Patents

Patents

Computer Vision - Granted

US 7,061,485, Issued Jun. 13, 2006: Method and system for producing a model from optical images.

Inventors: D. O. Tanguay, W. B. Culbertson, D. G. Gelb, M. Harville
Assignee: Hewlett-Packard.
Summary: Interactive methods for using a camera to visually "scan" and construct a model of an object in real-time, using real-time feedback to guide the operator of the camera. A handheld camera is envisioned in most embodiments.
Abstract: Disclosed is a method for producing a model of an object, comprising receiving at least one image of the object in a computing device, processing one or more of the at least one image to produce a model of the object, generating feedback information corresponding to the model of the object, and imparting the feedback information to a user of the computing device concurrently with the processing such that a determination is enabled to be made whether the model of the object is of a desired quality while the computing device is disposed to receive a further image of the object. The feedback information can be an image of the model which enables a user to determine whether an additional image is necessary or the feedback information can be direction to acquire an additional image of the object.

US 7,003,136, Issued Feb. 21 2006: Plan-view projections of depth image data for object tracking

Inventors: M. Harville
Assignee: Hewlett-Packard Corp.

Summary: Methods for tracking people or other objects using depth imagery (e.g. from a stereo camera), based on projection of the depth data into plan-view imagery. Papers on this work include SMVP Wkshp. 2002, Journal of Image and Vision Computing 2004, part of the CVPR 2004 paper, and the Conference on AVSS 2005 paper.
Abstract: Object tracking systems and methods are described. In one aspect, a three-dimensional point cloud is generated from a time series of video frames and partitioned into a set of vertically-oriented bins. The point cloud is mapped into one or more plan-view images each containing for each vertically-oriented bin a corresponding pixel having one or more values computed based upon one or more attributes of the point cloud members occupying the corresponding vertically-oriented bin. The object is tracked based at least in part upon one or more of the plan- view images. In another aspect, one or more original object templates are extracted from at least one of the one or more plan-view images, and the object is tracked based at least in part upon a comparison of at least one of the object templates with regions of the corresponding plan-view images. In another aspect, the point cloud may be discretized along the vertical axis into two or more horizontal partitions.

US 7,003,134 (issued Feb. 21, 2006) and US 7,158,656 (issued Jan. 02, 2007): Three-dimensional object pose estimation which employs dense depth information

Inventors: M. Covell, M. Lin, A. Rahimi, M. Harville, T. Darrell, J. Woodfill, H. Baker, G. Gordon
Assignee: Vulcan Patents, LLC
Summary: This is based on work done at Interval Research Corp., covering two ICCV papers and one CVPR paper in 1999 and 2000. These deal with methods for real-time tracking of the position and orientation of rigid and articulated bodies, without prior knowledge of object shape or appearance, using depth and color data from a stereo camera. Was state-of-the-art when we developed it, and I thought it had been filed in 2000, but perhaps the filing was delayed many years due to the demise of Interval.
Abstract: Dense range data obtained at real-time rates is employed to estimate the pose of an articulated figure. In one approach, the range data is used in combination with a model of connected patches. Each patch is the planar convex hull of two circles, and a recursive procedure is carried out to determine an estimate of pose which most closely correlates to the range data. In another aspect of the invention, the dense range data is used in conjunction with image intensity information to improve pose tracking performance. The range information is used to determine the shape of an object, rather than assume a generic model or estimate structure from motion. In this aspect of the invention, a depth constraint equation, which is a counterpart to the classic brightness change constraint equation, is employed. Both constraints are used to jointly solve for motion estimates.

US 6,999,620, Issued Feb. 14, 2006: Segmenting video input using high-level feedback.

Inventors: M. Harville
Assignee: Hewlett-Packard Corp.

Summary: General framework for supplying feedback from high-level visual analysis modules (e.g. person tracking, region finding, lighting analysis, etc.) to guide the evolution of per-pixel Gaussian-mixture background models. Covers the work of an ECCV 2002 paper.
Abstract: Systems and methods of segmenting video input are described. These systems and methods use feedback processing that operates on levels of information above the pixel level, such as image regions, frame-wide statistics, or object and event semantics. In one aspect, one or more pixel-level historical models of spatially local pixel observations is maintained. Pixels are segmented into two or more labeled groups based at least in part upon comparison of pixel-level video input with the one or more pixel-level historical models. The pixel- level historical models are updated based at least in part upon feedback maps identifying pixels respectively segmented into the one or more labeled groups in conformity with a spatially non-local segmentation model.

