Patent application number | Description | Published |
20110292166 | North Centered Orientation Tracking in Uninformed Environments - A mobile platform uses orientation sensors and vision-based tracking to track with absolute orientation. The mobile platform generates a panoramic map by rotating a camera, which is compared to an image frame produced by the camera, to determine the orientation of the camera with respect to the panoramic map. The mobile platform also estimates an orientation of the panoramic map with respect to a world reference frame, e.g., magnetic north, using orientation sensors, including at least one accelerometer and a magnetic sensor. The orientation of the camera with respect to the world reference frame is then determined using the orientation of the camera with respect to the panoramic map and the orientation of the panoramic map with respect to the world reference frame. A filter, such as a Kalman filter, provides an accurate and stable estimate of the orientation of the panoramic map with respect to the world reference frame. | 12-01-2011 |
20120300020 | REAL-TIME SELF-LOCALIZATION FROM PANORAMIC IMAGES - Real-time localization is performed using at least a portion of a panoramic image captured by a camera on a mobile device. A panoramic cylindrical map is generated using images captured by the camera, e.g., as the camera rotates. Extracted features from the panoramic cylindrical map are compared to features from a pre-generated three-dimensional model of the environment. The resulting set of corresponding features may be used to determine the pose of the camera. For example, the set of corresponding features may be converted into rays between the panoramic cylindrical map and the three-dimensional model, where the intersection of the rays is used to determine the pose. The relative orientation of the camera may also be tracked by comparing features from each new image to the panoramic cylindrical map, and the tracked orientation may be fused with the pose. | 11-29-2012 |
20120300979 | PLANAR MAPPING AND TRACKING FOR MOBILE DEVICES - Real time tracking and mapping is performed using images of unknown planar object. Multiple images of the planar object are captured. A new image is selected as a new keyframe. Homographies are estimated for the new keyframe and each of a plurality of previous keyframes for the planar object that are spatially distributed. A graph structure is generated using the new keyframe and each of the plurality of previous keyframes and the homographies between the new keyframe and each of the plurality of previous keyframes. The graph structure is used to create a map of the planar object. The planar object is tracked based on the map and subsequently captured images. | 11-29-2012 |
20130230214 | SCENE STRUCTURE-BASED SELF-POSE ESTIMATION - Pose estimation is performed using a scene structure captured in a query image and reference images from a database. Each of the reference images has an associated position estimate. Direction vectors are generated that describe directions between an unknown position of a camera center for the query image and a reference camera center for each reference image based on the query image and the plurality of reference images. The direction vectors may be generated using, e.g., homographies, essential matrices, or fundamental matrices. A pose estimation with six degrees of freedom is determined using the direction vectors and the associated position estimate for each reference image. The pose estimation, for example, may be determined by solving a three-point pose problem using the direction vectors and the associated position estimate for each reference image. | 09-05-2013 |
20140016821 | SENSOR-AIDED WIDE-AREA LOCALIZATION ON MOBILE DEVICES - A mobile device uses vision and orientation sensor data jointly for six degree of freedom localization, e.g., in wide-area environments. An image or video stream is captured while receiving geographic orientation data and may be used to generate a panoramic cylindrical map of an environment. A bin of model features stored in a database is accessed based on the geographic orientation data. The model features are from a pre-generated reconstruction of the environment produced from extracted features from a plurality of images of the environment. The reconstruction is registered to a global orientation and the model features are stored in bins based on similar geographic orientations. Features from the panoramic cylindrical map are matched to model features in the bin to produce a set of corresponding features, which are used to determine a position and an orientation of the camera. | 01-16-2014 |
20140123507 | REFERENCE COORDINATE SYSTEM DETERMINATION - A method of determining a reference coordinate system includes: obtaining information indicative of a direction of gravity relative to a device; and converting an orientation of a device coordinate system using the direction of gravity relative to the device to produce the reference coordinate system. The method may also include setting an origin of the reference coordinate system and/or determining a scale value of the reference coordinate system. The method may also include refining the reference coordinate system. | 05-08-2014 |
20140126769 | FAST INITIALIZATION FOR MONOCULAR VISUAL SLAM - Apparatuses and methods for fast visual simultaneous localization and mapping are described. In one embodiment, a three-dimensional (3D) target is initialized immediately from a first reference image and prior to processing a subsequent image. In one embodiment, one or more subsequent reference images are processed, and the 3D target is tracked in six degrees of freedom. In one embodiment, the 3D target is refined based on the processed the one or more subsequent images. | 05-08-2014 |
