Uber Technologies, Inc.

Percipient.ai Inc.

Timo Pekka Pylvaenaeinen

Vasudev Parameswaran

Jerome Berclaz

Blaise Aguera Y Arcas

Mohammed Waleed Kadous

Sudipta Narayan Sinha

Donald Allen Barnett

Eric Joel Stollnitz

Vijay Mahadevan

Johannes P Kopf

Aditya Sarawgi

Markus Unger

Christopher Stephen Messer

Thommen Korah

Balan Rama Ayyar

Ivan Kovtun

Rajendra Jayantilal Shah

Reechik Chatterjee

Nikhil Kumar Gupta

Anantha Krishnan Bangalore

Myra Nam

Johannes Peter Kopf

Donald A Barnett

This description describes a system for identifying individuals within a digital file. The system accesses a digital file describing the movement of unidentified individuals and detects a face for an unidentified individual at a plurality of locations in the video. The system divides the digital file into a set of segments and detects a face of an unidentified individual by applying a detection algorithm to each segment. For each detected face, the system applies a recognition algorithm to extract feature vectors representative of the identity of the detected faces which are stored in computer memory. The system applies a recognition algorithm to query the extracted feature vectors for target individuals by matching unidentified individuals to target individuals, determining a confidence level describing the likelihood that the match is correct, and generating a report to be presented to a user of the system.

Identification of individuals in a digital file using media analysis techniques

A system trains and applies a machine learning model to label maps of a region. Various data modalities are combined as inputs for multiple data tiles used to characterize a region for a geographical map. Each data modality reflects sensor data captured in different ways. Some data modalities include aerial imagery, point cloud data, and location trace data. The different data modalities are captured independently and then aggregated using machine learning models to determine map labeling information about tiles in the region. Data is ingested by the system and corresponding tiles are identified. A tile is represented by a feature vector of different data types related to the various data modalities, and values from the ingested data are added to the feature vector for the tile. Models can be trained to predict characteristics of a region using these various types of input.

Determining geographical map features with multi-sensor input

Architecture that summarizes a large amount (e.g., thousands of miles) of street-level image/video data of different perspectives and types (e.g., continuous scan-type data and panorama-type data) into a single view that resembles aerial imagery. Polygons surfaces are generated from the scan patterns and the image data is projected onto the surfaces, and then rendered into the desired orthographic projection. The street-level data is processed using a distributed computing approach across cluster nodes. The collection is processed into image tiles on the separate cluster nodes representing an orthographic map projection that can be viewed at various levels of detail. Map features such as lower-level roads, that are at lower elevations than higher-level roads, and are hidden by higher-level overpassing roads, can be navigated in the map. With the summarized data, the maps can be navigated and zoomed efficiently.

Map-like summary visualization of street-level distance data and panorama data

Among other things, one or more techniques and/or systems are provided for defining transition zones for navigating a visualization. The visualization may be constructed from geometry of a scene and one or more texture images depicted the scene from various viewpoints. A transition zone may correspond to portions of the visualization that do not have a one-to-one correspondence with a single texture image, but are generated from textured geometry (e.g., a projection of texture imagery onto the geometry). Because a translated view may have visual error (e.g., a portion of the translated view is not correctly represented by the textured geometry), one or more transition zones, specifying translated view experiences (e.g., unrestricted view navigation, restricted view navigation, etc.), may be defined. For example, a snapback force may be applied when a current view corresponds to a transition zone having a relatively higher error.

Translated view navigation for visualizations

Growing community of inventors

Menlo Park, CA, United States of America

Timo Pekka Pylvaenaeinen