Abstract: An image processing system configured to obtain a mesh representation of a scene, wherein the mesh representation comprises a plurality of polygons defined by respective vertices associated with an in-plane position, the in-plane position being in a plane comprising a first dimension and a second dimension, and the vertices having an associated vertex depth value in a third dimension different from the first dimension and the second dimension. The image processing system comprises an in-plane position estimation network configured to process image data representative of an image of the scene to estimate the in-plane positions associated with respective vertices of the mesh representation. The image processing system further comprises a depth estimation engine configured to process the in-plane positions and the image data to estimate the associated vertex depth values for the respective vertices of the mesh representation.

Abstract: A method comprising applying an object recognition pipeline to frames of video data. The object recognition pipeline provides a mask output of objects detected in the frames. The method includes fusing the mask output of the object recognition pipeline with depth data associated with the frames of video data to generate a map of object instances, including projecting the mask output to a model space for the map of object instances using a camera pose estimate and the depth data. An object instance in the map of object instances is defined using surface-distance metric values within a three-dimensional object volume, and has an object pose estimate indicating a transformation of the object instance to the model space. The object pose estimate and the camera pose estimate form nodes of a pose graph for the map of model instances.

Abstract: A computer-implemented method of determining a location of a mobile device is provided. The method can include receiving inertial data generated at the mobile device, the inertial data including a plurality of samples taken at different times, segmenting the inertial data into pseudo-independent windows, wherein each pseudo-independent window can include a plurality of the samples and wherein one or more initial states for each pseudo-independent window are treated as unknown, estimating a change in navigation state over each pseudo-independent window using the samples of inertial data, and summing the changes in the navigation states over the pseudo-independent windows so as to determine the location of the mobile device.

Abstract: A computer-implemented method of determining the location of a mobile device comprising a camera. The method comprises the steps of capturing, using the camera, a sequence of images over a period of time; for pairs of consecutive images from the sequence of images, determining, using a first neural network, features indicative of the motion of the device between the time the first image of the pair of images was captured and the time the second image of the pair of images was captured; for a sequence of consecutive images, determining, using a second neural network, features indicative of the location of the device from the features determined by the first neural network; and for a sequence of consecutive images, determining the location of the device from the features determined by the second neural network.

Abstract: An image processing system configured to obtain a mesh representation of a scene, wherein the mesh representation comprises a plurality of polygons defined by respective vertices associated with an in-plane position, the in-plane position being in a plane comprising a first dimension and a second dimension, and the vertices having an associated vertex depth value in a third dimension different from the first dimension and the second dimension. The image processing system comprises an in-plane position estimation network configured to process image data representative of an image of the scene to estimate the in-plane positions associated with respective vertices of the mesh representation. The image processing system further comprises a depth estimation engine configured to process the in-plane positions and the image data to estimate the associated vertex depth values for the respective vertices of the mesh representation.

Abstract: A computer-implemented method of determining the location of a mobile device comprising a camera and at least one inertial sensor. A sequence of images are captured over a period of time, and a first neural network determines features indicative of the motion of the device from pairs of consecutive images. Data indicative of the motion of the device is captured, and a second neural network determines features indicative of the motion of the device from the data. A third neural network then determines features indicative of the location of the device from the features determined by the first neural network and the second neural network. The location of the device is the determined from the features determined by the third neural network.

Abstract: A computer-implemented method of determining the location of a mobile device comprising a camera and at least one inertial sensor. A sequence of images are captured over a period of time, and a first neural network determines features indicative of the motion of the device from pairs of consecutive images. Data indicative of the motion of the device is captured, and a second neural network determines features indicative of the motion of the device from the data. A third neural network then determines features indicative of the location of the device from the features determined by the first neural network and the second neural network. The location of the device is the determined from the features determined by the third neural network.

Abstract: Examples are described that process image data to predict a thickness of objects present within the image data. In one example, image data for a scene is obtained, the scene featuring a set of objects. The image data is decomposed to generate input data for a predictive model. This may include determining portions of the image data that correspond to the set of objects in the scene, where each portion corresponding to a different object. Cross-sectional thickness measurements are predicted for the portions using the predictive model. The predicted cross-sectional thickness measurements for the portions of the image data are then composed to generate output image data comprising thickness data for the set of objects in the scene.

