Infinity Augmented Reality Israel Ltd.

Alibaba Technology (Israel) Ltd.

Alibaba Technologies (Israel) Ltd.

Matan Protter

Motti Kushnir

Felix Goldberg

Efrat Rotem

Ofer Kruzel

Ori Kotek

Chen Goldberg

A system and method is provided for improving sensor precision. In a training phase, a relatively low precision sensor system and a relatively high precision sensor system may record relatively low precision and relatively high precision training motion signals respectively of substantially the same training scene. Machine learning may be performed to generate a transformation mapping information from the relatively low precision training motion signal to the relatively high precision training motion signal. In a run-time phase, a run-time sensor system having a precision significantly less than the precision of the relatively high precision sensor system, may record run-time motion signals of a run-time scene. The run-time motion signal may be transformed using the transformation to generate a transformed run-time motion signal with a precision significantly greater than the precision of the run-time sensor system.

Dual-precision sensor system using high-precision sensor data to train low-precision sensor data for object localization in a virtual environment

A method and a system for calibrating an inertial measurement unit (IMU) via images of a calibration target are provided herein. The method may include: measuring parameters via an IMU; capturing a plurality of calibration images of a scene that contains at least one calibration target, wherein the calibration images are taken from different locations and/or orientations, wherein each of the calibration images shares a common calibration target with at least one other calibration image; calculating, based on the at least one common calibration target, a position and orientation of the sensing device relative to the calibration target, for each location of the capturing of the calibration images; and calibrating the IMU by comparing relative motion between two of the calibration images based on the calculated relative position and orientation, to measurements of the parameters taken by the IMU in time ranges corresponding to the at least two calibration images.

Method and system for calibrating components of an inertial measurement unit (IMU) using scene-captured data

A device, system and method is provided for estimating movement based on a human movement model in a virtual, augmented or mixed reality environment. In an offline phase, a human movement model may be stored that assigns a non-uniform probability of spatiotemporal representations of movements that occur in a human body. In an online phase, a user's movements may be recorded. The user's movements may be estimated by spatiotemporal representations of a plurality of (N) degrees of freedom (DOF) that maximize a joint probability comprising a first probability that the measured movements match the estimated movements and a second probability that the human movement model assigns to the spatiotemporal representations of the estimated movements. A virtual, augmented or mixed reality image may be displayed that is rendered based on the NDOF spatiotemporal representations of the estimated movements.

Device, system and method for improving motion estimation using a human motion model

A device, system, and method for applying time warp in an augmented or mixed reality environment. An image may be rendered corresponding to an estimated head position calculated based on head position and orientation measured at the initial time. Time warp may be independently applied to each sequential one of the plurality of segmented visual units of an image (e.g., color-frames or pixel-groups) to generate a plurality of respective time warp visual units corresponding to a plurality of different respective estimated head position and orientations calculated based on head position and orientations measured at a plurality of different respective sequential times after the initial time. The plurality of time warp visual units may be projected in the sequential order at the augmented or mixed reality device.

Optical engine time warp for augmented or mixed reality environment

A method and a system for analyzing distinct light or radiation sources affecting a scene are provided. The method may include: sensing at least one image of a scene containing surfaces and objects, wherein the scene is illuminated by at least one distinct radiation or source; maintaining a database of the scene which stores approximate positions of at least some of the objects in the scene; identifying at least one candidate silhouette suspected to be cast by the at least one distinct light or radiation source, deriving properties of the at least one distinct light or radiation source, based on the at least one identified silhouette, based on data derived from the database.

Method and a system for determining radiation sources characteristics in a scene based on shadowing analysis

Methods and a system for identifying reflective surfaces in a scene are provided herein. The system may include a sensing device configured to capture a scene. The system may further include a storage device configured to store three-dimensional positions of at least some of the objects in the scene. The system may further include a computer processor configured to attempt to obtain a reflective surface representation for one or more candidate surfaces selected from the surfaces in the scene. In a case that the attempted obtaining is successful, computer processor is further configured to determine that the candidate reflective surface is indeed a reflective surface defined by the obtained surface representation. According to some embodiments of the present invention, in a case the attempted calculation is unsuccessful, determining that the recognized portion of the object is an object that is independent of the stored objects.

Method and a system for identifying reflective surfaces in a scene

Methods and systems for generating synthetic samples of postures and gestures are provided. In one embodiment, the system may include: a database configured to store at least one sample of a posture or a gesture; a sensing device; and a computer processor configured to: derive values of parameters relating to a specific user and/or environment and generate datasets of gesture and posture samples based on the derived values. In another embodiment, a computer memory may be configured to: obtain at least one gesture or posture of at least one body part; and obtain data sets affecting the appearance of said postures and gestures; and a computer processor configured to generate sets of synthetic samples of said postures and gestures, based on the obtained data sets, wherein the synthetic samples embody virtual variations caused by at least one of the obtained data sets.

Method and system for generating a synthetic database of postures and gestures

Methods and systems for recalibrating sensing devices without using familiar targets are provided herein. The method may include: capturing a scene using a sensing device; determining whether or not the device is calibrated; in a case that said sensing device is calibrated, adding at least one new landmark to the known landmarks; in a case that said sensing device is not calibrated, determining at least some of the captured objects as objects stored on a database as known landmarks at the scene whose position is known; and calibrating the sensing device based on the known landmarks. The system may have various architectures that include a sensing device which captures images of the scene and further derive 3D data on the scene of some form.

Growing community of inventors

Kiryat Ono, Israel

Matan Protter