane Technologies Inc. This rapid succession of transfers among LLCs is a strong indicator of NPE activity.

5. Pre-litigation transfer — present. The earliest litigation found on Google Patents for US6700999 is filed in 2019 (specifically, a case filed in California Central District Court, 2:19-cv-08630, 2019-09-17). The assignment to Cedar Lane Technologies Inc. was executed on 2019-05-13 and recorded on 2019-05-20 (Reel 047120/0943), which is within six months of this first identified litigation.

6. Bankruptcy fire-sale — not present. Intel Corp. is a strong operating company and has not filed for bankruptcy.

7. Privateering — unclear. While the patent originated from an operating company (Intel) and was transferred to a known NPE chain, there is no explicit evidence in the provided data or Google Patents to suggest Intel is leveraging this chain to assert against competitors on their behalf.

8. Defensive aggregator (anti-NPE) — not present. The chain ends with Cedar Lane Technologies Inc., which is not a known defensive aggregator.

Verdict

NPE — high confidence

The assignment chain demonstrates multiple strong NPE signals. Specifically, the patent moved from Intel Corp. to a series of shell entities, including known asserter Intellectual Ventures Assets 99 LLC. There are also clear instances of cascading transfers within a short timeframe (January-May 2019), and a pre-litigation transfer to the final assignee, Cedar Lane Technologies Inc., occurring within months of the first recorded lawsuit. The presence of a repeat correspondent, Jason S. Okleshen, across multiple transfers within the chain further supports this verdict.

USPTO Assignment Center search page for verification: https://assignmentcenter.uspto.gov/

The following prior art references are considered most relevant to US patent 6700999, based on the citations provided within the patent document and general knowledge of the field.

Patent Citation

• US6111517A: Continuous video monitoring using face recognition for access control
  • Publication/Filing Date: Filed December 30, 1996; Published August 29, 2000.
  • Brief Description: This patent describes a system for continuous video monitoring that uses face recognition for access control. It focuses on recognizing faces in video streams for security applications.
  • Potential Anticipation (35 U.S.C. § 102): This patent could potentially anticipate aspects of Claim 1, Claim 8, Claim 15, Claim 21, and Claim 27 related to the general concept of face tracking in video sequences, especially in the context of human-computer interaction or security systems. Specifically, it addresses continuous video monitoring and face recognition, which are applications where face tracking is a prerequisite.

Non-Patent Citations

• Chellappa et al., "Human and Machine Recognition of Faces: A Survey," Proceedings of the IEEE, vol. 83, no. 5, pp. 705-740, May 1995.

  • Publication Date: May 1995.
  • Brief Description: This paper provides a comprehensive survey of both human and machine face recognition techniques. It discusses critical issues, various techniques for segmentation/location of faces, feature extraction, and recognition, and explores different applications.
  • Potential Anticipation (35 U.S.C. § 102): This survey article broadly covers many foundational aspects of face recognition and tracking, including techniques for segmenting faces from cluttered scenes and extracting features. It could potentially anticipate the general concepts of "constructing a score map," "producing a mask," and "locating face candidate regions" as described in Claims 1, 6, 8, 13, 15, 21, 25, 27, and 32, by outlining the state of the art in face detection and segmentation prior to US6700999.

• Dorin Comaniciu et al., "Mean Shift analysis and applications," The Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp 1197-1203, 1999.

  • Publication Date: September 20, 1999.
  • Brief Description: This paper introduces the mean shift algorithm, a nonparametric estimator of density gradient, for discontinuity preserving filtering and image segmentation in the joint spatial-range domain of images. It discusses its application in image smoothing and segmentation and its utility in detecting modes of density.
  • Potential Anticipation (35 U.S.C. § 102): The mean shift algorithm described here is a fundamental technique for identifying dense regions in feature spaces, which is directly relevant to locating face candidate regions. It could potentially anticipate aspects of "constructing a score map" and "producing a mask" by delineating regions of high flesh-tone probability, as described in Claims 1, 4, 5, 6, 8, 11, 12, 13, 17, 18, 23, 24, 27, 30, 31, and 32. Its application to image segmentation directly relates to the segmentation operation in location subtask P330 of US6700999.

• Dorin Comaniciu et al., "Robust Analysis of Feature Spaces: Color Image Segmentation," IEEE, pp750-755, 1997.

