US 11,769,257 B2
Systems and methods for image aided navigation
Benjamin Lee Johnson, Brooklyn Park, MN (US); Vibhor L Bageshwar, Minneapolis, MN (US); and Srivatsan Varadarajan, St. Louis Park, MN (US)
Assigned to Honeywell International Inc., Charlotte, NC (US)
Filed by Honeywell International Inc., Morris Plains, NJ (US)
Filed on May 30, 2019, as Appl. No. 16/426,733.
Prior Publication US 2023/0230256 A1, Jul. 20, 2023
Int. Cl. G06T 7/246 (2017.01); G06T 7/20 (2017.01)
CPC G06T 7/246 (2017.01) [G06T 7/20 (2013.01); G06T 2207/30244 (2013.01); G06T 2207/30252 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A vision aided navigation system, the system comprising:
at least one image sensor, wherein the at least one image sensor is configured to produce a plurality of image frames of a surrounding environment;
a feature extractor coupled to the at least one image sensor, wherein the feature extractor is configured to extract at least one image feature from a first image frame from the plurality of image frames captured by the at least one image sensor;
a navigation filter configured to output a navigation solution based on an input of navigation data from at least one navigation device and further based on changes in position of the at least one image feature in the plurality of images;
a feature tracker configured to receive the plurality of image frames and configured to predict a location of the at least one image feature in at least one subsequent image frame taken by the at least one image sensor; and
a dynamic localized parameter adjuster configured to adjust at least one image parameter of the at least one subsequent image frame;
wherein a feature track is associated with the at least one image feature, wherein the feature track comprises a location of the at least one image feature in each of the plurality of images, and wherein the feature track is stored in the memory;
wherein the feature tracker is configured so that when the at least one image feature cannot be identified in the at least one subsequent image frame within a bounded region around the predicted location, the dynamic localized parameter adjuster adjusts the at least one image parameter within the bounded region ;
wherein when the at least one image feature cannot be identified in the subsequent image after the dynamic localized parameter adjuster adjusts the at least one image parameter, then the feature track of the at least one image feature is deleted from the memory, and at least one new image feature is extracted to replace the at least one image feature.