US 6,661,918, Issued Dec. 9 2003: Background estimation and segmentation based on range and color.

Inventors: G. Gordon, M. Harville, J. Woodfill, T. Darrell.
Assignee: Interval Research Corp.

Summary: Video background modeling and removal based on color and range data.
Abstract: Segmentation of background and foreground objects in an image is based upon the joint use of both range and color data. Range-based data is largely independent of color image data, and hence not adversely affected by the limitations associated with color-based segmentation, such as shadows and similarly colored objects. Furthermore, color segmentation is complementary to range measurement in those cases where reliable range data cannot be obtained. These complementary sets of data are used to provide a multidimensional background estimation. The segmentation of a foreground object in a given frame of an image sequence is carried out by comparing the image frames with background statistics relating to range and normalized color, using the sets of statistics in a complementary manner.

US 6,188,777 (issued Feb 13, 2001) and US 6,445,810 (issued Sep. 3, 2002): Method and apparatus for personnel detection and tracking.

Inventors: T. Darrell, G. Gordon, M. Harville, J. Woodfill, H. Baker.
Assignee: Interval Research Corp.

Summary: Real-time 3D face detection and tracking using range, skin color, and pattern recognition; plus graphical distortion of faces in "virtual mirror" interface.
Abstract: Techniques from computer vision and computer graphics are combined to robustly track a target (e.g., a user) and perform a function based upon the image and/or the identity attributed to the target's face. Three primary modules are used to track a user's head: depth estimation, color segmentation, and pattern classification. The combination of these three techniques allows for robust performance despite unknown background, crowded conditions, and rapidly changing pose or expression of the user. Each of the modules can also provide an identity classification module with valuable information so that the identity of a user can be estimated. With an estimate of the position of a target in 3-D and the target's identity, applications such as individualized computer programs or graphics techniques to distort and/or morph the shape or apparent material properties of the user's face can be performed. The system can track and respond to a user's face in real-time using completely passive and non-invasive techniques.

Computer Vision - Pending

US 20070058860 A1, Filed Sep. 9, 2005: Method and system for skin color estimation from an image.
- Inventors: M. Harville, H. Baker, N. Bhatti, S. Susstrunk.
- Assignee: Hewlett-Packard
- Summary: Methods for automatically determining the "true" skin color of a person, independent of lighting or camera sensor properties, from a single image of a person's face. The only "extra" requirement is that the image also contains some known colors arranged in a known pattern that can be detected automatically. We applied this for automated cosmetics consulting (see "Other" patents below).
- Abstract: Embodiments of the present invention recite a computer implemented method and system for estimating skin color from an image. In embodiments of the present invention, an image of a subject and of an imaged reference color set is accessed. In embodiments of the present invention, a controlled infrastructure is not required when capturing the image. At least one skin pixel of the subject is located in the image and a color description of the at least one skin pixel is determined. Then, a color correction function to be applied to the color description of the at least one skin pixel is determined. The color correction function is applied to the color description of the at least one skin pixel to create a modified color description. Finally, the skin color of the subject is estimated based upon an analysis of the modified color description.
US 20050094879 A1, Filed Oct. 31, 2003: Method for visual-based recognition of an object.
- Inventors: M. Harville
- Assignee: Hewlett-Packard
- Summary: Construct plan-view templates from depth imagery, and feed them to classifiers to make rapid decisions about object type, configuration, etc. For example, plan-view templates of people may be used to make rapid judgments about body pose, orientation, identity, gender, etc.
- Abstract: A method for visual-based recognition of objects is described. Depth data for at least a pixel of an image of the object is received, the depth data comprising information relating to a distance from visual sensor to a portion of the object visible at the pixel. At least one plan-view image is generated based on the depth data. At least one plan-view template is extracted from the plan-view image. The plan- view template is processed by at least one classifier, wherein the classifiers are trained to make a decision according to pre-configured parameters.
US 20040153671 A1, Filed Oct. 31, 2003: Automated physical access control systems and methods.

Inventors: M. Schuyler, M. Harville.
Assignee: Hewlett-Packard.
Summary: Prevent "tailgating" at secured building entrances, by requiring the numbers of electronic badges sensed (e.g. via a swiping mechanism) to match the number of people tracked via video cameras.