  • Publication Date: 1997.
  • Brief Description: This work presents a general nonparametric technique, based on the mean shift algorithm, for recovering significant image features and performing color image segmentation. It emphasizes autonomous segmentation and robust feature space analysis.
  • Potential Anticipation (35 U.S.C. § 102): Similar to "Mean Shift analysis and applications," this paper's focus on robust color image segmentation using mean shift directly relates to the score map construction and segmentation steps in US6700999. It could anticipate the general process of using pixel values and color space analysis to identify and segment regions, as in Claims 1, 2, 4, 5, 6, 8, 9, 11, 12, 13, 16, 17, 18, 22, 23, 24, 27, 28, 30, 31, and 32.

• Gary R. Bradski, "Computer Vision Face Tracking for Use in a Perceptual User Interface," Intel Technology Journal, Q2 1998.

  • Publication Date: Q2 1998.
  • Brief Description: This article describes the Continuously Adaptive Mean Shift (CAMSHIFT) algorithm for real-time face and object tracking, particularly for use in perceptual user interfaces. It modifies the mean shift algorithm to adapt to dynamically changing color probability distributions in video frames and uses color histograms (e.g., hue channel in HSV color space) to track faces.
  • Potential Anticipation (35 U.S.C. § 102): This publication is highly relevant as it explicitly discusses real-time face tracking using color models (specifically HSV hue histograms) and the mean shift algorithm, which are core components of US6700999. It could anticipate Claim 1 (method of tracking, score map based on pixel values, mask production), Claim 2 (pixel values and flesh-tone probabilities), Claim 6 (temporal filtering conceptually, as tracking over time is implied), Claim 8 (apparatus for tracking, mapper for score map, segmenter for mask), Claim 9 (mapper produces score map based on pixel values/flesh-tone), and other claims detailing the color-based segmentation and tracking. The use of a "probability density image" and "initial histogram" in CAMSHIFT for color-based tracking directly correlates to the "score map" and "histogram that relates pixel values to flesh-tone probabilities" in US6700999.

• Martin Hunke et al., "Face Locating and Tracking for Human-Computer Interaction," IEEE, pp1277-1281, 1995.

  • Publication Date: 1995.
  • Brief Description: This paper proposes a connectionist face tracker that manipulates camera orientation and zoom to keep a person's face located in a stable image for human-computer interaction. It uses features like shape and color for locating faces and adapts to changing lighting conditions.
  • Potential Anticipation (35 U.S.C. § 102): This reference explicitly addresses face locating and tracking for human-computer interaction, including controlling camera position and zoom. This directly relates to Claim 21 (system with camera control) and Claim 25 (system with camera control and temporal filter, as temporal information is used in control decisions). The use of "color" as a feature for locating faces also potentially anticipates aspects of score map construction and mask production related to color analysis in Claims 1, 6, 8, 13, 15, 21, 25, 27, and 32.

• Raja Yogesh, et al., "Tracking and Segmenting people in varying lighting conditions using colour," Proceedings. Third IEEE International Conference on Automatic Face and Gesture Recognition, pp228-233, 1998.

  • Publication Date: 1998.
  • Brief Description: This paper focuses on tracking and segmenting people using color information, with an emphasis on varying lighting conditions. It likely discusses methods for robust color-based segmentation in different environments.
  • Potential Anticipation (35 U.S.C. § 102): This reference could anticipate elements of Claims 1, 2, 6, 8, 9, 13, 15, 16, 21, 22, 25, 28, and 32 by addressing the use of color for segmentation and tracking, especially under varying lighting conditions, which is a practical challenge also addressed by US6700999's flesh-tone probability and adaptive parameters.

• Samal and Iyengar, "Automatic recognition and analysis of human faces and facial expressions: A survey," Pattern Recognition, vol. 25, no. 1, pp. 65-77, Jan. 1992.

  • Publication Date: January 1992.
  • Brief Description: This is an early survey paper on the automatic recognition and analysis of human faces and facial expressions, reviewing various techniques available before 1990.
  • Potential Anticipation (35 U.S.C. § 102): As another foundational survey, this article provides context for the prior art in face recognition and analysis. It would cover the general ideas of face detection, feature extraction, and recognition, potentially anticipating the high-level goals and basic components of face tracking systems outlined in Claims 1, 6, 8, 13, 15, 21, 25, 27, and 32, by showing that the problems and general approaches were known in the art.