Patent application number | Description | Published |
20130314442 | SPATIALLY REGISTERED AUGMENTED VIDEO - A source video stream is processed to extract a desired object from the remainder of video stream to produce a segmented video of the object. Additional relevant information, such as the orientation of the source camera for each frame in the resulting segmented video of the object, is also determined and stored. During replay, the segmented video of the object, as well as the source camera orientation are obtained. Using the source camera orientation for each frame of the segmented video of the object, as well as target camera orientation for each frame of a target video stream, a transformation for the segmented video of the object may be produced. The segmented video of the object may be displayed over the target video stream, which may be a live video stream of a scene, using the transformation to spatially register the segmented video to the target video stream. | 11-28-2013 |
20140320593 | MONOCULAR VISUAL SLAM WITH GENERAL AND PANORAMA CAMERA MOVEMENTS - Disclosed are a system, apparatus, and method for monocular visual simultaneous localization and mapping that handles general 6DOF and panorama camera movements. A 3D map of an environment containing features with finite or infinite depth observed in regular or panorama keyframes is received. The camera is tracked in 6DOF from finite, infinite, or mixed feature sets. Upon detection of a panorama camera movement towards unmapped scene regions, a reference panorama keyframe with infinite features is created and inserted into the 3D map. When panoramic camera movement extends toward unmapped scene regions, the reference keyframe is extended with further dependent panorama keyframes. Panorama keyframes are robustly localized in 6DOF with respect to finite 3D map features. Localized panorama keyframes contain 2D observations of infinite map features that are matched with 2D observations in other localized keyframes. 2D-2D correspondences are triangulated, resulting in new finite 3D map features. | 10-30-2014 |
20140323148 | WIDE AREA LOCALIZATION FROM SLAM MAPS - Exemplary methods, apparatuses, and systems for performing wide area localization from simultaneous localization and mapping (SLAM) maps are disclosed. A mobile device can select a first keyframe based SLAM map of the local environment with one or more received images. A respective localization of the mobile device within the local environment can be determined, and the respective localization may be based on the keyframe based SLAM map. The mobile device can send the first keyframe to a server and receive a first global localization response representing a correction to a local map on the mobile device. The first global localization response can include rotation, translation, and scale information. A server can receive keyframes from a mobile device, and localize the keyframes within a server map by matching keyframe features received from the mobile device to server map features. | 10-30-2014 |
20140327792 | METHODS FOR FACILITATING COMPUTER VISION APPLICATION INITIALIZATION - Embodiments disclosed pertain to systems, method s and apparatus for the initialization of Computer Vision (CV) applications on user devices (UDs) comprising a camera and a display. In some embodiments, an optimal camera trajectory for initialization of a Computer Vision (CV) application may be determined based on an initial camera pose and an estimated pivot distance. For example, the initial camera pose may be estimated based on a first image captured by the camera. Further, the display may be updated in real-time with an indication of a desired movement direction for the camera. In some embodiments, the indication of desired movement direction may be based, in part, on a current camera pose and the optimal trajectory, where the current camera pose may be estimated based on a current image captured by the camera. | 11-06-2014 |
20150062117 | SYSTEM AND METHOD FOR DETERMINING THE EXTENT OF A PLANE IN AN AUGMENTED REALITY ENVIRONMENT - Methods, systems, computer-readable media, and apparatuses for constructing a representation of a planar object are presented. In some embodiments, techniques for constructing a representation of a planar object are disclosed. According to some embodiments, a method for constructing a representation of a planar object may include obtaining a depth image of a physical scene as captured from a viewing position. The depth image may comprise a plurality of depth values and corresponding to a plurality of points in the physical scene. The method may further include identifying a planar surface along which the planar object is estimated to be positioned. Furthermore, the method may include constructing a support map. Moreover, the method may include constructing an occlusion map, the occlusion map indicating portions of the planar surface where the planar object is missing. Subsequently, the method may include constructing a representation of at least one boundary of the planar object, using the occlusion map. | 03-05-2015 |
20150070387 | STRUCTURAL MODELING USING DEPTH SENSORS - Techniques are presented for constructing a digital representation of a physical environment. In some embodiments, a method includes obtaining image data indicative of the physical environment; receiving gesture input data from a user corresponding to at least one location in the physical environment, based on the obtained image data; detecting at least one discontinuity in the physical environment near the at least one location corresponding to the received gesture input data; and generating a digital surface corresponding to a surface in the physical environment, based on the received gesture input data and the at least one discontinuity. | 03-12-2015 |