Amazon Technologies, Inc.

James Eather

Jon Robert Ducrou

Michael John Neville

Lev Zelenskiy

Ryan David Hapgood

Alexander Edwards

Sheng-Wei Lin

Uladzimir Silchanka

Vaibhav Gupta

Techniques are disclosed. The techniques include receiving, from a camera, an image showing a portion of a physical topography and target object. The techniques include determining, based on the image, a location of the target object shown in the image and a physical characteristic of the target object shown in the image, the physical characteristic being common with at least another target object. The techniques then include determining a three dimensional (3D) position of the target object in a 3D representation of the portion of the physical topography, the 3D position determined based on (i) the location of the target object, and (ii) the physical characteristic. Based on detecting a cluster of 3D positions of target objects (over several images), the techniques involve generating a 3D boundary of a zone of a portion of the physical topography.

Self-learning three-dimensional boundaries from images

Upon receiving an indication that a customer is initiating travel to a merchant location to pick up one or more items, sensor data may be obtained by, and received from, a customer device of the customer. After the customer has arrived at the merchant location, the customer may be greeted or otherwise interacted with and a corresponding interaction time may be determined. The service provider may identify one or more stop events based on the sensor data, where a stop event indicates that a customer stopped while in transit to the merchant location. A most recent stop event prior to the interaction time may constitute the customer arriving/stopping at the merchant location, and a corresponding arrival time may be estimated. A wait time of the customer may be determined based on a difference between the interaction time and the arrival time.

Sensor-based customer arrival detection

A system and method are disclosed, in which two or more points of a target object from a two-dimensional (2D) image may be 'reverse projected' from a 2D plane to a 3D space. The method may comprise receiving a 2D image from a 2D camera, the 2D image including a representation of a physical topography and a target object of a plurality of target objects, the plurality of target objects being associated with a common physical characteristic, the common physical characteristic of the target object being detectable within the 2D image. The method may further comprise determining a position relative to the physical topography of the target object based upon a position of the target object in the image and the common physical characteristic of the target object.

Identifying parking location using single camera reverse projection

Growing community of inventors

Kelvin Grove, Australia

James Eather