Abstract: Automated physical access control systems and methods are described. In one aspect, an access control system includes an object detector, a token reader, and an access controller. The object detector is configured to detect persons present within a detection area. The token reader is configured to interrogate tokens present within a token reader area. The access controller is configured to receive signals from the object detector and the token reader. The access controller is configured to compute one or more characteristics linking persons and tokens based upon signals received from the object detector and the token reader and to determine whether detected persons are carrying permissioned tokens based upon the one or more computed characteristics linking persons and tokens.

US 20060092178 A1, Filed Oct. 29, 2004 : Method and system for communicating through shared media.

Inventors: D. O. Tanguay, D. G. Gelb, M. Harville, H. H. Baker
Assignee: Hewlett-Packard.
Summary: Sorry for the horribly vague invention title. A better name would be "shared virtual whiteboard". The idea is to create a shared whiteboard for remote collaboration systems, without requiring the users to employ any fancy gadgets. Instead, they use their regular old pens and pencils, and may write on sheets of paper or on physical whiteboards. The trick is to use cameras to capture what all users are writing on their separate phsyical drawing boards, and then employ projectors to "write" the merged content onto each of these surfaces so that each person sees the same view of the shared virtual whiteboard. Care must be taken to align projections of other people's writings with those of an individual on his drawing surface. Also, care is taken to ignore hands and other body parts, and only extract the writing from the surface. Lots of other cool sub-inventions in this one, like how to erase, recording and "TiVo-ing" of the whiteboard session, gestural controls, etc.
Abstract: A method and system for communicating through shared media. Specifically, a method provides for accessing a plurality of images from respective input interfaces of a plurality of input interfaces. At least one of the plurality of images is captured using a camera, and wherein at least one of the plurality of images contains a form of communication. The form of communication is extracted from the plurality of images. A respective appearance model is constructed corresponding to each of the plurality of input interfaces. At least one of the respective appearance models contributes the respective form of communication that is extracted and transformed to a reference frame of a reference coordinate system. The respective appearance models are combined together to generate a shared virtual model. The shared virtual model is displayed to at least one output medium.

Media Processing - Granted

US 6,993,245, Issued Jan. 31, 2006: Iterative, maximally probable, batch-mode commercial detection for audiovisual content

Inventors: M. Harville
Assignee: Vulcan Patents, LLC.
Summary: Given the full recording of a television program, combine audio and visual cue detection (e.g. black frames, audio pauses, music, text on screen, etc.) with probabilistic models of commerical lengths and commercial break separations in order to identify the most likely start and end points of television commercials. This is based on work done in 1999 at Interval Research Corp, but for which the patent filing apparently was delayed due to Interval's demise in 2000.
Abstract: Identification of starting and ending times of commercial breaks and commercials within those commercial breaks found in audiovisual content is disclosed. A solution to a "batch optimization" problem is used in which commercial locations within a set of audiovisual content are detected as a group by choosing a set of commercial locations which optimizes a cost function which can include considerations of, for example, 1) one or more cues, 2) relative locations of commercials within the audiovisual content, and/or 3) probability models based on statistics obtained regarding characteristics of typical commercial and commercial breaks. Optimization can be done over the total set of commercial location decisions, rather than on a per-commercial basis. Additionally, the cost function can be iteratively evaluated and many more types of cues and combinations of cues can be used in detection of commercials.

Media Processing - Pending

US 20060080102 A1 (filed Oct. 13, 2004), WO2006044253 A1 (filed Oct. 7, 2005), and EP1800292 A1 (filed Oct. 7, 2005): Method and system for improving the fidelity of a dialog system

Inventors: S. Roy, M. Harville, M. Covell
Assignee: Hewlett-Packard
Summary: Suppose two people are engaged in a conversation over a network, but the first person is listening/speaking while the second person is reading/typing. Speech recognition and text-to-speech are used to couple the two people, so that words spoken the first person can be read by the second, while words typed by the second person are heard by the first. The idea behind the invention is to link the speech recognizer and text-to-speech engines, to favor recognition of speech related to words being typed, while adjusting pronunciation of text-to-speech output to match how the speaking person pronounces words.
Abstract: Embodiments of the present invention recite a method and system for improving the fidelity of a dialog system. In one embodiment, a first input generated by a user of a first system operating in a first modality is accessed. In embodiments of the present invention, the first system also generates a first output corresponding to the first input. An second input from a second user, who is engaged in a conversation with the first user, is accessed by a second system. The second input is then utilized to modify the first output of the first system.

