Abstract: A method of registering distributed devices includes discovering a plurality of devices at a central panel or server, localizing the devices, and authorizing the devices with a mobile device communicating with the central panel or server. The method also includes registering the devices with the central panel. The model can include verifying link quality with each of the devices before registering the devices with the central panel by comparing signal quality between each device and a central panel with a pre-defined threshold level.

Abstract: A method for searching video includes receiving a video query, the video query including a first video query term identifying a first foreground object, a second video query term identifying a second foreground object, and a third video query term identifying a spatiotemporal relationship; searching the video in response to the video query for the first foreground object and the second foreground object within the spatiotemporal relationship; and generating a search result in response to the searching.

Abstract: A method of registering distributed devices includes discovering a plurality of devices at a central panel or server, localizing the devices, and authorizing the devices with a mobile device communicating with the central panel or server. The method also includes registering the devices with the central panel. The model can include verifying link quality with each of the devices before registering the devices with the central panel by comparing signal quality between each device and a central panel with a pre-defined threshold level.

Abstract: A method for searching video includes receiving a video query, the video query including a first video query term identifying a first foreground object, a second video query term identifying a second foreground object, and a third video query term identifying a spatiotemporal relationship; searching the video in response to the video query for the first foreground object and the second foreground object within the spatiotemporal relationship; and generating a search result in response to the searching.

Abstract: A method of registering distributed devices includes discovering a plurality of devices at a central panel or server, localizing the devices, and authorizing the devices with a mobile device communicating with the central panel or server. The method also includes registering the devices with the central panel. The model can include verifying link quality with each of the devices before registering the devices with the central panel by comparing signal quality between each device and a central panel with a pre-defined threshold level.

Abstract: A method for capturing building information includes capturing dimensions of a 360 degree image at a first location within a room of a building using a mobile device equipped with at least direction sensor and at least one motion sensor. The step of capturing dimensions is repeated within at least one additional room. The mobile device receives user input to connect the rooms to create a floor plan of the building and align the floor plans over each other to create a multi-level building map.

Abstract: Systems, methods, computer program products, and apparatuses to transform a weight space of an inference model to increase the compute efficiency of a target inference platform. A density of a weight space can be determined, and a transformation parameter derived based on the determined density. The weight space can be re-ordered based on the transformation parameter to balance the compute load between the processing elements (PEs) of the target platform, and as such, reduce the idle time and/or stalls of the PEs.

Abstract: A method and apparatus to control access to at least one resource is provided, the method including identifying a location parameter of a mobile device via a locating system, verifying the location parameter with a location parameter database via an authentication processor, receiving a motion parameter of the mobile device via at least one motion sensor of the mobile device, verifying the motion parameter with a motion parameter data-base via the authentication processor, and selectively providing access to the at least one resource in response to the location parameter and the motion parameter via the authentication processor.

Abstract: A method for capturing building information includes capturing dimensions of a 360 degree image at a first location within a room of a building using a mobile device equipped with at least direction sensor and at least one motion sensor. The step of capturing dimensions is repeated within at least one additional room. The mobile device receives user input to connect the rooms to create a floor plan of the building and align the floor plans over each other to create a multi-level building map.

Abstract: A method of registering distributed devices includes discovering a plurality of devices at a central panel or server, localizing the devices, and authorizing the devices with a mobile device communicating with the central panel or server. The method also includes registering the devices with the central panel. The model can include verifying link quality with each of the devices before registering the devices with the central panel by comparing signal quality between each device and a central panel with a pre-defined threshold level.

Abstract: An improved method and a system are disclosed for recovering a three-dimensional (3D) scene structure from a plurality of two-dimensional (2D) image frames obtained from imaging means. Sets of 2D features are extracted from the image frames, and sets corresponding to successive image frames are matched, such that at least one pair of matched 2D features refers to a same 3D point in a 3D scene captured in 2D in the image frames. A 3D ray is generated by back-projection from each 2D feature, and the generated 3D rays are subjected to an anchor-based minimization process, for determining camera motion parameters and 3D scene points coordinates, thereby recovering a structure of the 3D scene.

Abstract: An improved method and a system are disclosed for recovering a three-dimensional (3D) scene structure from a plurality of two-dimensional (2D) image frames obtained from imaging means. Sets of 2D features are extracted from the image frames, and sets corresponding to successive image frames are matched, such that at least one pair of matched 2D features refers to a same 3D point in a 3D scene captured in 2D in the image frames. A 3D ray is generated by back-projection from each 2D feature, and the generated 3D rays are subjected to an anchor-based minimization process, for determining camera motion parameters and 3D scene points coordinates, thereby recovering a structure of the 3D scene.