US 12,450,762 B2
Passive range finder and associated method
Donovan Lee Alexander, Fayetteville, NC (US); James Andrew Harding, Haslingden (GB); and Ryan Ellis Pargeter, Llanfyllin (GB)
Assigned to QIOPTIQ LIMITED, St. Asaph (GB)
Filed by Qioptiq Limited, St. Asaph (GB)
Filed on Oct. 26, 2022, as Appl. No. 17/973,853.
Claims priority of provisional application 63/272,254, filed on Oct. 27, 2021.
Prior Publication US 2023/0360238 A1, Nov. 9, 2023
Int. Cl. G06K 9/00 (2022.01); G06T 7/12 (2017.01); G06T 7/50 (2017.01); G06T 7/73 (2017.01)
CPC G06T 7/50 (2017.01) [G06T 7/12 (2017.01); G06T 7/73 (2017.01); G06T 2207/10028 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A passive system for determining a range to a target, the system comprising: a sensor array configured to generate image data; and a processing unit configured to: generate, using an artificial intelligence (AI) model, a set of coordinates by identifying a subset of the image data as comprising information corresponding to at least a portion of the target; generate dimension information representing a dimension corresponding to the at least a portion of the target based on the set of coordinates; obtain reference dimension information corresponding to the at least a portion of the target; and generate range information representing the range to the target using the dimension information and the reference dimension information,
wherein the image data comprises a data set representing an incomplete portion of the target, wherein the AI model comprises a pose estimation module, wherein the pose estimation module is configured to generate the set of coordinates by: identifying coordinates of the image data corresponding to joint keypoints of the target;
wherein generating dimension information comprises: identifying a limb of the target using the coordinates of the image data corresponding to the joint keypoints; and identifying a dimension of the limb; and
wherein obtaining the reference dimension information comprises obtaining limb dimension information corresponding to the limb of a target having limbs of average dimensions.