公开(公告)号：US20240169748A1

公开(公告)日：2024-05-23

申请号：US18391820

申请日：2023-12-21

Applicant: CARNEGIE MELLON UNIVERSITY

Inventor： JONATHAN CAGAN ,  PHILIP LeDUC ,  DANIEL CLYMER

IPC: G06V20/69 ,  G06F18/10 ,  G06F18/2135 ,  G06F18/214 ,  G06F18/241 ,  G06F18/2415 ,  G06T7/00

CPC classification number: G06V20/69 ,  G06F18/10 ,  G06F18/2135 ,  G06F18/2148 ,  G06F18/241 ,  G06F18/2415 ,  G06T7/0012 ,  G06V20/695 ,  G06V20/698 ,  G06T2207/10056 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/30101 ,  G06V40/14 ,  G06V2201/031

Abstract: A hierarchical deep-learning object detection framework provides a method for identifying objects of interest in high-resolution, high pixel count images, wherein the objects of interest comprise a relatively a small pixel count when compared to the overall image. The method uses first deep-learning model to analyze the high pixel count images, in whole or as a patchwork, at a lower resolution to identify objects, and a second deep-learning model to analyze the objects at a higher resolution to classify the objects.