Trimble Inc.

Robert Banfield

Michael Aziz Tadros

Wei Wang

Aristodimos Komninos

Vishakaraj Shanmugavel

Karoliina Torttila

Michael Tadros

Jim Coleman

James Coleman

Karolina Torttila

Ross Stump

Matthew Compton

Jacques Harvent

One or more three-dimensional models that corresponds to at least one two-dimensional image are determined by receiving image data that corresponds to the at least one two-dimensional image, generating features based on the image data corresponding to the at least one two-dimensional image, generating a representation vector for the at least one two-dimensional image by transforming the features into a predetermined amount of numerical representations corresponding to the features, and outputting the representation vector for the at least one two-dimensional image to facilitate a search query for the one or more three-dimensional models associated with the at least one two-dimensional image.

Determining 3D models corresponding to an image

Techniques for orchestrating activities at an earthmoving site are described. In an example, a stream of images are captured by an image capturing device removably fixed to a mobile earthmoving machine with a field of view overlapping with a working range of an attachment coupled to the mobile earthmoving machine. Using a selected subset of images from the stream captured during a time period, a first trained algorithm generates a probability that the subset of images depicts an action performable by the machine. Based on the probability, it is determined that the machine was performing the action during the time period, and in response, an image from the subset of images is selected. The image and an indication that the machine was performing the action during the time period are transmitted to a remote server system through a network.

Construction site orchestration using dynamic computer vision

A user computing device displays a three-dimensional virtual space via a user interface. The user computing device detects a gesture input at a location of the user interface. The user computing device translates the gesture input into a user interface input by predicting, based on the gesture input, a design intended by the gesture input and mapping, based on the design and the location of the gesture input on the user interface, the design to the user interface to generate the user interface input. The user computing device executes, in response to the user interface input, an operation to add an object in the three dimensional virtual space. The user computing device renders an updated three dimensional space displaying the object.

Interpreting inputs for three-dimensional virtual spaces from touchscreen interface gestures to improve user interface functionality

Embodiments describe a method for capturing objects in action at an earthmoving site. The method includes capturing an image of a region of the earthmoving site including an object, the image being recorded as captured digital data; identifying a classification of the object using a trained algorithm existing in memory of the image capturing device; sending the classification of the object to a remote server through a network; determining a pixel location and a boundary of the object within a field of view of the image capturing device based on positions of pixels of the object in the image; sending a set of images including the image to the remote server; determining an activity being performed by the object based on an analysis of digital data associated with the classification of the object and the movement of the object at the earthmoving site; and outputting a report to a user.

Construction site productivity capture using computer vision

Growing community of inventors

Riverview, FL, United States of America

Robert Banfield