The obviousness of US patent 6700999 under 35 U.S.C. § 103 can be assessed by examining the differences between the claimed invention and the prior art, and whether a person having ordinary skill in the art (PHOSITA) would have been motivated to combine prior art references to arrive at the claimed invention.

A PHOSITA in 2000, the priority date of US6700999, would be a computer vision engineer or researcher familiar with image processing, pattern recognition, and algorithms for real-time video analysis. This individual would be aware of various techniques for object detection, segmentation, tracking, and methods for optimizing computational load. The cited prior art, including survey papers and technical articles, reflects this level of skill and common knowledge in the field.

Here are combinations of prior art references that would render the independent claims of US6700999 obvious, along with the motivation for such combinations:

Claims 1, 8, and 27 (Method and Apparatus with Operating Modes)

These claims introduce a first operating mode (tracking every frame) and a standby mode (tracking only a portion of frames), where the standby mode activates after a specified number of consecutive frames are processed without locating any face candidate regions.

• Primary References:

  • Gary R. Bradski, "Computer Vision Face Tracking for Use in a Perceptual User Interface" (1998): This article describes a real-time face-tracking system using skin-color detection and highlights the challenge of "large amount of data processing required" for face tracking.
  • Dorin Comaniciu et al., "Robust Analysis of Feature Spaces: Color Image Segmentation" (1997) and "Mean Shift analysis and applications" (1999): These papers describe techniques for color image segmentation, which is fundamental to identifying face candidate regions.
  • Raja Yogesh et al., "Tracking and Segmenting people in varying lighting conditions using colour" (1998): This reference discusses using color models to extract skin regions for tracking.
  • Chellapa et al., "Human and Machine Recognition of Faces: A survey" (1995) and Samal and Iyengar, "Automatic recognition and analysis of human faces and facial expressions: A survey" (1992): These survey papers provide an overview of face detection and tracking techniques, including various cues and challenges.

• Motivation to Combine: Bradski explicitly points out the significant computational demands of real-time face tracking. A PHOSITA, aware of this known problem, would be strongly motivated to implement strategies to reduce processor load when face tracking is not actively yielding results. It is a common engineering principle to conserve computational resources by reducing the frequency of processing when a target object is absent or not detected. Therefore, designing a system to transition to a "standby mode" that processes only a portion of frames after a period of no face detections, and returning to a "normal mode" upon detection, would be an obvious solution to the known problem of high processor utilization.

Claims 6, 13, 19, 25, and 32 (Method and Apparatus with Temporal Filtering)

These claims describe temporal filtering of the face candidate mask, specifically by obtaining an average (or median, as described in the patent) of entries from the current mask and corresponding entries from temporally distinct (previous and/or subsequent) masks.

• Primary References:

  • Gary R. Bradski, "Computer Vision Face Tracking for Use in a Perceptual User Interface" (1998): Mentions "temporal filtering" in the context of improving robustness for face tracking.
  • Raja Yogesh et al., "Tracking and Segmenting people in varying lighting conditions using colour" (1998): Refers to "temporal coherence of the tracked regions," acknowledging that object presence is correlated across frames.
  • Chellapa et al., "Human and Machine Recognition of Faces: A survey" (1995) and Samal and Iyengar, "Automatic recognition and analysis of human faces and facial expressions: A survey" (1992): These surveys would establish the general understanding of temporal consistency in video processing.

• Motivation to Combine: The temporal correlation of faces in a video sequence is a fundamental characteristic. A PHOSITA would be motivated to apply temporal filtering techniques, such as averaging or median filtering across multiple frames, to the face candidate masks. This is a well-known technique in image and video processing for noise reduction, smoothing, and improving the accuracy and stability of object detection by mitigating transient false alarms or missed detections. Applying such filtering would lead to a more robust and reliable face tracking output, which is a predictable benefit.

Claims 7, 14, 20, 26, and 33 (Filtering Based on Specific Characteristics)

These claims detail filtering the mask to remove false alarms by testing characteristics such as size, position, aspect ratio, intra-region flatness, shape, and contrast between interior and boundary areas of face candidate regions.

