公开(公告)号：US20220215207A1

公开(公告)日：2022-07-07

申请号：US17701710

申请日：2022-03-23

Applicant: Novatek Microelectronics Corp.

Inventor： Jen-Huan Hu ,  Wei-Ting Chen ,  Yu-Che Hsiao ,  Shih-Hsiang Lin ,  Po-Chin Hu ,  Yu-Tsung Hu ,  Pei-Yin Chen

IPC: G06K9/62 ,  G06N3/04 ,  G06T3/40 ,  G06N3/08 ,  G06V20/40

Abstract: A training method for video stabilization and an image processing device using the same are proposed. The method includes the following steps. An input video including low dynamic range (LDR) images is received. The LDR images are converted to high dynamic range (HDR) images by using a first neural network. A feature extraction process is performed to obtain features based on the LDR images and the HDR images. A second neural network for video stabilization is trained according to the LDR images and the HDR images based on a loss function by minimizing a loss value of the loss function to generate stabilized HDR images in a time-dependent manner, where the loss value of the loss function depends upon the features. An HDR classifier is constructed according to the LDR images and the HDR images. The stabilized HDR images are classified by using the HDR classifier to generate a reward value, where the loss value of the loss function further depends upon the reward value.

公开(公告)号：US11790501B2

公开(公告)日：2023-10-17

申请号：US17701710

申请日：2022-03-23

Applicant: Novatek Microelectronics Corp.

Inventor： Jen-Huan Hu ,  Wei-Ting Chen ,  Yu-Che Hsiao ,  Shih-Hsiang Lin ,  Po-Chin Hu ,  Yu-Tsung Hu ,  Pei-Yin Chen

IPC: G06T7/80 ,  G06T7/70 ,  G06T5/00 ,  G06T3/40 ,  G06N3/08 ,  G06V20/40 ,  G06F18/214 ,  G06F18/22 ,  G06N3/045 ,  G06V10/82

CPC classification number: G06T5/009 ,  G06F18/214 ,  G06F18/22 ,  G06N3/045 ,  G06N3/08 ,  G06T3/4046 ,  G06V10/82 ,  G06V20/41 ,  G06V20/46

Abstract: A training method for video stabilization and an image processing device using the same are proposed. The method includes the following steps. An input video including low dynamic range (LDR) images is received. The LDR images are converted to high dynamic range (HDR) images by using a first neural network. A feature extraction process is performed to obtain features based on the LDR images and the HDR images. A second neural network for video stabilization is trained according to the LDR images and the HDR images based on a loss function by minimizing a loss value of the loss function to generate stabilized HDR images in a time-dependent manner, where the loss value of the loss function depends upon the features. An HDR classifier is constructed according to the LDR images and the HDR images. The stabilized HDR images are classified by using the HDR classifier to generate a reward value, where the loss value of the loss function further depends upon the reward value.

公开(公告)号：US11373060B2

公开(公告)日：2022-06-28

申请号：US16882692

申请日：2020-05-25

Applicant: Novatek Microelectronics Corp.

Inventor： Jen-Huan Hu ,  Wei-Ting Chen ,  Yu-Che Hsiao ,  Shih-Hsiang Lin ,  Po-Chin Hu ,  Yu-Tsung Hu ,  Pei-Yin Chen

IPC: G06K9/62 ,  G06N3/04 ,  G06T3/40 ,  G06N3/08 ,  G06V20/40

Abstract: A training method for video stabilization and an image processing device using the same are proposed. The method includes the following steps. An input video including low dynamic range (LDR) images is received. The LDR images are converted to high dynamic range (HDR) images by using a first neural network. A second neural network for video stabilization is trained to generate stabilized HDR images in a time-dependent manner.

公开(公告)号：US20210365729A1

公开(公告)日：2021-11-25

申请号：US16882692

申请日：2020-05-25

Applicant: Novatek Microelectronics Corp.

Inventor： Jen-Huan Hu ,  Wei-Ting Chen ,  Yu-Che Hsiao ,  Shih-Hsiang Lin ,  Po-Chin Hu ,  Yu-Tsung Hu ,  Pei-Yin Chen

IPC: G06K9/62 ,  G06K9/00 ,  G06T3/40 ,  G06N3/08 ,  G06N3/04

Abstract: A training method for video stabilization and an image processing device using the same are proposed. The method includes the following steps. An input video including low dynamic range (LDR) images is received. The LDR images are converted to high dynamic range (HDR) images by using a first neural network. A second neural network for video stabilization is trained to generate stabilized HDR images in a time-dependent manner.