Google Inc.

Deepmap Inc.

Apple Inc.

Xiaqing Wu

Mark Damon Wheeler

Lin Yang

Yang Liu

Rudolph Van Der Merwe

Emil Constantin Praun

Jaron Waldman

Jan Erik Solem

Samuel Noble

John Kassebaum

Wei Luo

An online system builds a high definition (HD) map for a geographical region based on sensor data captured by a plurality of autonomous vehicles driving through a geographical region. The autonomous vehicles detect map discrepancies based on differences in the surroundings observed using sensor data compared to the high definition map and send messages describing these map discrepancies to the online system. The online system updates existing occupancy maps to improve the accuracy of the occupancy maps (OMaps), and to thereby improve passenger and pedestrian safety. While vehicles are in motion, they can continuously collect data about their surroundings. When new data is available from the various vehicles within a fleet, this can be updated in a local representation of the occupancy map and can be passed to the online HD map system (e.g., in the cloud) for updating the master occupancy map shared by all of the vehicles.

Occupancy map updates based on sensor data collected by autonomous vehicles

An online system build a high definition map for geographical regions based on sensor data captured by a plurality of vehicles driving through the geographical regions. The high definition map comprises landmark map including representations of driving paths and landmarks and occupancy map comprising spatial 3D representation of the road and all physical objects around the road. The vehicles provide information to update the landmark map and the occupancy map to the online system. The vehicles detect map discrepancies based on differences in the surroundings observed using sensor data compared to the high definition map and send messages describing these map discrepancies to the online system. The online system ranks the vehicles based on factors including an upload rate of the vehicle and requests data describing high definition map from vehicles selected based on the ranking.

High definition map updates based on sensor data collected by autonomous vehicles

Embodiments determine the species of trees present in an aerial image. Tree crowns are detected in a received image, and represented as histograms of their color, texture and entropy features. Similar trees are clustered together. Using classification techniques, each cluster is assigned the closest species. The species information for each tree may be used in a rendering of the tree in geographical information systems.

Predicting tree species from aerial imagery

Methods and apparatus for a roof analysis tool for constructing a parameter set, where the parameter set is derived from mapping data for a map region, and where the parameter set describes the roofs for the buildings within the map region. In some cases, the parameter set includes a list of roof type identification values and the respective buildings in the map region for which a given roof type identification value corresponds. The roof analysis tool may operate on a server and work in conjunction with a mobile device, where the mobile device may display map views of a map region such that the map view is based on a three-dimensional model of the map region, and where a portion of the three-dimensional model is based on data generated on the mobile device and a portion of the three-dimensional model is based on data generated on the server.

Identifying and parameterizing roof types in map data

Systems and methods for modifying settings of mobile device are provided. Method includes determining first geographic location of mobile device. First geographic location is associated with first time. Method also includes determining second geographic location of mobile device. Second geographic location is associated with second time. The method also includes determining a speed of the mobile device based on the first geographic location, the first time, the second geographic location, and the second time. The method also includes associating at least the speed of the mobile device with a device profile. The device profile is a member of a set of device profiles stored within the mobile device. The method also includes adjusting at least one user-interface setting of the mobile device based on the device profile. The at least one user-interface setting is associated with an audio or visual user-interface element of the mobile device.

Mobile device profiling based on speed

The present invention relates to methods for aligning raster and vector data. In an embodiment, a raster/vector aligner receives raster data and an approximate vector of a feature within the raster data. The raster/vector aligner generates an edge signal by edge filtering the raster data along a direction of the approximate vector and a smoothness signal by smoothness filtering the raster data along a direction of the approximate vector. The raster/vector aligner combines the edge signal and the smoothness signal into a combined signal which is used to generate a translation vector or a signal weight for the feature within the raster data.

Method for automatic alignment of raster data with vector data in a geographic information system

Methods and systems for detecting trees in aerial imagery are provided. A method for detecting trees in aerial imagery may include training a pixel-level classifier to assign a tree or non-tree label to each pixel in an aerial image. The method may further include segmenting tree and non-tree regions of the labeled pixels. The method may also include locating individual tree crowns in the segmented tree regions using one or more tree templates. A system for detecting trees in aerial imagery may include a trainer, a segmenter and a tree locator.

Growing community of inventors

San Mateo, CA, United States of America

Xiaqing Wu