• Primary References:

  • Chellapa et al., "Human and Machine Recognition of Faces: A survey" (1995) and Samal and Iyengar, "Automatic recognition and analysis of human faces and facial expressions: A survey" (1992): These surveys discuss various features and cues used for face detection and verification, including shape, size, and aspect ratio.
  • Gary R. Bradski, "Computer Vision Face Tracking for Use in a Perceptual User Interface" (1998): Describes face detection using initial cues and template matching, which implicitly involves feature comparison.

• Motivation to Combine: The patent explicitly states that "color matching schemes... are not entirely immune to false alarms." A PHOSITA, facing the known problem of false positives in color-based face detection, would be motivated to employ additional discrimination criteria. Utilizing commonly known facial characteristics (e.g., expected size, aspect ratio, and shape of a human face) and general image processing features (e.g., color uniformity or contrast) to validate or reject face candidates is a standard approach in computer vision for improving detection accuracy and reducing false alarms.

Claim 15 (System with Video Encoder)

This claim describes a system where the face-tracking apparatus provides a mask to a video encoder, which then allocates a disproportionate number of bits to encode regions corresponding to face candidate regions.

• Primary References:

  • Gary R. Bradski, "Computer Vision Face Tracking for Use in a Perceptual User Interface" (1998): Provides a system for face tracking.
  • General knowledge in video encoding: The patent itself mentions MPEG and H.263 standards and the concept of "content-directed video encoding" where "higher priority is given to regions of interest... such as human faces." This indicates that the goal of prioritizing faces in encoding was a known and desirable objective.

• Motivation to Combine: Given the established desire in video compression to allocate more bits to perceptually important regions (like human faces) to improve subjective quality, a PHOSITA would be directly motivated to combine the output of a face tracking system (the mask identifying face regions) with a video encoder. This combination provides a practical and obvious way to achieve content-directed bit allocation, a known and desired application in the field.

Claims 21 and 25 (System with Camera Control)

These claims describe a system with a camera, a face-tracking apparatus (with or without temporal filtering and operating modes), and a camera control unit that adjusts camera movement (position/focal length) in response to face candidate regions across frames.

• Primary References:

  • Gary R. Bradski, "Computer Vision Face Tracking for Use in a Perceptual User Interface" (1998): Teaches face tracking.
  • Martin Hunke et al., "Face Locating and Tracking for Human-Computer Interaction" (1995): Deals with face locating and tracking, in contexts that naturally lead to camera control for human-computer interaction.
  • US6111517A (Visionics Corporation): Describes a "Continuous video monitoring system" for "detecting and tracking faces," which inherently implies a need to keep faces within the field of view.
  • General knowledge of PTZ (Pan-Tilt-Zoom) cameras: The capability to control camera position and focal length was well-known.

• Motivation to Combine: In applications such as video conferencing, surveillance, or telecine (as mentioned in US6700999), it is highly desirable to automatically keep human subjects' faces in the camera's view and in focus. A PHOSITA would be motivated to combine existing face tracking technology with known camera control capabilities to create an automated system for this purpose. The method of comparing face locations across successive frames to derive movement vectors for the camera is a logical and straightforward implementation for tracking a moving target. The inclusion of temporal filtering (as in Claim 25), already motivated for robustness, would further enhance the stability and smoothness of camera movements, preventing jerky or erratic behavior, which is an obvious improvement.

Claims 27 and 32 (Apparatus with Data Storage Medium)

These claims describe an apparatus comprising a data storage medium having machine-readable code that, when executed, defines the methods of Claims 1 and 6, respectively.

• Primary References: The methods of Claim 1 and Claim 6, as discussed above, are themselves obvious.

  • General knowledge in computer engineering: By 2000, it was a fundamental and widespread practice to implement computer-executable methods as machine-readable code stored on data storage media (e.g., ROM, flash memory, disks) for execution by processors (e.g., microprocessors, DSPs, ASICs, FPGAs). This is explicitly acknowledged within the US6700999 patent itself (FIGS. 17A and 17B and corresponding description).

• Motivation to Combine: The implementation of any computer-based method as software or firmware on a data storage medium is a standard design choice and not inventive in itself. It is the obvious way to make such methods functional on a computing apparatus.

In conclusion, the various elements of US6700999, including the core face tracking methodology, temporal filtering, false alarm reduction, operational modes for processor efficiency, and specific applications like video encoding and camera control, would have been obvious to a PHOSITA by the patent's priority date (June 30, 2000), given the available prior art and the clear motivations to address known problems or achieve desirable system functionalities.