83 results about "Point of regard" patented technology

A gaze direction determining system and method is provided. A two-camera system may detect the face from a fixed, wide-angle camera, estimates a rough location for the eye region using an eye detector based on topographic features, and directs another active pan-tilt-zoom camera to focus in on this eye region. A eye gaze estimation approach employs point-of-regard (PoG) tracking on a large viewing screen. To allow for greater head pose freedom, a calibration approach is provided to find the 3D eyeball location, eyeball radius, and fovea position. Both the iris center and iris contour points are mapped to the eyeball sphere (creating a 3D iris disk) to get the optical axis; then the fovea rotated accordingly and the final, visual axis gaze direction computed.

This invention discloses an optical object tracking method and system with to up to six degrees of freedom: three translational and three angular coordinates. In the preferred embodiment, the system includes two near-infra-red light sources (e.g., light emitting diode), two cameras, and a digital signal processor. The system performs to tasks: object locking and tracking. For object locking and tracking, a single camera and two off-axis light sources are engaged. For more precise object tracking, two spatially-separate cameras and a single diode are used. In another embodiment, a third camera may be used to separate the locking and tracking tasks. The light sources may have different light wavelengths and may operate in a sequential mode. The cameras may be sensitive over different spectral ranges and may also differ in terms of field-of-view and resolution. The invention describes a method based on capturing images of light reflections at the camera focal plane and analyzing them, through mathematical mapping, for known locations of light sources and cameras. Invention can be adopted for the tracking of an eyeball. The related method determines an object location and orientation or a gaze vector and a point-of-regard.

A computer based eye-tracking solution is disclosed. A computer apparatus is associated with one or more graphical displays (GUI components) that may be manipulated based on user-generated commands. An event engine is adapted to receive an eye-tracking data signal that describes a user's point of regard on the display. Based on the signal, the event engine is adapted to produce a set of non-cursor controlling event output signals, which influence the GUI-components. Each non-cursor controlling event output signal describes a particular aspect of the user's ocular activity in respect of the display. Initially, the proposed event engine receives a control signal request from each of the GUI-components. The control signal request defines a sub-set of the set of non-cursor controlling event output signals which is required by the particular GUI-component. The event engine delivers non-cursor controlling event output signals to the GUI-components in accordance with each respective control signal request.

A method and apparatus are provided for generating a sale offer over an electronic network (such as the Internet). The method and apparatus may be used with a commercial sale system designed to increase the revenue income of Web site by offering, at a substantially discounted or virtually free basis, one or more goods and / or services to visitors of the Web site. According to the features of the invention, the seller (who may be the owner or co-owner of the Web site) transmits a sale offer on the Web site for a high quality good or service, wherein the good or service can be purchased for free or a cost near to zero. The seller may make the offer visible and available to a number of perspective buyers, who are connected at that very moment to the Web site. According to an additional aspect of the invention, the sale offer may be available for only a very limited amount of time (e.g., one or more minutes) and may be offered at random or unpredictable times on the Web site in order to increase Web traffic to the site.

The present invention relates to entry of control commands into a computer in response to eye-tracker detected movement sequences of a point of regard over a graphical display, which is associated with the computer. A processing module in the computer causes the display to present graphical feedback information in the form of a data-manipulating window, which visually confirms any entered control commands. The data-manipulating window is presented at a position relative to an active control object on the display, such that a center point of the window is located within a relatively small offset distance from a center point of the active control object. The window includes graphical information, which symbolizes and activity portion of the display presently being the object of an eye-tracker-controlled entry of control commands. Moreover the information in the window is repeatedly updated in response to the eye-tracker-controlled entry of control commands.

An image generation device and an information storage medium that make it possible to increase the virtual realism and dramatic effect of a shooting, game in an efficient manner. A plurality of objects such as target objects are set within an object space, and a hit check is performed on shots from 1P and 2P players and the target objects. First and second viewpoints for the 1P and 2P players are controlled and images as seen from those first and second viewpoints are output to first and second display screens, respectively. Although the viewpoints of the 1P and 2P players are the same in the prior art, they can be made different in this game. The first and second viewpoints move along first and second movement paths, and the first and second viewpoints are controlled in such a manner that the first and second movement paths diverge when a given circumstance occurs. The configuration is such that a target object and a character object representing one player can enter into the field of view of the other player. The first and second viewpoints and the target object are controlled in accordance with a difference in game results between the 1P and 2P players.

