-
公开(公告)号：US11354887B2
公开(公告)日：2022-06-07
申请号：US16825222
申请日：2020-03-20
Inventor： Jiadong Zhang , Guoyi Liu , Chao Li
Abstract: A coin identification method and device, as well as a coin register are provided, which are related to a field of image identification. A specific implementation includes: extracting, from a to-be-identified image including coins, image blocks corresponding to the coins, to form an input coin set; inputting the input coin set into a coin classification model, to obtain categories and a classification confidences of the image blocks of the coins in the input coin set, wherein the category includes a face value of the coin; incorporating an image block, with a classification confidence reaching a threshold, of a coin of the input coin set into a first coin set; and determining a face value indicated by a category of the image block of the coin in the first coin set as a final face value of the coin in the first coin set.
-
公开(公告)号：US20220004812A1
公开(公告)日：2022-01-06
申请号：US17479147
申请日：2021-09-20
Inventor： Chao Li
Abstract: An image processing method, a method for training a pre-training model, and an electronic device are provided. An implementation solution is described as follows. A pre-training model is obtained after a training process based on a plurality of training images, in which image features output by the pre-training model satisfy that a first image feature distance and a second image feature distance have a minimum difference. Furthermore, according to the general pre-training model and a target image processing task, a corresponding image processing model is generated.
-
公开(公告)号：US20210385409A1
公开(公告)日：2021-12-09
申请号：US17406965
申请日：2021-08-19
Inventor： Chao Li
Abstract: A method and apparatus for video frame interpolation, and a device and a storage medium for the same are provided. The method may include: acquiring a target video, and acquiring a (t−1)th frame of image and a tth frame of image in the target video; acquiring motion level information of pixel points of the (t−1)th frame of image and the tth frame of image; acquiring deep frame interpolation features of the (t−1)th frame of image and the tth frame of image, respectively; and performing a frame interpolation operation layer by layer based on the deep frame interpolation features and the motion level information of the (t−1)th frame of image and the tth frame of image to generate an intermediate frame between the (t−1)th frame of image and the tth frame of image, and interpolating the intermediate frame between the (t−1)th frame of image and the tth frame of image.
-
4.发明授权公开(公告)号：US10861133B1
公开(公告)日：2020-12-08
申请号：US16810986
申请日：2020-03-06
Inventor： Chao Li , Dongliang He , Xiao Liu , Yukang Ding , Shilei Wen , Errui Ding , Henan Zhang , Hao Sun
IPC: G06T3/40
Abstract: A super-resolution video reconstruction method, device, apparatus and a computer-readable storage medium are provided. The method includes: extracting a hypergraph from consecutive frames of an original video; inputting a hypergraph vector of the hypergraph into a residual convolutional neural network to obtain an output result of the residual convolutional neural network; and inputting the output result of the residual convolutional neural network into a spatial upsampling network to obtain a super-resolution frame, wherein a super-resolution video of the original video is formed by multiple super-resolution frames.
-
公开(公告)号：US11627281B2
公开(公告)日：2023-04-11
申请号：US17406965
申请日：2021-08-19
Inventor： Chao Li
Abstract: A method and apparatus for video frame interpolation, and a device and a storage medium for the same are provided. The method may include: acquiring a target video, and acquiring a (t−1)th frame of image and a tth frame of image in the target video; acquiring motion level information of pixel points of the (t−1)th frame of image and the tth frame of image; acquiring deep frame interpolation features of the (t−1)th frame of image and the tth frame of image, respectively; and performing a frame interpolation operation layer by layer based on the deep frame interpolation features and the motion level information of the (t−1)th frame of image and the tth frame of image to generate an intermediate frame between the (t−1)th frame of image and the tth frame of image, and interpolating the intermediate frame between the (t−1)th frame of image and the tth frame of image.
-
Patent Agency Ranking
公开(公告)号：US11416967B2
公开(公告)日：2022-08-16
申请号：US17024253
申请日：2020-09-17
Inventor： Chao Li , Shilei Wen , Errui Ding
Abstract: Embodiments of the present disclosure provide a video processing method, a video processing device and a related non-transitory computer readable storage medium. The method includes the following. Frame sequence data of a low-resolution video to be converted is obtained. Pixel tensors of each frame in the frame sequence data are inputted into a pre-trained neural network model to obtain high-resolution video frame sequence data corresponding to the video to be converted output by the neural network model. The neural network model obtains the high-resolution video frame sequence data based on high-order pixel information of each frame in the frame sequence data.
-
公开(公告)号：US11363271B2
公开(公告)日：2022-06-14
申请号：US17125370
申请日：2020-12-17
Inventor： Chao Li , Yukang Ding , Dongliang He , Fu Li , Hao Sun , Shilei Wen , Hongwu Zhang , Errui Ding
IPC: H04N19/132 , H04N19/172 , G06K9/62 , G06N3/04
Abstract: A method for video frame interpolation, a related electronic device and a storage medium is disclosed. A video is obtained. An (i−1)th frame and an ith frame of the video are obtained. Visual semantic feature maps and depth maps of the (i−1)th frame and the ith frame are obtained. Frame interpolation information is obtained based on the visual semantic feature maps and the depth maps. An interpolated frame between the (i−1)th frame and the ith frame is generated based on the frame interpolation information and the (i−1)th frame and is inserted between the (i−1)th frame and the ith frame.
-
公开(公告)号：US11637986B2
公开(公告)日：2023-04-25
申请号：US17361055
申请日：2021-06-28
Inventor： Chao Li
Abstract: The disclosure provides a method and an apparatus for interpolating a frame to a video. A first deep-level feature of a first frame is obtained and a second deep-level feature of a second frame is obtained. Forward optical flow information and inverse optical flow information between the first frame and the second frame are obtained based on first deep-level feature and the second deep-level feature. An interpolated frame between the first frame and the second frame is generated based on the forward optical flow information and the inverse optical flow information, and the interpolated frame is inserted between the first frame and the second frame.
-
9.发明授权公开(公告)号：US11087741B2
公开(公告)日：2021-08-10
申请号：US16254309
申请日：2019-01-22
Inventor： Jianwei Sun , Chao Li , Xin Li , Weixin Zhu , Ming Wen
IPC: G10L15/06 , G10L21/0264 , G10L25/78 , G10L21/0216 , G10L15/20 , G10L15/16 , G10L25/51
Abstract: Embodiments of the present disclosure include methods, apparatuses, devices, and computer readable storage mediums for processing far-field environmental noise. The method can comprise processing collected far-field environmental noise to a noise segment in a predetermined format. The method can further comprise establishing a far-field voice recognition model based on the noise segment and a near-field voice segment; and determining validity of the noise segment based on the far-field voice recognition model. The solution of the present disclosure can optimize anti-noise performance of the far-field voice recognition model by differentiated training of noise in different user scenarios of a far-field voice recognition product.
-
公开(公告)号：US20210089810A1
公开(公告)日：2021-03-25
申请号：US16825222
申请日：2020-03-20
Inventor： Jiadong Zhang , Guoyi Liu , Chao Li
Abstract: A coin identification method and device, as well as a coin register are provided, which are related to a field of image identification. A specific implementation includes: extracting, from a to-be-identified image comprising coins, image blocks corresponding to the coins, to form an input coin set; inputting the input coin set into a coin classification model, to obtain categories and a classification confidences of the image blocks of the coins in the input coin set, wherein the category comprises a face value of the coin; incorporating an image block, with a classification confidence reaching a threshold, of a coin of the input coin set into a first coin set; and determining a face value indicated by a category of the image block of the coin in the first coin set as a final face value of the coin in the first coin set.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.018 seconds)