Rich Media Environments - Pending

US 20060244817 A1, Filed Apr. 29, 2005:

Inventors: M. Harville, D. Tanguay, H H. Baker, W. B. Culbertson
Assignee: Hewlett-Packard.
Summary: This patent tackles the problem of how to use a fixed infrastructure (i.e. cameras, displays, audio, etc.) to enable "life-size", immersive videoconferencing between an arbitrary number of groups of people at different sites, while preserving at least an approximate sense of eye contact at a group level. That is, if people in group A are looking at people in group B, a third party C will know that they are not being looked at, and could reasonably surmise that group B is the target of attention. Our solution involves a large curved screen that partially wraps around the table at each conferencing site, as well as a camera array positioned behind the screen that is capable of generating views of the local party from any viewpoint intermediate to the camera locations. Essentially, this is a blueprint for "next-generation", high-end videoconferencing systems, surpassing current product offerings by companies like Telesuite and Cisco.
Abstract: A method and system for videoconferencing between parties at N sites. Specifically, a virtual space arrangement of N sites is created. Video sequences of N-1 remote sites are simultaneously displayed on a non-planar display arranged around a local party at a local site consistent with the virtual space arrangement. The displayed images of the remote parties are scaled consistently with their true physical sizes at their distances from the local party in the virtual space arrangement. Real-time video streams of the local party are captured from a plurality of viewpoints and are used to generate N-1 video view streams representing views of the local party from approximately the local display locations of the N-1 remote parties.

US 20050078172 A1, Filed Oct. 9, 2003:

Inventors: M. Harville, M. Covell, D. Tanguay.
Assignee: Hewlett-Packard.
Summary: The basic idea is that everyone brings their PDA or cellphone to a meeting, with each of these mobile devices having built-in camera, screen, microphone, speaker, and networking. Each person positions his mobile device on the table in front of him so that he is in its camera's field-of-view. These devices all find each other (via wireless, audio, and/or visual signals), and then coordinate amongst themselves to achieve either or both of 1) producing a nice multimedia summarization of the meeting, using video and audio captured by the mobile devices, and 2) creating a teleconferencing session with people at some remote site, with intelligent view selection, audio enhancement, and so on based on the activities of the meeting. Lots of interesting ideas in this patent - read the specification, as the abstract is not very informative.
Abstract: In one embodiment, the present invention recites a coordinating component for creating an enhanced representation of an ongoing event using inputs from a communication session established between a plurality of communication devices. A first input port receives a first input from a first of the plurality of communication devices. A second input port receives a second input from a second of the plurality of communication devices. The first of the plurality of communication devices and the second of the plurality of communication devices do not have a prior association. A generator for selectively combining the first input and the second input creates an enhanced representation of the ongoing event. The enhanced representation is then output from an output port.

US 20050078613 A1 (filed Oct. 9, 2003) and WO2005036856 A1 (filed Oct. 6, 2004) and EP 1671464 A1 (filed Oct. 6, 2004): System and method for establishing a parallel conversation during a remote collaboration.

Inventors: M. Covell, N. Bhatti, H. Baker, B. Culbertson, M. Harville, T. Malzbender, S. Wee.
Assignee: Hewlett-Packard
Summary: Imagine a video conference between two parties at different sites, each in their own big room looking at a big screen. Each party has multiple people. This invention tackles the problem of how an individual at one site might have a private conversation with an individual at the other, while the rest of the people are engaged in the meeting. More generally, it looks at how to allow mutliple conversation threads to be carried on simultaneously amongst the participants in a videoconferencing context, without hopelessly confusing everyone, just as might be possible if all the participants were gathered together in a single large room.
Abstract: Methods and systems for utilizing a parallel conversational thread during a remote collaboration are described. In one embodiment, a managing entity is utilized to establish a first communications path for a remote collaboration of at least two parties. Then, a request for a parallel conversation is received from at least one of the at least two parties during the remote collaboration. The managing entity then establishes a second communications path for the parallel conversation between the at least two parties. Wherein, the enabling of the parallel conversation on the second communications path is performed without inhibiting the first communications path, such that a portion of a first party can have a parallel conversation with a portion of a second party on the second communications path while the first communications path for the remote collaboration remains active.

US 20050081160 A1 (filed Oct. 9, 2003) and WO2005036359 A2 (filed Oct. 6, 2004) and EP 1671220 (filed Oct. 6, 2004): Communication and collaboration system using rich media environments.