A method for processing three-dimensional data that defines a three-dimensional scene, and determining and displaying lines-of-sight (LOS) and viewsheds on all visible surfaces of the scene, includes: i) assigning at a user-selected location at least one viewpoint in the scene; ii) applying ray tracing from locations in the scene to the viewpoint to determine locations in the scene that are in a line of sight (LOS) and outside the LOS of the viewpoint, thus determining the viewshed relative to the viewpoint while generating a set of color-coding information; iv) saving the set of color-coding information as a 2D texture image in graphics hardware memory; and v) compositing the 2D texture image over the 3D scene in a 3D window at a frame rate that enables real-time updating of the color coding as the scene is translated or rotated or the viewpoint is changed.

A computer based eye-tracking solution is disclosed. A computer apparatus is associated with one or more graphical displays (GUI components) that may be manipulated based on user-generated commands. An event engine is adapted to receive an eye-tracking data signal that describes a user's point of regard on the display. Based on the signal, the event engine is adapted to produce a set of non-cursor controlling event output signals, which influence the GUI-components. Each non-cursor controlling event output signal describes a particular aspect of the user's ocular activity in respect of the display. Initially, the proposed event engine receives a control signal request from each of the GUI-components. The control signal request defines a sub-set of the set of non-cursor controlling event output signals which is required by the particular GUI-component. The event engine delivers non-cursor controlling event output signals to the GUI-components in accordance with each respective control signal request.

An animation generating apparatus for generating a three-dimensional animation tracking a moving object includes a camera parameter setting section setting a point of regard and a point of view based on a current position of the moving object using route data indicating a route of the moving object so that the point of regard is located on the route and the point of view is located behind the point of regard along the route, and a rendering processor generating an image by retrieving necessary rendering data from three-dimensional map data based on the point of regard and point of view set by the camera parameter setting section.

A method and system are provided for controlling the display of an mobile device by: capturing an image using a camera device of the mobile device, the camera device being directed in a same direction as a display of the mobile device, the image comprising one or more subjects (e.g. users or other humans seen in the image); determining a point of regard in the image for at least one of the one or more subjects, the point of regard being indicative of an area on the display at which a gaze of the corresponding subject is directed; determining, based on the point of regard, an instruction for controlling the display; and controlling the display according to the instruction, wherein controlling the display includes reducing visibility of at least one portion of what is displayed on the display.

The invention provides a control system for playing and pausing videos by detecting a point of regard of eyeballs. The control system is used for detecting eyeball moving traces and comprises a mobile phone operating system, an infrared front-mounted camera and a processor, wherein the infrared front-mounted camera detects states of the eyeballs and transmits the detection information to the processor; and the processor controls pause and playing of the videos according to the states of the eyeballs. The videos can be played and paused through an eyeball point of regard detection technology, the infrared camera and mobile phone software, so that a user can conveniently play and pause the videos without the help of a hand under some scenes, and convenience can be brought to the user by a brand-new interaction mode.

The present invention relates to entry of control commands into a computer in response to eye-tracker detected movement sequences of a point of regard over a graphical display, which is associated with the computer. A processing module in the computer causes the display to present graphical feedback information in the form of a data-manipulating window, which visually confirms any entered control commands. The data-manipulating window is presented at a position relative to an active control object on the display, such that a center point of the window is located within a relatively small offset distance from a center point of the active control object. The window includes graphical information, which symbolizes and activity portion of the display presently being the object of an eye-tracker-controlled entry of control commands. Moreover the information in the window is repeatedly updated in response to the eye-tracker-controlled entry of control commands.

A method, apparatus and computer-usable medium for discovering groups of users that are distinguished by common views of on-line documents and content items. These common views are analyzed to recommend and facilitate introductions to potential corresponding parties and / or the formation of communities of interest. Users' interactions are logged for a specific task or time period according to predetermined scoping parameters. Accordingly, potential contacts relevant to a current task can be recommended as well as general contact recommendations relevant to interactions over a longer time period. Users can thereby find advisors or mentors for the current task they are performing as well as individuals they may want to contact in general.

A gaze direction determining system and method is provided. A two-camera system may detect the face from a fixed, wide-angle camera, estimates a rough location for the eye region using an eye detector based on topographic features, and directs another active pan-tilt-zoom camera to focus in on this eye region. A eye gaze estimation approach employs point-of-regard (PoG) tracking on a large viewing screen. To allow for greater head pose freedom, a calibration approach is provided to find the 3D eyeball location, eyeball radius, and fovea position. Both the iris center and iris contour points are mapped to the eyeball sphere (creating a 3D iris disk) to get the optical axis; then the fovea rotated accordingly and the final, visual axis gaze direction computed.

An eye gaze tracking system is disclosed. The system includes a gaze data acquisition system including a plurality of light sources and a plurality of image sensors. The plurality of light sources are arranged to emit light to a head of the user, and the plurality of image sensors are configured to receive the light. In an embodiment, the system further includes a gaze tracking module including an ocular feature extraction module, a point of regard (POR) calculation module and a POR averaging module. The ocular feature extraction module is configured to process the gaze data and to extract ocular features, and is configured to determine a confidence value associated with an accuracy of the parameters. The POR calculation module is configured to determine a POR from the ocular features. The POR averaging module is configured to determine an average POR.

