US Patent Application 17955827. OBJECT TRACKING AND TIME-TO-COLLISION ESTIMATION FOR AUTONOMOUS SYSTEMS AND APPLICATIONS simplified abstract

From WikiPatents
Jump to navigation Jump to search

OBJECT TRACKING AND TIME-TO-COLLISION ESTIMATION FOR AUTONOMOUS SYSTEMS AND APPLICATIONS

Organization Name

NVIDIA Corporation

Inventor(s)

Mehmet K. Kocamaz of San Jose CA (US)

Parthiv Parikh of Santa Clara CA (US)

Sangmin Oh of San Jose CA (US)

OBJECT TRACKING AND TIME-TO-COLLISION ESTIMATION FOR AUTONOMOUS SYSTEMS AND APPLICATIONS - A simplified explanation of the abstract

This abstract first appeared for US patent application 17955827 titled 'OBJECT TRACKING AND TIME-TO-COLLISION ESTIMATION FOR AUTONOMOUS SYSTEMS AND APPLICATIONS

Simplified Explanation

- The patent application describes systems and methods for tracking objects and determining their time-to-collision values. - The systems and methods use feature points in images to determine changes and translations associated with the objects. - By analyzing the changes and translations, the systems and methods can identify and track the objects in multiple images. - The systems and methods also use a temporal baseline to calculate the time-to-collision for the objects. - The output of the systems and methods includes data such as object identifiers, object locations, and time-to-collision values.


Original Abstract Submitted

In various examples, systems and methods for tracking objects and determining time-to-collision values associated with the objects are described. For instance, the systems and methods may use feature points associated with an object depicted in a first image and feature points associated with a second image to determine a scalar change associated with the object. The systems and methods may then use the scalar change to determine a translation associated with the object. Using the scalar change and the translation, the systems and methods may determine that the object is also depicted in the second image. The systems and methods may further use the scalar change and a temporal baseline to determine a time-to-collision associated with the object. After performing the determinations, the systems and methods may output data representing at least an identifier for the object, a location of the object, and/or the time-to-collision.