Inventors: S. Wee, H. Baker, N. Bhatti, M. Covell, M. Harville
Assignee: Hewlett-Packard
Summary: A bit of a kitchen-sink patent on the concept of using lots of cameras, microphones, large displays, and speakers to provide a highly-enhanced video conferencing experience. My main contributions were on the person sensing and projector-based "virtual whiteboard" parts of the system.
Abstract: A system that enables communication and collaboration among individuals using rich media environments. A system according to the present techniques includes a set of rich media environments each having a corresponding arrangement of sensing and rendering components for sensing of and rendering to a corresponding set of individuals. A system according to the present techniques includes an interest thread detector that uses the sensing and rendering components to detect formation of multiple communication interactions among the individuals and that creates an interest thread for each detected communication interaction and further includes a communication provider that for each interest thread captures a set of media data from a corresponding subset of the sensing components and that combines the captured media data in response to the activities of the corresponding individuals and that communicates the combined media data to a corresponding subset of the rendering components.

US 20050080849 A1 (filed Oct. 9, 2003) and WO2005036350 A2 (filed Oct. 6, 2004) and EP 1671211 A2 (filed Oct. 6, 2004): Management system for rich media environments.

Inventors: S. Wee, H. Baker, N. Bhatti, M. Covell, M. Harville, D. Gelb, D. Tanguay.
Assignee: Hewlett-Packard
Summary: How to manage and allocate resources lots of sensors and output devices for the purposes of enhanced video conferencing.
Abstract: A management system for a rich media environment that enables relatively large numbers of sensing and rendering components to be marshaled for a variety of tasks and services. A management system according to the present teachings includes a service manager that provides a communication service pertaining to the rich media environment by coordinating a set of tasks in the rich media environment and further includes a task manager that manages each task by allocating a set of processing resources and communication resources to each task and performing each task in response to a request for each task from the service manager.

Path-Enhanced Media - Granted

Tagging digital media, such as photos and videos, with capture time and location information has previously been proposed to enhance its organization and presentation. We believe that the full path traveled during media capture, rather than just the media capture locations, provides a much richer context for understanding and "re-living" a trip experience, and offers many possibilities for novel applications. We introduced the concept of "path-enhanced media", in which media is associated and stored together with a densely sampled path in time and space, and we developed an architecture for capturing, representing, browsing, editing, presenting, and searching this data. A set of patents was filed to cover various parts of this architecture.

US 6,906,643, Issued June 14, 2005: Systems and methods of viewing, modifying, and interacting with "path-enhanced" multimedia.

Inventors: R. Samadani, M. Harville.
Assignee: Hewlett-Packard.
Summary: In this patent, we focus on methods for statically rendering views of path-enhanced media, and browsing, editing, and interacting with these views. The most obvious way of viewing path enhanced media is to overlay the path on a map, and draw icons at path locations where media was captured. Selection of icons plays the media. A variety of editing is supported, including various types of path editing, addition of text or voice comments at path locations that spark memories, setting permissions on path and media, "bookmarking" path locations and/or media, and attachment of other media (e.g. photos from previous trips taken by you or your friends) at selected path locations. The path data can also be used to search for media, points of interest, restaurant names. etc., which can also be associated with your the path. Other ways of viewing the media, such as in a calendar format, are also discussed.
Abstract: "Path-enhanced" multimedia (PEM) data may be viewed, modified, or interacted with according to user selected views which determine the manner in which at least a portion of the PEM data is displayed. The PEM data is stored in a data structure as a scrapbook object including first data object types corresponding to the PEM data and second object types corresponding to the different view types. The scrapbook object data structure lends itself to displaying portions of the PEM data according to selected views that correspond to a particular time and place or to a particular time ordered sequence of locations (i.e., a particular path segment) and/or can be enhanced with other multimedia content related to that time and place or to that path segment, thereby providing a more interesting and effective display of the "path-enhanced" recorded events. For example, the time and location of a particular point on the path may be used to locate and append other recorded sounds and images associated with that time and/or that location, to thereby provide an enhanced presentation of a trip or other path-oriented experience. Moreover, the data defining any such associated path may also be edited to thereby define a new or modified path.

US 7,149,961, Issued Dec. 12, 2006: Automatic generation of presentations from "path-enhanced" multimedia.

Inventors: M. Harville, R. Samadani.
Assignee: Hewlett-Packard.
Summary: A movie-like presentation of your trip is automatically generated from your photos, videos, and audio clips, using your recorded path information as the context to tie it all together. In the movie, a map of your trip location is shown, and we zoom in to trace your path, pausing to show photos and videos along the way. Other geographically tagged information about the area (e.g. music, points of interest, restaurant names, etc.) are used to augment the presentation. Many versions of the presentation generation are explored.
Abstract: A "path-enhanced" presentation is automatically generated from previously recorded "path-enhanced" multimedia based on time and location information associated with the multimedia. The path based on the time and location information is rendered over a two-dimensional map. The presentation indicates position and progress along the path, and at the same time, previously recorded multimedia corresponding to points or segments of that path are automatically played. When the moving icon reaches a location that is associated with multimedia, that multimedia is automatically played.

