Ultrahaptics IP Two Limited

The technology disclosed can provide methods and systems for identifying users while capturing motion and/or determining the path of a portion of the user with one or more optical, acoustic or vibrational sensors. Implementations can enable use of security aware devices, e.g., automated teller machines (ATMs), cash registers and banking machines, other secure vending or service machines, security screening apparatus, secure terminals, airplanes, automobiles and so forth that comprise sensors and processors employing optical, audio or vibrational detection mechanisms suitable for providing gesture detection, personal identification, user recognition, authorization of control inputs, and other machine control and/or machine communications applications. A virtual experience can be provided to the user in some implementations by the addition of haptic, audio and/or other sensory information projectors.

The technology disclosed relates to adjusting the monitored field of view of a camera and/or a view of a virtual scene from a point of view of a virtual camera based on the distance between tracked objects. For example, if the user's hand is being tracked for gestures, the closer the hand gets to another object, the tighter the frame can become—i.e., the more the camera can zoom in so that the hand and the other object occupy most of the frame. The camera can also be reoriented so that the hand and the other object remain in the center of the field of view. The distance between two objects in a camera's field of view can be determined and a parameter adjusted based thereon. In particular, the pan and/or zoom levels of the camera may be adjusted in accordance with the distance.

The technology disclosed relates to determining positional information of an object in a field of view. In particular, it relates to measuring, using a light sensitive sensor, returning light that is (i) emitted from respective directionally oriented non-coplanar light sources of a plurality of directionally oriented light sources and (ii) returning from the target object, such as an automobile, as the target object moves through a region of space monitored by the light sensitive sensor. The technology disclosed compares the measured returning light to a look-up table that comprises mappings of measurements from the light sensitive sensor to a corresponding incoming angle of light; and determines positional information for the target object using the incoming angle of light.

Free space machine interface and control can be facilitated by predictive entities useful in interpreting a control object's position and/or motion (including objects having one or more articulating members, i.e., humans and/or animals and/or machines). Predictive entities can be driven using motion information captured using image information or the equivalents. Predictive information can be improved applying techniques for correlating with information from observations.

The technology disclosed relates to identifying an object in a field of view of a camera. In particular, it relates to identifying a display in the field of view of the camera. This is achieved by monitoring a space including acquiring a series of image frames of the space using the camera and detecting one or more light sources in the series of image frames. Further, one or more frequencies of periodic intensity or brightness variations, also referred to as ‘refresh rate’, of light emitted from the light sources is measured. Based on the one or more frequencies of periodic intensity variations of light emitted from the light sources, at least one display that includes the light sources is identified.

The technology disclosed relates to simplifying updating of a predictive model using clustering observed points. In particular, it relates to observing a set of points in 3D sensory space, determining surface normal directions from the points, clustering the points by their surface normal directions and adjacency, accessing a predictive model of a hand, refining positions of segments of the predictive model, matching the clusters of the points to the segments, and using the matched clusters to refine the positions of the matched segments. It also relates to distinguishing between alternative motions between two observed locations of a control object in a 3D sensory space by accessing first and second positions of a segment of a predictive model of a control object such that motion between the first position and the second position was at least partially occluded from observation in a 3D sensory space.

The technology disclosed also initializes a new hand that enters the field of view of a gesture recognition system using a parallax detection module. The parallax detection module determines candidate regions of interest (ROI) for a given input hand image and computes depth, rotation and position information for the candidate ROI. Then, for each of the candidate ROI, an ImagePatch, which includes the hand, is extracted from the original input hand image to minimize processing of low-information pixels. Further, a hand classifier neural network is used to determine which ImagePatch most resembles a hand. For the qualified, most-hand like ImagePatch, a 3D virtual hand is initialized with depth, rotation and position matching that of the qualified ImagePatch.

The technology disclosed performs hand pose estimation on a so-called “joint-by-joint” basis. So, when a plurality of estimates for the 28 hand joints are received from a plurality of expert networks (and from master experts in some high-confidence scenarios), the estimates are analyzed at a joint level and a final location for each joint is calculated based on the plurality of estimates for a particular joint. This is a novel solution discovered by the technology disclosed because nothing in the field of art determines hand pose estimates at such granularity and precision. Regarding granularity and precision, because hand pose estimates are computed on a joint-by-joint basis, this allows the technology disclosed to detect in real time even the minutest and most subtle hand movements, such a bend/yaw/tilt/roll of a segment of a finger or a tilt an occluded finger, as demonstrated supra in the Experimental Results section of this application.

Free space machine interface and control can be facilitated by predictive entities useful in interpreting a control object's position and/or motion (including objects having one or more articulating members, i.e., humans and/or animals and/or machines). Predictive entities can be driven using motion information captured using image information or the equivalents. Predictive information can be improved applying techniques for correlating with information from observations.

The technology disclosed introduces two types of neural networks: “master” or “generalists” networks and “expert” or “specialists” networks. Both, master networks and expert networks, are fully connected neural networks that take a feature vector of an input hand image and produce a prediction of the hand pose. Master networks and expert networks differ from each other based on the data on which they are trained. In particular, master networks are trained on the entire data set. In contrast, expert networks are trained only on a subset of the entire dataset. In regards to the hand poses, master networks are trained on the input image data representing all available hand poses comprising the training data (including both real and simulated hand images).