公开(公告)号：US11354903B2

公开(公告)日：2022-06-07

申请号：US17059968

申请日：2018-12-18

Applicant: Intel Corporation

Inventor： Yan Hao ,  Zhi Yong Zhu ,  Lu Li ,  Ciyong Chen ,  Kun Yu

IPC: G06K9/00 ,  G06V20/40 ,  G06K9/62

Abstract: Techniques related to training and implementing a bidirectional pairing architecture for object detection are discussed. Such techniques include generating a first enhanced feature map for each frame of a video sequence by processing the frames in a first direction, generating a second enhanced feature map for frame by processing the frames in a second direction opposite the first, and determining object detection information for each frame using the first and second enhanced feature map for the frame.

公开(公告)号：US11948340B2

公开(公告)日：2024-04-02

申请号：US17255331

申请日：2018-09-07

Applicant: Intel Corporation

Inventor： Kun Yu ,  Ciyong Chen ,  Xiaotian Guo ,  Yan Hao ,  Hui Li ,  Lu Li ,  Jianguo Pei ,  Zhi Yong Zhu

IPC: G06V10/25 ,  G06F18/21 ,  G06F18/22 ,  G06N3/045 ,  G06V10/62 ,  G06V10/74 ,  G06V10/82 ,  G06V20/40 ,  G06V20/52

CPC classification number: G06V10/25 ,  G06F18/21 ,  G06F18/22 ,  G06N3/045 ,  G06V10/62 ,  G06V10/761 ,  G06V10/82 ,  G06V20/46 ,  G06V20/48 ,  G06V20/52

Abstract: An example apparatus for detecting objects in video frames includes a receiver to receive a plurality of video frames from a video camera. The apparatus also includes a first still image object detector to receive a first frame of the plurality of video frames and calculate localization information and confidence information for each potential object patch in the first frame. The apparatus further includes a second still image object detector to receive an adjacent frame of the plurality of video frames adjacent to the first frame and calculate localization information and confidence information for each potential object patch in the adjacent frame. The apparatus includes a similarity detector trained to detect paired patches between the first frame and the adjacent frame based on a comparison of the detected potential object patches. The apparatus further includes an enhancer to modify a prediction result for a paired patch in the adjacent frame to a prediction result of a corresponding paired patch in the first frame including a higher confidence score than the prediction result of the paired patch in the adjacent frame.

公开(公告)号：US11776263B2

公开(公告)日：2023-10-03

申请号：US17742122

申请日：2022-05-11

Applicant: Intel Corporation

Inventor： Yan Hao ,  Zhi Yong Zhu ,  Lu Li ,  Ciyong Chen ,  Kun Yu

IPC: G06K9/00 ,  G06V20/40 ,  G06F18/22 ,  G06F18/213 ,  G06V10/74 ,  G06V10/764 ,  G06V10/776 ,  G06V10/82

CPC classification number: G06V20/41 ,  G06F18/213 ,  G06F18/22 ,  G06V10/761 ,  G06V10/764 ,  G06V10/776 ,  G06V10/82 ,  G06V20/46

Abstract: Techniques related to training and implementing a bidirectional pairing architecture for object detection are discussed. Such techniques include generating a first enhanced feature map for each frame of a video sequence by processing the frames in a first direction, generating a second enhanced feature map for frame by processing the frames in a second direction opposite the first, and determining object detection information for each frame using the first and second enhanced feature map for the frame.

公开(公告)号：US11380086B2

公开(公告)日：2022-07-05

申请号：US16828987

申请日：2020-03-25

Applicant: Intel Corporation

Inventor： Kun Yu ,  Yan Hao ,  Lu Li ,  Zhiyong Zhu

IPC: G06V10/75 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06V10/22

Abstract: System and techniques are provided for three-dimension (3D) semantic segmentation. A device for 3D semantic segmentation includes: an interface, to obtain a point cloud data set for a time-ordered sequence of 3D frames, the 3D frames including a current 3D frame and one or more historical 3D frames previous to the current 3D frame; and processing circuitry, to: invoke a first artificial neural network (ANN) to estimate a 3D scene flow field for each of the one or more historical 3D frames by taking the current 3D frame as a reference frame; and invoke a second ANN to: produce an aggregated feature map, based on the reference frame and the estimated 3D scene flow field for each of the one or more historical 3D frames; and perform the 3D semantic segmentation based on the aggregated feature map.

公开(公告)号：US20210271923A1

公开(公告)日：2021-09-02

申请号：US17255331

申请日：2018-09-07

Applicant: Intel Corporation

Inventor： Kun Yu ,  Ciyong Chen ,  Xiaotian Guo ,  Yan Hao ,  Hui Li ,  Lu Li ,  Jianguo Pei ,  Zhi Yong Zhu

IPC: G06K9/62 ,  G06K9/32 ,  G06K9/00 ,  G06K9/46 ,  G06N3/04

Abstract: An example apparatus for detecting objects in video frames includes a receiver to receive a plurality of video frames from a video camera. The apparatus also includes a first still image object detector to receive a first frame of the plurality of video frames and calculate localization information and confidence information for each potential object patch in the first frame. The apparatus further includes a second still image object detector to receive an adjacent frame of the plurality of video frames adjacent to the first frame and calculate localization information and confidence information for each potential object patch in the adjacent frame. The apparatus includes a similarity detector trained to detect paired patches between the first frame and the adjacent frame based on a comparison of the detected potential object patches. The apparatus further includes an enhancer to modify a prediction result for a paired patch in the adjacent frame to a prediction result of a corresponding paired patch in the first frame including a higher confidence score than the prediction result of the paired patch in the adjacent frame.