US 12,412,364 B2
Systems and methods for object recognition
Xiaodong Wang, Shanghai (CN); and Xiong Yang, Shanghai (CN)
Assigned to SHANGHAI UNITED IMAGING HEALTHCARE CO., LTD., Shanghai (CN)
Filed by SHANGHAI UNITED IMAGING HEALTHCARE CO., LTD., Shanghai (CN)
Filed on Oct. 24, 2022, as Appl. No. 18/049,283.
Application 18/049,283 is a continuation of application No. PCT/CN2020/137816, filed on Dec. 19, 2020.
Claims priority of application No. 202010333819.5 (CN), filed on Apr. 24, 2020; and application No. 202010518681.6 (CN), filed on Jun. 9, 2020.
Prior Publication US 2023/0074296 A1, Mar. 9, 2023
Int. Cl. G06V 10/44 (2022.01); G06V 10/75 (2022.01); G06V 10/82 (2022.01); G06V 40/14 (2022.01)
CPC G06V 10/454 (2022.01) [G06V 10/44 (2022.01); G06V 10/757 (2022.01); G06V 10/82 (2022.01); G06V 40/14 (2022.01); G06V 2201/031 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A system, comprising:
at least one storage device including a set of instructions; and
at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is directed to perform operations including:
obtaining image data captured by an imaging device, the image data including one or more objects;
determining a centerline of a target object in the one or more objects based on the image data, the target object including a tubular structure; and
determining a recognition result of the target object based on an output of a trained neural network model that takes at least one feature parameter of the centerline of the target object as input, the recognition result including at least one of a name of the target object or a label of the target object.