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.

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.

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.

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.

Abstract: A movement detection circuit, a motion estimation circuit and associated movement detection method are provided. The movement detection circuit includes a candidate searching module including a first-frame and a second-frame candidate circuits, an object selection module including a first selection circuit, a second selection circuit, and a motion vector calculation circuit. The first-frame and the second-frame candidate circuits respectively locate a first and a second first-frame candidate positions in the first frame and locates a first and a second second-frame candidate positions in the second frame. The first-frame object selection circuit identifies one of the first and the second first-frame candidate positions as a first-frame object position, and the second-frame object selection circuit identifies one of the first and the second second-frame candidate positions as a second-frame object position.

Abstract: A movement detection circuit, a motion estimation circuit and associated movement detection method are provided. The movement detection circuit includes a candidate searching module including a first-frame and a second-frame candidate circuits, an object selection module including a first selection circuit, a second selection circuit, and a motion vector calculation circuit. The first-frame and the second-frame candidate circuits respectively locate a first and a second first-frame candidate positions in the first frame and locates a first and a second second-frame candidate positions in the second frame. The first-frame object selection circuit identifies one of the first and the second first-frame candidate positions as a first-frame object position, and the second-frame object selection circuit identifies one of the first and the second second-frame candidate positions as a second-frame object position.