Adam T Geitgey

US Patent:

20200082167, Mar 12, 2020

Filed:

Sep 7, 2018

Appl. No.:

16/125136

Inventors:

Ben Shalom - San Diego CA, US
Adam Todd Geitgey - San Diego CA, US

International Classification:

G06K 9/00
G06N 3/08
G06N 5/04
G06T 7/73

Abstract:

A system and process for trash-can management. The process uses digital images to extract trash-cans from the images and a classifier to determine the trash-cans state. The process can include responses to trash-cans that need servicing. A neural network machine learning algorithm is used to identify trash-cans in the image. Neural networks classifiers are used to classify the state of the identified a trash-cans. The neural networks are trained with images containing trash-cans and the surrounding area that have trash and do not have trash to determine a binary state. Trash-cans identified with a low-confidence level can be used to retrain the neural networks. The process can include the management of the trash-can by generating report, maps, notifications, collection routes, or assigning workers.

US Patent:

20190278834, Sep 12, 2019

Filed:

Feb 8, 2019

Appl. No.:

16/270722

Inventors:

- Chicago IL, US
Adam Geitgey - Mountain View CA, US

International Classification:

G06F 17/22
G06F 16/958
G06Q 30/02
G06Q 30/06

Abstract:

A system and related devices and methods facilitating orchestration of page composition based on performance of one or more portions of the page are disclosed herein. An exemplary system may comprise a first device and a second device. An exemplary method may comprise providing to a client device, a first portion of a requested page while waiting for one or more service calls required to render a second portion to return, and after a time at which the one or more service calls required to render the second portion return, providing the client device with the second portion, the one or more service calls required to render the second portion having a higher latency than any service calls required to render the first portion.