METHOD FOR FAST CAMERA POSE REFINEMENT FOR WIDE AREA MOTION IMAGERY

Patent №

US 10,438,366

Granted

2019-10-08

Filed 2018

Owner

UNITED STATES AIR FORCE

+2 more

Lab

AI components

2

ml · vision

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

15885874

The present invention provides a method for fast, robust and efficient BA pipeline (SfM) for wide area motion imagery (WAMI). The invention can, without applying direct outliers filtering (e.g. RANSAC) or re-estimation of the camera parameters (e.g. essential matrix estimation) efficiently refine noisy camera parameters in very short amounts of time. The method is highly robust owing to its adaptivity with the persistency factor of each track. The present invention highly suitable for sequential aerial imagery, particularly for WAMI, where camera parameters are available from onboard sensors.

Machine learningVisionG06T 7/579G06T 7/73G06V 20/647G06T 2207/10016G06T 2207/30244

AI classification

Vision1.00
Machine learning1.00
AI hardware0.05
Knowledge representation0.03
Natural language0.01
Evolutionary computation0.00
Speech0.00
Planning0.00

Ownership

UNITED STATES AIR FORCE

assignment · 497150724

THE CURATORS OF THE UNIVERSITY OF MISSOURI

assignment · 497150915

THE DEPARTMENT OF THE AIR FORCE

assignment · 497160039

Assignors

AKABARPOUR, HADI ALI, PALANIAPPAN, KANNAPPAN

On an employer assignment, the assignors are typically the inventors.

From the same owner

© 2026 NYSGPT2525 LLC