Jonathan T Chen

US Patent:

20200058158, Feb 20, 2020

Filed:

Aug 9, 2019

Appl. No.:

16/536869

Inventors:

- San Francisco CA, US
Jonathan Chen - San Francisco CA, US
Vladimir Lyapunov - Erie CO, US
Lionel Gueguen - Erie CO, US
Noah Goodman - Menlo Park CA, US
Benjamin James Kadlec - Boulder CO, US
Douglas Bemis - San Francisco CA, US

International Classification:

G06T 15/20
G06T 7/70
G06T 17/05
G01C 21/32

Abstract:

Example systems and methods improve a location detection process. A system accesses image data and image metadata, whereby the image data captures images of a plurality of objects from different views, each image having corresponding image metadata. The system then detects each object in the plurality of objects in the image data. A plurality of rays in three-dimensional space is generated, whereby each ray of the plurality of rays is generated based on the detected objects and the corresponding image metadata. The system predicts object locations using the generated rays based on a probabilistic triangulation of the rays. The networked system updates map data using the predicted object locations. The updating includes adding objects at their predicted object locations to the map data. The map data is used to generate a map.

US Patent:

20190166404, May 30, 2019

Filed:

Nov 30, 2017

Appl. No.:

15/828250

Inventors:

- Menlo Park CA, US
Russell Aaron Phillips - San Francisco CA, US
Heping Gao - Issaquah WA, US
Jonathan E. Chen - Seattle WA, US
Abhishek Bapna - Mountain View CA, US

International Classification:

H04N 21/472
G06Q 50/00
G06F 17/30
G06Q 30/02
H04N 21/234
H04L 29/08

Abstract:

In one embodiment, a method includes a computer server machine receiving a request from a first user to interact with a multimedia content. The computer server machine then associates the first user with a control group, wherein the control group comprises a first set of users interacting with the multimedia content. When the first user is associated with the control group, the computer server machine then applies a first content insertion model to the multimedia content and records a first set of metrics based on the interaction of the first user with the multimedia content.