Abstract: A computer-implemented method of determining the location of a mobile device comprising a camera. The method comprises the steps of capturing, using the camera, a sequence of images over a period of time; for pairs of consecutive images from the sequence of images, determining, using a first neural network, features indicative of the motion of the device between the time the first image of the pair of images was captured and the time the second image of the pair of images was captured; for a sequence of consecutive images, determining, using a second neural network, features indicative of the location of the device from the features determined by the first neural network; and for a sequence of consecutive images, determining the location of the device from the features determined by the second neural network.

Abstract: A method comprising applying an object recognition pipeline to frames of video data. The object recognition pipeline provides a mask output of objects detected in the frames. The method includes fusing the mask output of the object recognition pipeline with depth data associated with the frames of video data to generate a map of object instances, including projecting the mask output to a model space for the map of object instances using a camera pose estimate and the depth data. An object instance in the map of object instances is defined using surface-distance metric values within a three-dimensional object volume, and has an object pose estimate indicating a transformation of the object instance to the model space. The object pose estimate and the camera pose estimate form nodes of a pose graph for the map of model instances.

Abstract: A computer-implemented method of determining a location of a mobile device, the method comprising receiving inertial data generated at the mobile device, the inertial data comprising a plurality of samples taken at different times, segmenting the inertial data into pseudo-independent windows, wherein each pseudo-independent window comprises a plurality of the samples and wherein one or more initial states for each pseudo-independent window are treated as unknown, estimating a change in navigation state over each pseudo-independent window using the samples of inertial data, and summing the changes in the navigation states over the pseudo-independent windows so as to determine the location of the mobile device.

Abstract: A set of ordered playing cards includes indicia of preceding and following cards. The indicia are on the face of each cards and preferably along the side and orientated corresponding to the card designation commonly on the top left and bottom right corner of each card. The first card in the ordered set references the last card as the preceding card, and the last card in the deck references the first card as the following card.

Abstract: A clamshell food tray. In some embodiments, the clamshell food tray can comprise a window such that a viewer can see into the interior of the clamshell food tray when the clamshell food tray is in a closed configuration. In some embodiments, the clamshell food tray can have apertures configured to accept a beverage container.

Abstract: A clamshell-style food container having a beverage holder that can also act as a closure mechanism for securing the container in a closed configuration. In some embodiments, the food container also has multiple compartments for separating food items.

Abstract: A novel production process is disclosed for the conversion of methane or natural gas, particularly shale gas, into a liquid fuel near the point of origin. The process is notably “non-Fischer-Tropsch” meaning that it does not require oxygen to be admitted into the reactor for supplying thermal energy by partial combustion, which is normally required to split methane. This freedom from high temperature operation and the other demands of an oxygenation process means that higher carbon efficiency is achievable This is made possible with mechanochemistry and “sonic catalysis” that employ kinetic energy to promote the breakdown of methane molecules, the reformation of the resulting carbon-hydrogen fragments, and the rejuvenation of the catalyst surface. A number of liquid fuels can be produced which are easily transported and fully marketable without further processing.

Abstract: A clamshell food tray. In some embodiments, the clamshell food tray can comprise a window such that a viewer can see into the interior of the clamshell food tray when the clamshell food tray is in a closed configuration. In some embodiments, the clamshell food tray can have apertures configured to accept a beverage container.

Abstract: An injector assembly for delivering flowable material to a medical implant, including a tube having a first end and a second end, a connector member and a port connector, where the connector member is coupled to the first end of the tube and the port connector is coupled to the second end of the tube, the connector member being configured to attach to a material delivery mechanism and the port connector being configured to attach to the medical implant. When the material delivery mechanism is actuated, the flowable material passes through the tube to the medical implant. A method of using an injector assembly to deliver a flowable material to a medical implant and bone surface is also described. A kit containing various sized parts for an injector assembly is also described.