Path-Enhanced Media - Pending

US 20040218895 A1 (filed Apr. 30, 2003) and WO 2004100166 A2 (filed Apr. 29, 2004): Apparatus and method for recording "path-enhanced" multimedia.

Inventors: R. Samadani, M. Harville.
Assignee: Hewlett-Packard.
Abstract: A “path-enhanced” recorder combines the recording of multimedia data files (typically, but not necessarily, using conventional digital audio, photo, and video recording technology), along with quasi- continuous capturing of time and position data to permit a subsequent reconstruction of the user's entire path, preferably including times and/or locations at which no multimedia data files were being recorded. A "path-enhanced" recorder device thus provides a combined record of not only multimedia data files but also data concerning path traveled between (and possibly during the capturing of individual recorded media files to thereby create "path-enhanced" multimedia, which in turn facilitates a number of contemplated applications including the Automatic Generation of Presentations; Exploration, Enhancement and Editing of "Path-Enhanced" Multimedia; and Searching of " Path-Enhanced" Multimedia Database.

WO 2005017780 A1, Filed Apr. 29, 2004: Systems and methods of viewing, modifying, and interacting with "path-enhanced" multimedia.

Inventors: R. Samadani, M. Harville.

Assignee: Hewlett-Packard.
Same as issued patent US 6906643 (above).

US 20040220965 A1, Filed Apr. 30, 2003: Indexed database structures and methods for searching path-enhanced multimedia.

Inventors: M. Harville, R. Samadani.
Assignee: Hewlett-Packard.
Abstract: Media from multiple sources is labeled with time and location metadata organized as individual paths and shared in a common searchable database with search tools that take advantage of spatio-temporal relationships between the different paths. This combination of path oriented data and path oriented search tools permits an individual associated with a first path to locate information associated with another spatio-temporally related path. In particular, certain embodiments of the invention can facilitate the use of a given set of path data and/or path-enhanced multimedia to identify other paths and path-enhanced multimedia that overlap or intersect in space and/or time within a specified precision. Path information previously recorded by one user may be used in accordance with the present invention to obtain multimedia recorded on a different path by a different user, but that is close in space and time to a location on the user's own path.

Network-Based Media Services - Pending

US 20050005025 A1 (filed July 4, 2003), WO 2005006709 A1 (filed July 1, 2004), and EP 1642443 A1 (filed July 1, 2004): Method for managing a streaming media service.

Inventors: M. Harville, M. Covell, S. Wee, S. Roy, J. Ankcorn, B. Shen
Assignee: Hewlett-Packard
Abstract: One embodiment of the invention includes a method (1300) for managing a streaming media service. The method includes receiving (1302) a request (1004) for a streaming media service from a client (1002). The streaming media service includes a plurality of media services components (1020). Additionally, the method includes determining (1304) which media service component of the plurality of media services components to assign to a service node (1022) of a plurality of service nodes of a network (1212). The method also includes informing (1306) each service node assigned to perform a media service components enabling the streaming media service to be performed on a streaming media (1032).

US 20050005019 A1 (filed Oct. 30, 2003) and WO 2004105314 A2 (filed May 13, 2004): Service management using multiple service location managers.

Inventors: M. Harville, M. Covell, J. Ankcorn, J. Apostolopoulos, S. Roy, B. Shen, W. Tan, S. Wee.
Assignee: Hewlett-Packard.
Abstract: One embodiment of the invention includes a method (300) for managing a streaming media service. The method includes receiving a request (302) for a streaming media service from a client (150). It is noted that the streaming media service includes a media service component. Additionally, the method includes selecting (304) a service manager (120) from a plurality of service managers (120 and 122) to provide the request to. Furthermore, the method includes selecting (306) a provider (130) from a plurality of providers (130, 132, 134 and 136) of a network assign the media service component. Moreover, the method includes informing (308) said provider assigned to perform the media service component, enabling the streaming media service to be performed on a streaming media.

US 20050015765 A1 (filed Oct. 30, 2003) and WO 2004104867 A2, Filed May 13, 2004: System for doing service location management taking into account the node and network characteristics.