A system and method are provided for displaying search results on an electronic device. The method includes: displaying at least a portion of a first set of search results; capturing one or more images using a camera device of the electronic device, the camera device being directed in a same direction as a display of the electronic device, the image comprising one or more subjects; determining corresponding points of regard in the one or more images for at least one of the one or more subjects, the points of regard being indicative of areas on the display at which a gaze of the corresponding subject is directed; determining one or more search results associated with the points of regard; and displaying further search results based on information associated with the one or more search results associated with the points of regard.

The invention provides an eye movement track law analysis method. The eye movement track law analysis method comprises the following steps: Q fixation data of a page to be surveyed are acquired, wherein the Q is a positive integer greater than 1; Q corresponding eye movement tracks are generated according to the Q fixation data respectively; the diversity factor between every two of the Q eye movement tracks is acquired; according to the diversity factor between every two of the Q eye movement tracks, the Q eye movement tracks are clustered to generate at least one eye movement track category, and at least one eye movement track law for the page to be surveyed is generated according to at least one eye movement track category. According to the eye movement track law analysis method, the fixation data are acquired and used for generating the eye movement tracks, the eye movement tracks are clustered to generate the eye movement track categories, and then the eye movement track laws are generated; concern points and a concern order of a user are reflected accurately, and support is provided for more developers in respect of website monitoring and optimization; cost of manual analysis is lowered, reliability is improved, and user experience is enhanced.

Described herein is a method for enabling human-to-computer three-dimensional hand gesture-based natural interactions from depth images provided by a range finding imaging system. The method enables recognition of simultaneous gestures from detection, tracking and analysis of singular points of interests on a single hand of a user and provides contextual feedback information to the user. The singular points of interest of the hand: include hand tip(s), fingertip(s), palm centre and centre of mass of the hand, and are used for defining at least one representation of a pointer. The point(s) of interest is / are tracked over time and are analysed to enable the determination of sequential and / or simultaneous “pointing” and “activation” gestures performed by a single hand.

A method of controlling the position and orientation of user controlled computer generated avatars in computer generated virtual world in a manner that tends to bias the user controlled avatar positions and orientations in a way that sends useful non-verbal social cues to outside observers. These non-verbal cues can include cues such as “this conversation is open to outside participants” and “this conversation is private”. The methods can also convey “stage presence” to that can somewhat bias the position and orientation of the user controlled avatars in a manner that takes the viewpoint of an outside observer into account. These effects can be modulated up or down as desired, and may be further modulated by the degree of social connections or past history of virtual world interactions between various users.

The present invention belongs to the computer vision field, and relates to a point of regard detection method based on the multilayer information fusion. The point of regard detection method is characterized by obtaining a bottom-layer information detection result diagram by the bottom-layer information, such as the colors, etc.; utilizing the spatial position to obtain a center prior diagram; extracting a candidate target frame and the CNN depth features of an original image, utilizing a bag-of-word model to encode, sending the encoded visual features in a trained multi-instance RMI-SVM classifier to mark, and carrying out the Gaussian smoothing on the center of the frame and then carrying out the weighted stack according to the mark of the target frame to obtain a detection result diagram of a target grade; extracting the features describing the overall content of the original image itself, training a softmax regression device to obtain the fusion weight, and adopting the weight to carry out the weighted fusion on the above result diagram. The point of regard detection method of the present invention comprehensively utilizes the information at the three aspects of the color contrast, the significant target and the spatial position, adjusts the proportion of various information aiming at different images, and can have a better detection rate aiming at the image containing various content.

The present disclosure describes methods and systems directed towards providing scaled engagement and views of an e-sports event. Instead of providing the same distribution of live e-sport event data to all remote viewers of a live e-sports event, features associated with e-sports gaming network could be used to customize the distribution of live e-sport event data to promote immersive viewer experience. The enhanced immersion can also be carried out in a virtual reality or augmented reality setting. The features would be capable of providing additional information, different views, and a variety of different commentators for the e-sports event so that the viewer can be more engaged when viewing the particular e-sports event. With the increased engagement from remote viewers, the distribution of live e-sports event data can also be further modified for monetization by incorporating advertisements as well.

