Qualcomm Incorporated

Ptc Inc.

Qi Pan

Daniel Wagner

Michael Gervautz

Per Nielsen

Emilio Maggio

Gerhard Reitmayr

Stephen Prideaux-Ghee

Andre Gosselin

Zsolt Szalavari

Irene Reisner-Kollmann

Istvan Siklossy

Vincent Del Castillo

Andrew Gee

Romain Tallonneau

Peter Hans Rauber

Roy Lawrence Ashok Inigo

Slawomir K Grzechnik

Youngmin Park

Stefan Walk

Winston Yll

Wonwoo Lee

Disclosed are a system, apparatus, and method for in-situ creation of planar natural feature targets. In one embodiment, a planar target is initialized from a single first reference image one or more subsequent images are processed. In one embodiment, the planar target is tracked in six degrees of freedom upon the processing of the one or more subsequent images and a second reference image is selected from the processed one or more subsequent images. In one embodiment, upon selecting the second reference image the planar target is refined to a more accurate planar target.

In situ creation of planar natural feature targets

An example method includes: obtaining, from computer memory, information from a three-dimensional (3D) graphical model that represents an object; identifying, based on the information, a first part of the object having an attribute; performing a recognition process on the object based on features of the object, where the recognition process attaches more importance to a second part of the object than to the first part, with the second part either not having the attribute or having less of the attribute than the first part; and providing data for rendering content on a graphical user interface based, at least in part, on recognition of the object performed by the recognition process.

Processing uncertain content in a computer graphics system

Systems, methods, and devices are described for constructing a digital representation of a physical scene by obtaining information about the physical scene. Based on the information, an initial portion of a planar surface within the physical scene may be identified. In one aspect of the disclosure, constructing a digital representation of a physical scene may include obtaining information about the physical scene, identifying a planar surface within the physical scene, selecting a physical object within the physical scene, placed above the planar surface, detecting properties associated with the physical object, generating a three-dimensional (3D) reconstructed object using the properties associated with the physical object, and representing the planar surface as an augmented reality (AR) plane in an augmented reality environment, wherein the AR plane in the AR environment is capable of supporting 3D reconstructed objects on top of it.

Method and apparatus for representing a physical scene

A computer-implemented method of tracking a target object in an object recognition system includes acquiring a plurality of images with a camera and simultaneously tracking the target object and dynamically building online map data from the plurality of images. Tracking of the target object is based on the online map data and the offline map data. In one aspect, tracking the target object includes enabling only one of the online map data and offline map data for tracking based on whether tracking is successful. In another aspect, tracking the target object includes fusing the online map data with the offline map data to generate a fused online model.

Dynamic extension of map data for object detection and tracking

Disclosed are a system, apparatus, and method for detecting objects. Input image frames may be received and distinct regions created within each frame. Descriptors may be extracted from the regions according to their associated probability. Extracted descriptors may be matched to reference descriptors. Votes or confidence is cast for particular regions according to region properties. The region properties may be determined from center voting methods based on vector intersection to other vectors or intersections with a region. The probability of selecting particular regions can increase with each vote or increase in confidence for a region. In response to updating probabilities, additional regions may be selected and additional descriptors may be extracted. Additional voting iterations can update the probability of selecting a next region. An object pose may be estimated in response to meeting one or more thresholds.

Optimized object detection

Techniques are presented for expanding a digital representation of a physical plane from a physical scene. In some aspects, a method may include determining an orientation and an initial portion of a physical plane in the scene, and subdividing a rectified image for the scene into a plurality of grid cells. For the grid cells, an image signature may be generated. A grid cell contiguous to the obtained initial portion of the plane is determined to include part of the plane. An iterative process may be performed for each neighboring grid cell from the grid cell contiguous to at least part of the obtained initial portion, determining whether the neighboring grid cell is to be included as part of the plane if the image signature of said neighboring grid cell is similar to the image signature of a grid cell already determined to be included as part of the plane.

Expanding a digital representation of a physical plane

Methods, systems, computer-readable media, and apparatuses for assigning a color class of a defined finite set of colors to at least one sub-region within a test image are presented. A plurality of sub-regions are identified within a test image. A first sub-region color value is determined for a selected first sub-region of the test image. Using the first sub-region color value and a plurality of zero-order probability distributions, a first color class of the defined finite set of colors is determined as a hypothesis color for the first sub-region. A second sub-region color value is determined for a selected second sub-region of the test image. Using the second sub-region color value and a conditional probability distribution conditioned on the hypothesis color for the first sub-region, a second color class of the defined set of colors is determined. The second color class is assigned to the second sub-region.

Probabilistic color classification

Disclosed is a server that can perform a visual search using at least one rectified image. A method implemented at a server includes storing a plurality of images with the server, receiving at least one rectified image having at least one potential object of interest from a computing device for a visual search, and extracting descriptors representing features of the at least one rectified image. The extracted descriptors of the at least one rectified image are designed to be invariant to rotation, scale, and lighting without needing to be invariant to perspective or affine distortion.

Performing a visual search using a rectified image

A computer-implemented method of tracking a target object in an object recognition system includes acquiring a plurality of images with a camera. The method further includes simultaneously tracking the target object and dynamically building environment map data from the plurality of images. The tracking of the target object includes attempting to estimate a target pose of the target object with respect to the camera based on at least one of the plurality of images and based on target map data. Next, the method determines whether the tracking of the target object with respect to the camera is successful. If not, then the method includes inferring the target pose with respect to the camera based on the dynamically built environment map data. In one aspect the method includes fusing the inferred target pose with the actual target pose even if tracking is successful to improve robustness.

Object tracking based on dynamically built environment map data

Method, mobile device, computer program product and apparatus for performing a search are disclosed. The method of performing a search comprises receiving one or more images of an environment in view of a mobile device, generating a simultaneous localization and mapping of the environment using the one or more images, wherein the simultaneous localization and mapping of the environment comprises a plurality of map points representing a plurality of surfaces in a three dimensional coordinate system of the environment, sending a set of the plurality of map points as a search query to a server, receiving a query response from the server, and identifying an object in the environment based at least in part on the query response.

Client-server based dynamic search

Disclosed is a method and apparatus for selecting a part of SLAM map information of a first device for transmission to a second device in a collaborative SLAM environment. In one embodiment, the functions implemented include: determining whether a 3D registration transformation between a map of the first device and a map of the second device is available; and transmitting a part of map information of the first device to the second device according to one of a first strategy or a second strategy based on whether or not a 3D registration transformation between the map of the first device and the map of the second device is available.

Selection strategy for exchanging map information in collaborative multi-user SLAM systems

Various methods, apparatuses and/or articles of manufacture are provided which may be implemented for use by an electronic device to track objects across two or more digital images. For example, an electronic device may generate a plurality of warped patches corresponding to a reference patch of a reference image, and combine two or more warped patches to form a blurred warped patch corresponding to the reference patch with a motion blur effect applied to a digital representation corresponding to a keypoint of an object to be tracked.

Motion blur aware visual pose tracking

Disclosed is a computing device that can perform automatic image rectification for a visual search. A method implemented at a computing device includes receiving one or more images from an image capture device, storing the one or more images with the computing device, building a three dimensional (D) geometric model for one or more potential objects of interest within an environment based on at least one image of the one or more images, and automatically creating at least one rectified image having at least one potential object of interest for a visual search.

Growing community of inventors

Vienna, Austria

Qi Pan