US 12,470,683 B1
Flow-guided online stereo rectification
Felix Heide, New York City, NY (US); Anush Kumar, Austin, TX (US); Shile Li, Munich (DE); Omid Hosseini Jafari, Munich (DE); and Fahim Mannan, Toronto (CA)
Assigned to Torc Robotics, Inc., Blacksburg, VA (US)
Filed by Torc Robotics, Inc., Blacksburg, VA (US)
Filed on Aug. 28, 2024, as Appl. No. 18/817,540.
Claims priority of provisional application 63/667,026, filed on Jul. 2, 2024.
Int. Cl. H04N 13/246 (2018.01); G06V 10/44 (2022.01); G06V 10/74 (2022.01); G06V 10/771 (2022.01); H04N 13/239 (2018.01)
CPC H04N 13/246 (2018.05) [G06V 10/44 (2022.01); G06V 10/761 (2022.01); G06V 10/771 (2022.01); H04N 13/239 (2018.05)] 20 Claims
OG exemplary drawing
 
1. An autonomous vehicle comprising:
a stereo camera pair disposed on the autonomous vehicle, the stereo camera pair comprising a first camera and a second camera separated by a baseline distance, the first camera and the second camera configured to capture a first image and a second image, respectively;
at least one memory device storing computer executable instructions; and
at least one processor coupled to the at least one memory device and the stereo camera pair, the least one processor, upon execution of the computer executable instructions, configured to:
receive the first image and the second image captured using respective cameras in the stereo camera pair;
predict, using a neural network model, a rotation matrix between the first image and the second image by:
extracting a first feature map and a second feature map based on the first image and the second image;
applying positional feature enhancement on the first feature map and the second feature map to derive a first enhanced feature map and a second enhanced feature map;
computing a correlation volume across the first enhanced feature map and the second enhanced feature map;
determining a set of likely matches between the first enhanced feature map and the second enhanced feature map based on the correlation volume;
computing a predicted relative pose based on the set of likely matches; and
computing the rotation matrix based on the predicted relative pose; and
calibrate the stereo camera pair by:
employing differentiable rectification to rectify the first image and the second image based on the rotation matrix.