A computer-implemented method of communicating via interaction with a user-interface based on a person's gaze and gestures, comprising: computing an estimate of the person's gaze comprising computing a point-of- regard on a display through which the person observes a scene in front of him; by means of a scene camera, capturing a first image of a scene in front of the person's head (and at least partially visible on the display) and computing the location of an object coinciding with the person's gaze; by means of the scene camera, capturing at least one further image of the scene in front of the person's head, and monitoring whether the gaze dwells on the recognised object; and while gaze dwells on the recognised object: firstly, displaying a user interface element, with a spatial expanse, on the display face in a region adjacent to the point-of-regard; and secondly, during movement of the display, awaiting and detecting the event that the point-of- regard coincides with the spatial expanse of the displayed user interface element. The event may be processed by communicating a message.

A method capable of converting motion image data, which is captured in an ordinary way without intending to produce parallax image printed matter, to data that can be printed as parallax image printed matter is provided. The method includes the steps of specifying at least one frame as a reference frame from a plurality of frames constituting the motion image data, and setting a point-of-regard on an object in the reference frame, calculating an amount of movement of the point-of-regard using a relation between the point-of-regard in the reference frame and a point corresponding thereto in another frame, obtaining a motion compensation amount for each frame based on this amount of movement thereof, and executing a motion compensation processing for the motion image data based on the motion compensation amount, thereby converting the motion image data to parallax image data.

The invention discloses an eye movement data-based electroencephalogram experiment evaluation system and method. The method comprises the following steps of: acquiring eye movement data of an object through an eye tracker, and establishing a time-space model according to a point of regard in the eye movement data; calculating a similarity between sequences by using a dynamic time wrapping algorithm fast technology, establishing a distance matrix, carrying out outlier detection through a density-based clustering algorithm, and carrying out quantitative sorting by adoption of a learning, sorting and training model according to a clustering result so as to obtain a participation degree of the object. According to the system and method, the experiment participation degrees of objects can be objectively and quantitatively evaluated, so as to form feedbacks for experiments and models and then ensure the data quality and improve the model prediction accuracy. According to the system and method, quantitative evaluation is carried out on the experiment participation degrees of the objects, and quantitative feedbacks of emotion recognition experiment are constructed.

A system and method for organizing and evaluating different points of view on controversial topics that minimizes the ‘spin’ that typically accompanies different opinions, and also minimizes the tendency to ‘cherry pick’ issues by emphasizing only those that support a particular point of view and ignoring others. It allows these different points of view to be compared side by side, and computes the similarity between them.

A passive guidance system including a viewpoint capture system (VCS) including a first processor in communication with first memory and a first SWIR imager for creating a viewpoint image database having a plurality of images, at least one of the images having a target point. A weapon guidance module is in communication with the VCS and coupled to a weapon. The weapon guidance module includes a second processor in communication with second memory and a second SWIR imager for storing the viewpoint image database and correlating in-flight images from the second SWIR imager to provide guidance commands directing the weapon to the target point.

The embodiment of the invention provides a method, a device, equipment and a system for determining a focus point, and an information processing method, and belongs to the technical field of information processing. The method for determining the focus comprises the following steps: acquiring at least two images of a scene; and determining a focus point of the object in the image in the scene basedon the at least two images. According to the method provided by the embodiment of the invention, the attention point of the object in the real scene can be determined without wearing any equipment bythe object, the method can be suitable for an actual application scene without wearing extra equipment by the object, and a more natural interaction mode can be provided for the object.

The invention aims to provide a method and equipment for preferably selecting an open type interactive forum based on user interests. The method comprises the steps of: acquiring an interest keyword sequence of a user by forum preference equipment; performing matching selection according to the interest keyword sequence to acquire one or more open type interactive forums matched with the interests of the user; and providing the one or more open type interactive forums to the user for selection. Compared with the prior art, the method makes information sharing and viewpoint exchange between the user and people with same interests possible by preferably selecting the open type interactive forum on the basis of the user interests, so that the method can better serving the requirements of people for acquiring high-quality information and realizing effective interactive communication.

The present disclosure generally relates to a gaze tracking device. Gaze tracking is a process of measuring either the point of regard or the motion of an eye relatively to the head of a person. A gaze tracking device is a device capable of measuring eye positions and eye movement. In order to track the gaze of a person, infra-red light is projected into the user's eye. Utilizing the primary Purkinje reflection and the pupil-masked reflection, the position of the eye of the user is determined. The gaze tracking devices running such a tracking method offer a limited field of view due to the illumination scheme combined with the geometry of the reflected images. It is proposed a gaze tracking device embedding a light-field camera. Such a gaze tracking device may be embedded in a head mounted device.

An animation generating apparatus for generating a three-dimensional animation tracking a moving object includes a camera parameter setting section setting a point of regard and a point of view based on a current position of the moving object using route data indicating a route of the moving object so that the point of regard is located on the route and the point of view is located behind the point of regard along the route, and a rendering processor generating an image by retrieving necessary rendering data from three-dimensional map data based on the point of regard and point of view set by the camera parameter setting section.