公开(公告)号：US20220230425A1

公开(公告)日：2022-07-21

申请号：US17613767

申请日：2020-05-22

Applicant: Google LLC

Inventor： Adam Roman Kosiorek ,  Geoffrey E. Hinton ,  Sara Sabour Rouh Aghdam ,  Yee Whye Teh

IPC: G06V10/82 ,  G06V10/40 ,  G06T7/70

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting objects in images. One of the methods includes obtaining an input image; processing the input image to generate predicted part feature data, the predicted part feature data comprising, for each of a plurality of possible object parts: a part presence probability representing a likelihood that the possible object part is depicted in the input image, a predicted pose of the possible object part in the input image given that the possible object part is depicted in the input image, and an object part feature vector characterizing the depiction of the possible object part given that the possible object part is depicted in the input image; and processing the predicted part feature data for the plurality of possible object parts to generate an object detection output that identifies one or more objects depicted in the input image.

公开(公告)号：US12067758B2

公开(公告)日：2024-08-20

申请号：US17613767

申请日：2020-05-22

Applicant: Google LLC

Inventor： Adam Roman Kosiorek ,  Geoffrey E. Hinton ,  Sara Sabour Rouh Aghdam ,  Yee Whye Teh

IPC: G06V10/44 ,  G06T7/70 ,  G06V10/82

CPC classification number: G06V10/44 ,  G06T7/70 ,  G06V10/82 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting objects in images. One of the methods includes obtaining an input image; processing the input image to generate predicted part feature data, the predicted part feature data comprising, for each of a plurality of possible object parts: a part presence probability representing a likelihood that the possible object part is depicted in the input image, a predicted pose of the possible object part in the input image given that the possible object part is depicted in the input image, and an object part feature vector characterizing the depiction of the possible object part given that the possible object part is depicted in the input image; and processing the predicted part feature data for the plurality of possible object parts to generate an object detection output that identifies one or more objects depicted in the input image.