Facebook, Inc.

Meta Platforms, Inc.

Andreas Gros

Yael Gregory Maguire

Karthik Yogeeswaran

Tobias Gerard Tiecke

Bogdan State

Aude Hofleitner

Amy Zhang

Andrew Todd Grier

Xianming Liu

Various embodiments of the present application set forth a computer-implemented method comprising aggregating positional signals that were received from device sensors, where each positional signal has an observed signal strength, identifying a subset of the positional signals, where each positional signal in the subset was received by a device sensor while the device sensor was located within the physical location, for each positional signal, generating, by an estimation device and based at least on a position of the device sensor, an approximate object height for an object located at the physical location, for each approximate object height, determining an expected signal strength for the positional signal corresponding to the approximate object height, generating a cost value that is based on a difference between the expected signal strength and the observed signal strength, and determining, by the estimation device and based on the cost values, an estimated object height.

GPS-based spatial measurements

Various of the disclosed embodiments relate to line-of-sight (LOS), e.g., optical, based networks. Systems and methods for determining where to place and how to configure nodes in an optically connected network across a geographic region are provided. Various factors concerning the region may be collected, including, e.g., building locations and height, building types, population densities, backbone connection locations, recurring weather factors, geographic elevation, etc. The algorithm may iteratively place nodes based upon the accessible range of a preceding contemplated node position.

Deploying line-of-sight communication networks

Various of the disclosed embodiments relate to line-of-sight (LOS), e.g., optical, based networks. Systems and methods for determining where to place and how to configure nodes in an optically connected network across a geographic region are provided. Various factors concerning the region may be collected, including, e.g.,: building locations and height, building types, population densities, backbone connection locations, recurring weather factors, geographic elevation, etc. The algorithm may iteratively place nodes based upon the accessible range of a preceding contemplated node position.

In one embodiment, a method includes receiving an image on a computing device. The computing device may further execute a weakly-supervised classification algorithm to determine whether a target feature is present in the received image. As an example, the weakly-supervised classification algorithm may determine whether a building is depicted in the received image. In response to determining that a target feature is present, the method further includes using a weakly-supervised segmentation algorithm of the convoluted neural network to segment the received image for the target feature. Based on a determined footprint size of the target feature, a distribution of statistical information over the target feature in the image can be calculated.

Determination of population density using convoluted neural networks

Systems, methods, and non-transitory computer-readable media can acquire shape data representative of one or more polygons. At least one serialization format can be produced based on the shape data. The at least one serialization format can be packaged into a proprietary package that is representative of the one or more polygons. At least a portion of the proprietary package can be utilized for one or more applications.

Growing community of inventors

Mountain View, CA, United States of America

Andreas Gros