Inventors: M. Covell, S. Roy, J. Ankcorn, J. Apostolopoulos, M. Harville, B. Shen, W. Tan, S. Wee.
Assignee: Hewlett-Packard.
Abstract: Methods and systems for selecting media service providers based on static resource information are described. A type of service to be performed on an item of content is (304) identified. The item of content is identified during a session with a client device. A service provider is selected (306) from a plurality of service providers. The selection is based on static service provider and static network information. The selection of a service provider is further based on service session information if the service session information has been received. Information is provided for transferring the session to the selected service provider. The selected service provider performs (314) the service on the item of content.

US 20040236848 A1 (filed Oct. 30, 2003) and WO 2004105313 A2 (filed May 13, 2004): Managing handoffs of media sessions among service providers.

Inventors: S. Roy, B. Shen, J. Ankcorn, J. Apostolopoulos, M. Covell, M. Harville, W. Tan, S. Wee.
Assignee: Hewlett-Packard.
Abstract: A method (700) and system (100) for managing handoff of media service sessions among service providers (130A-130D) in a network are disclosed. Information associated with the media service sessions is received at a service manager (120). The information at the service manager (130) is used to determine whether to initiate a handoff of any of the media service sessions from a service provider to another service provider. Moreover, if it is deterrmined to initiate the handoff, the handoff is initiated.

US 20040236854 A1 (filed Oct. 30, 2003) and WO 2004105348 A2 (filed May 13, 2004): Systems and methods in which a provider is selected to service content requested by a client device.

Inventors: S. Roy, M. Covell, B. Shen, J. Ankcorn, J. Apostolopoulos, M. Harville, W. Tan, S. Wee.
Assignee: Hewlett-Packard.
Abstract: Methods (300, 400) and systems (100) for servicing content for delivery to a client device (150) are described. An item of content is identified during a session with the client device. A type of service to be performed on the item of content is identified. A provider (130) is selected from a plurality of providers capable of performing the service. The session is transferred to the selected provider, which performs the service on the item of content.

US 20040236847 A1 (filed Oct. 30, 2003) and WO 2004105349 A2 (filed May 13, 2004): Systems and methods for performing a service on content requested by a client device.

Inventors: S. Roy, B. Shen, J. Ankcorn, J. Apostolopoulos, M. Covell, M. Harville, W. Tan, S. Wee.
Assignee: Hewlett-Packard.
Abstract: Methods (300, 400) and systems (100) for servicing and delivering content to a client device (150) are described. A request that identifies an item of content is received at a portal (140) from the client device. A type of service to be performed on the item of content is identified. A provider (130) of the type of service is identified. Communication with the client device is transferred from the portal to the service provider. The service provider sends service result content to the client device

US 20040236826 A1 (filed Oct. 30, 2003) and WO 2004105350 A2 (filed May 13, 2004): Method and system for managing a streaming media service / Combination case for service location management of media services.

Inventors: M. Harville, M. Covell, J. Ankcorn, J. Apostolopoulos, S. Roy, B. Shen, W. Tan, S. Wee.
Assignee: Hewlett-Packard.
Abstract: One embodiment of the invention includes a method for managing a streaming media service. The method includes receiving a request (1902) for a streaming media service from a client (150) and the streaming media service includes a media service component. A service location manager (120) is selected (1904) to which to provide the request from a plurality of service location managers (120 and 122). Additionally, a service provider (130) is selected (1906) to which to assign the media service component from a plurality of service providers of a network (130, 132, 134, ans 136). Furthermore, the service provider is infomed (1908) of the assignment to perform the media service component. The service provider is caused to prepare to perform the streaming media service on streaming media. Moreover, information is used to determine (1620) whether to initiate a handoff of the streamimng media service from the service provider to another service provider. If it is determined (1630) to initiate the handoff, the handoff is initiated.

US 20040236857 A1 (filed Oct. 30, 2003) and WO 2004105352 A1 (filed May 13, 2004): System and methods for selecting a provider to service content requested by a client device.

Inventors: S. Roy, M. Covell, J. Ankcorn, J. Apostolopoulos, M. Harville, B. Shen, W. Tan, S. Wee.
Assignee: Hewlett-Packard.
Abstract: Methods (300,400) and systems (100) for servicing content for delivery session to a client device (150) are described. An item of content is identified during a session with the client device. A type of service to be performed on the item of content is identified. An estimate of resources associated with performing the service is used to select a provider (130) from a plurality of providers capable of performing the service. Information for transferring the session to the provider is provided. The provider performs the service on the item of content upon being transferred the session.

