12 results about "Facial tracking" patented technology

The tracking system uses one or more light sources to direct light towards one or more of the user's eyes. A dynamic vision sensor (DVS) operably coupled to a processor is configured to visually recognize the user's eyes. The DVS has an array of photosensitive elements within a known configuration. The DVS outputs a signal corresponding to an event at a corresponding photosensitive element within the array in response to a change in the light from the light source reflected from a portion of the user's eye. The output signal includes information corresponding to the position of the corresponding photosensitive element within the array. The processor determines an association between each event and a corresponding particular light source and adapts the orientation of the user's eyes using the determined association, the relative position of the light source with respect to the user's eyes, and the position of the corresponding photosensitive element within the array.

Filtering subjects subject to facial image processing in a face-tracking environment by capturing at least one image using an image capture device, defining an inclusion polygon having at least three vertices such that at least one angle formed at at least one of said vertices is not a right angle, identifying a plurality of faces in said at least one image, defining a geometric shape around each said identified plurality of faces, respectively, excluding from further processing any of said identified faces with a defined geometric shape that that fails an inclusion criteria. Performing further processing on not-excluded identified faces to thereby determine an identification-linked property linked to such identified faces.

Techniques are described for improved eye-tracking through the combination of multiple sensor modalities. Embodiments of the present disclosure may include a wearable device (e.g., artificial-reality device) comprising an eye-tracking module that tracks the positions of either or both of the wearer's eyes based on image data of the eye(s) in addition to other sensor data. The additional sensor data may include, for instance, a depth sensor, an inertial sensor, a face-tracking system, or combinations thereof.

The embodiment of the invention discloses a dynamic head portrait Gaussian reconstruction method and system oriented to geometric reality. A specific embodiment of the method comprises the following steps: performing face tracking on each face image in a face image sequence to generate a model patch information set; based on the model patch information, executing a deformation operation on a Gaussian center and a covariance matrix to generate a Gaussian deformation matrix; generating a fusion deformation projection; constructing a dynamic BVH tree based on the fusion deformation projection, and executing topological rotation based on the dynamic BVH tree; selecting at least one Gaussian point as a jump point set, and constructing a local tetrahedral mesh based on the jump point set; and according to the local tetrahedral mesh, executing a triangular mesh extraction and reconstruction operation to generate a dynamic head portrait triangular mesh model. According to the embodiment, the accuracy of geometric reconstruction and the fidelity of facial details are improved, the triangular mesh extraction efficiency is improved, and rapid dynamic reconstruction can be supported.

The application provides a small animal-oriented face tracking image transmission system, comprising a transmitting end, a receiving end and an animal end stimulator; the transmitting end is an animal wearing structure, comprising a miniature camera and a wireless transmitting module; the miniature camera is used for capturing face images; the wireless transmitting module establishes communication with the receiving end through a wireless image transmission link and sends face video data collected by the miniature camera to the receiving end; the receiving end comprises a wireless receiving module, a video data stream module, a data analysis module and a stimulator control module. Through the cooperative matching of the transmitting end, the receiving end and the animal end stimulator, combined with wireless image transmission, face feature analysis and multi-mode stimulation feedback, the components such as the miniature camera and the wireless transmitting module in the application are small in size and light in weight, can be adapted to various small animals, and can detect small animals and reduce the dependence on manual observation.

The invention provides a short play video character facial feature intelligent matching analysis method, which comprises the following steps: analyzing a short play video, identifying adjacent frame pairs before and after hard cutting, separating a facial region and a clothing region from each frame, and obtaining a facial region pixel set and a clothing region pixel set; for the facial region pixel set and the clothing region pixel set, extracting facial Lab color space chromaticity coordinates and clothing Lab color space chromaticity coordinates of the frames before and after hard cutting; extracting the overall light source color temperature of the frames before and after hard cutting through the clothing color synchronous change mark, and correcting the color space chromaticity coordinates of the face Lab by adopting white balance to obtain the corrected skin color chromaticity coordinates; and determining a continuous tracking path according to the identity attribution of the same person and the face tracking chains of the frames before and after hard cutting.

A head mounted display for eye and face tracking includes an optical assembly arranged proximate to a user's eyes, a display panel arranged behind the optical assembly and visible to the user through the optical assembly along a line of sight of the user, a camera arranged within the display panel so that the user's eyes are visible to the camera through the optical assembly, and a light source arranged proximate to the camera so that light from the light source is incident upon the user's eyes through the optical assembly.

The utility model relates to the technical field of cosmetic mirrors, and discloses a cosmetic mirror with an angle rotating mechanism, which comprises an electric rotating base body, an adjusting assembly is arranged on the upper surface of the electric rotating base body, the adjusting assembly comprises a support frame, and a swing frame is arranged in the support frame. According to the make-up mirror with the angle rotating mechanism, through cooperation of the electric rotating base body and the adjusting assembly, flexible adjustment of the left-right angle and the up-down inclination of the mirror body is achieved, the best view angle can be easily found for making up, shaving or daily appearance tidying, diversified use requirements are met, and the make-up mirror is suitable for popularization and application. After adjustment is completed, the mirror body can be ensured to be stable and immovable by means of excellent stability, shaking caused by slight touch is avoided, and the use effect is prevented from being affected, the face tracking sensor is additionally arranged, the position change of the face of a user can be sensed in real time, the angle of the mirror body can be rapidly and accurately adjusted, the user does not need to manually adjust, and the optimal visual effect is always kept.

This invention relates to the field of medical image processing technology, and in particular to a system for image recognition and oral motor assessment of neonatal feeding behavior. The system includes a data acquisition module, a feature extraction module, a differential geometry modeling module, a trajectory analysis module, a cooperative motion analysis module, an anomaly detection module, a result display module, and an application service module. The system employs a high-speed camera, a 3D facial tracking camera, and an optical perspective camera working collaboratively. It simultaneously acquires multi-view image data of neonatal facial and oral motor movements through a data acquisition and analysis instrument. Innovatively, it applies differential geometry theory to oral motor analysis, treating facial feature point groups as Riemannian manifolds embedded in 3D Euclidean space. Through curvature feature calculation, shape operator construction, and differential invariant extraction, it accurately characterizes oral motor properties. The system constructs a coupled model of the lip manifold and the mandibular manifold, analyzing the synchronicity measurement and topological features between the manifolds to achieve accurate detection of feeding abnormalities.

This invention provides a facial recognition system, a facial recognition program, and a facial recognition method for appropriately performing authentication processing for online learning. [Solution] A facial recognition system for performing facial recognition of online learning participants, wherein the information processing device 1 comprises an acquisition unit 12, a tracking processing unit 13, and an authentication processing unit 15, and the authentication device 4 comprises an authentication database 5, the authentication database stores authentication facial information for authenticating participants, the acquisition unit acquires the participant's facial information while they are taking the online learning course, the tracking processing unit performs facial tracking based on the facial information, and the authentication processing unit performs authentication based on the facial information from which the facial tracking process was successful and the authenticated facial information.

A computing system can determine, based on one or more sensors associated with a handheld device, a device pose of the handheld device in a real-world space. The system can determine, based on facial tracking data of the handheld device, a head pose of a first user associated with the handheld device, the head pose being relative to the handheld device in the real-world space; the system can render, in a virtual space, a first avatar associated with the first user based on the head pose of the first user in the real-world space. The system can render, in the virtual space, one or more virtual objects for the first user based on the head pose of the first user in the real-world space.