17745920. VEHICLE POSE MANAGEMENT simplified abstract (Ford Global Technologies, LLC)

From WikiPatents
Jump to navigation Jump to search

VEHICLE POSE MANAGEMENT

Organization Name

Ford Global Technologies, LLC

Inventor(s)

Sushruth Nagesh of Mountain View CA (US)

Shubham Shrivastava of Santa Clara CA (US)

Punarjay Chakravarty of Campbell CA (US)

VEHICLE POSE MANAGEMENT - A simplified explanation of the abstract

This abstract first appeared for US patent application 17745920 titled 'VEHICLE POSE MANAGEMENT

Simplified Explanation

The abstract describes a computer system that receives image frames from cameras showing a vehicle and determines its position and orientation in each frame. The system initializes multiple possible poses for the vehicle and calculates the best pose by minimizing the difference between the observed and estimated pixel coordinates. The system then selects the pose with the lowest error.

  • The computer system includes a processor and memory.
  • It receives image frames from cameras showing a vehicle.
  • It determines the baseline pixel coordinate for the vehicle in each frame.
  • It initializes multiple possible poses for the vehicle in a preset pattern.
  • For each pose, it calculates the final pose by minimizing the difference between observed and estimated pixel coordinates.
  • The estimated pixel coordinates are obtained by reprojecting the vehicle onto the image frame.
  • The system selects the final pose with the lowest error.

Potential Applications

  • Autonomous vehicles: This technology can be used in self-driving cars to accurately determine the position and orientation of the vehicle in real-time.
  • Augmented reality: It can be applied in AR applications to precisely overlay virtual objects onto real-world scenes.
  • Robotics: The system can be used in robotic systems to accurately track the position and orientation of objects.

Problems Solved

  • Accurate pose estimation: The system solves the problem of accurately determining the position and orientation of a vehicle in image frames.
  • Reprojection error minimization: By minimizing the reprojection error, the system ensures that the estimated pose closely matches the observed pose.

Benefits

  • Improved accuracy: The system provides more accurate pose estimation by considering multiple possible poses and minimizing the reprojection error.
  • Real-time tracking: The technology enables real-time tracking of the vehicle's position and orientation.
  • Versatile applications: The system can be applied in various fields such as autonomous vehicles, augmented reality, and robotics.


Original Abstract Submitted

A computer includes a processor and a memory, and the memory stores instructions executable by the processor to receive at least one image frame from at least one camera, the at least one image frame showing a vehicle; determine at least one baseline pixel coordinate within one image frame for the vehicle; initialize a plurality of initial poses for the vehicle in a preset pattern; for each initial pose, determine a respective final pose by minimizing a reprojection error between the at least one baseline pixel coordinate and at least one respective estimated pixel coordinate, the at least one respective estimated pixel coordinate resulting from reprojecting the vehicle to pixel coordinates in the one image frame; and select a first final pose from the final poses, the first final pose having the lowest minimized reprojection error of the final poses.

Retrieved from "http://wikipatents.org/index.php?title=17745920._VEHICLE_POSE_MANAGEMENT_simplified_abstract_(Ford_Global_Technologies,_LLC)&oldid=18974"