US 20040237097 A1 (filed Oct. 30, 2003) and WO 2004105353 A2 (filed May 13, 2004): Method for adapting service location placement based on recent data received from service nodes and actions of the service location manager.

Inventors: M. Covell, S. Roy, J. Ankcorn, J. Apostolopoulos, M. Harville, B. Shen, W. Tan, S. Wee.
Assignee: Hewlett-Packard.
Abstract: Methods and systems for selecting media service providers are described. A type of service to be performed on an item of content is identified. The item of content is identified (404) during a session with a client device. Information regarding current resource availability is received (406) from a plurality of service providers. The information is ascertained from ongoing resource measurements. A service provider is selected (408) from the plurality of service providers based on the information that is received. Information is provided for transferring the session to the service provider. The service provider performs the service on the item of content.

Automated Cosmetics Consulting and Related Apps - Pending

US 20060129411 A1, Filed Dec. 7, 2004: Method and system for cosmetics consulting using a transmitted image.

Inventors: N. Bhatti, T. Sima, S. Susstrunk, H. Baker, M. Harville
Assignee: Hewlett-Packard.
Summary: A new way for women to select cosmetics for themselves, when they do not want to go a "make-up lady" in a fancy store. Instead, you snap a picture of yourself with your cellphone or digital camera, while holding a special color chart, and the system automatically finds both your face and the color chart to determine the true color distribution (independent of illuminant and camera) of your skin, which in turn is used to select appropriate cosmetics (e.g. foundation) recommendations that are transmitted back to you via an SMS message or email.
Abstract: Embodiments of the present invention recite a system for providing product consulting using a transmitted image. In one embodiment, the present invention comprises an image capture device for capturing an image of a user and a reference color set. In embodiments of the present invention, the image capture device does not require a provided infrastructure when capturing the image. The system further comprises a categorizing system for determining at least one data category from data comprising the image. A result generator generates a result based upon the determining of the categorizing system. The system further comprises a result reporting system for conveying the product consultation to the user when the result is conveyed.

US 20070058858 A1, Filed Sep. 9, 2005: Method and system for recommending a product based upon skin color estimated from an image.
- Inventors: M. Harville, H. Baker, N. Bhatti, S. Susstrunk.
- Assignee: Hewlett-Packard
- Summary: Some specific methods for how to compute a cosmetics recommendation from a photograph of a person.
- Abstract: Embodiments of the present invention recite a computer implemented method for recommending a product based upon skin color estimated from a single captured image. In one embodiment of the present invention, a skin color estimate which is generated from a single captured image is accessed. The skin color estimate is then compared with a classification color. A correlation between the classification color and at least one product is accessed. Then, at least one of the products which corresponds with the classification color is recommended.
US 20070071314 A1, Filed Sep. 9, 2005: Capture and systematic use of expert color analysis.
- Inventors: N. Bhatti, H. Baker, M. Harville, S. Susstrunk
- Assignee: Hewlett-Packard
- Summary: How to gather data for training a system to provide automatic cosmetic recommendations, or other related recommendations based on color info, the way an expert (e.g. a cosmetician, fashion designer, home decorator) would.
- Abstract: Embodiments of the present invention recite a method of compiling color analysis parameters. In one embodiment of the present invention, a corrected color description of at least one test subject is constructed. The corrected color description of at least one test subject is then accessed. The at least one test subject is assigned to a classification color according the accessed corrected color description. The said classification color is then correlated with a prescriptive recommendation.
US 20070058859 A1, Filed. Sep. 9, 2005: True color communication.
- Inventors: H. Baker, N. Bhatti, S. Susstrunk, M. Harville
- Assignee: Hewlett-Packard
- Summary: Methods and applications for automatically color calibrating an image based on detection and analysis of a known color pattern in the scene, and transmitting the color corrected image and/or the correction info elsewhere. Some applications include matching paint at a hardware store to your current home decorations, or calibrating a video display.
- Abstract: Embodiments of the present invention recite a system and method for conveying the true color of a subject. In one embodiment, the present invention comprises an image capture device, an imaged reference color set comprising at least one reference color, and a control reference color set comprising at least one control color corresponding to the at least one reference color. The present invention further comprises a color correction component for accessing the control reference color set and the imaged reference color set and for generating a color correction function which eliminates a discrepancy between the at least one reference color and the at least one control color.

About 10 others I'm not sure I can tell you about...