-
公开(公告)号：US20210357683A1
公开(公告)日：2021-11-18
申请号：US17338328
申请日：2021-06-03
Inventor： Xipeng YANG , Xiao TAN , Hao SUN , Hongwu ZHANG
Abstract: Embodiments of the present disclosure disclose a method and apparatus for determining a target anchor, a device and a storage medium. The method may include: extracting a plurality of feature maps of an original image using a feature extraction network; inputting the plurality of feature maps into a feature pyramid network to perform feature fusion, to obtain a plurality of fused feature maps; and using a region proposal network to implement operations as follows: determining an initial anchor of a web header using the fused feature map, based on a size of each fused feature map, and determining an offset parameter of the initial anchor, based on a ratio of the size of the fused feature map to the original image, and generating a plurality of candidate anchors in different directions, based on the offset parameter of the initial anchor.
-
2.发明申请公开(公告)号：US20210216782A1
公开(公告)日：2021-07-15
申请号：US17144205
申请日：2021-01-08
Inventor： Tianwei LIN , Xin LI , Dongliang HE , Fu LI , Hao SUN , Shilei WEN , Errui DING
Abstract: A method and apparatus for detecting a temporal action of a video, an electronic device and a storage medium are disclosed, which relates to the field of video processing technologies. An implementation includes: acquiring an initial temporal feature sequence of a video to be detected; acquiring, by a pre-trained video-temporal-action detecting module, implicit features and explicit features of a plurality of configured temporal anchor boxes based on the initial temporal feature sequence; and acquiring, by the video-temporal-action detecting module, the starting position and the ending position of a video clip containing a specified action, the category of the specified action and the probability that the specified action belongs to the category from the plural temporal anchor boxes according to the explicit features and the implicit features of the plural temporal anchor boxes.
-
公开(公告)号：US20210383120A1
公开(公告)日：2021-12-09
申请号：US17116578
申请日：2020-12-09
Inventor： Zhichao ZHOU , Dongliang HE , Fu LI , Hao SUN
Abstract: The present disclosure provides a method and apparatus for detecting a region of interest in a video, a device and a storage medium. The method may include: acquiring a current to-be-processed frame from a picture frame sequence of a video; detecting a region of interest (ROI) in the current to-be-processed frame, in response to determining that the current to-be-processed frame is a detection picture frame, to determine at least one ROI in the current to-be-processed frame; and updating a to-be-tracked ROI, based on the ROI in the current to-be-processed frame and a tracking result determined by a pre-order tracking picture frame; and tracking the current to-be-processed frame based on the existing to-be-tracked ROI, in response to determining that the current to-be-processed frame is a tracking picture frame, to determine at least one tracking result as the ROI of the current to-be-processed frame.
-
公开(公告)号：US20210360252A1
公开(公告)日：2021-11-18
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 , G06N3/04 , G06K9/62
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：US20210335008A1
公开(公告)日：2021-10-28
申请号：US17172883
申请日：2021-02-10
Inventor： Xiaoqing YE , Xiao TAN , Hao SUN , Hongwu ZHANG
Abstract: Embodiments of the present disclosure provide a method and apparatus for processing a video frame, and relates to the field of computer vision technology. The method may include: acquiring a plurality of candidate first-order radial distortion parameters preset for a to-be-processed video frame, and acquiring a specified value of a specified radial distortion parameter; performing radial distortion correction on the to-be-processed video frame to obtain a first initial corrected video frame; selecting a first initial corrected video frame in which a local region except for a center region after distortion correction includes a largest number of straight line segments; and determining a candidate first-order radial distortion parameter corresponding to the selected first initial corrected video frame for use as a target first-order radial distortion parameter of the to-be-processed video frame.
-
Patent Agency Ranking
公开(公告)号：US20210334979A1
公开(公告)日：2021-10-28
申请号：US17366691
申请日：2021-07-02
Inventor： Mian PENG , Jian WANG , Hao SUN , Xiao TAN , Errui DING
Abstract: A method of segmenting an image includes acquiring a first segmentation probability map of an input portrait image and detecting a region where a target part of the input portrait image is located. The method also includes acquiring a partial image including the target part and corresponding to the region and acquiring a partial segmentation probability map of the region in the first segmentation probability map. The method further includes segmenting the partial image in accordance with the partial segmentation probability map to acquire a second segmentation probability map. The first segmentation probability map and the second segmentation probability map are combined to acquire a segmentation result of the input portrait image.
-
公开(公告)号：US20210304413A1
公开(公告)日：2021-09-30
申请号：US17344917
申请日：2021-06-10
Inventor： Hao SUN , Fu LI , Tianwei LIN , Dongliang HE
Abstract: An image processing method, an image processing device and an electronic device, all relate to computer vision and deep learning. The image processing method includes: acquiring a first image and a second image; performing semantic region segmentation on the first image and the second image to acquire a first segmentation image and a second segmentation image respectively; determining an association matrix between the first segmentation image and the second segmentation image; and processing the first image in accordance with the association matrix to acquire a target image.
-
公开(公告)号：US20200342271A1
公开(公告)日：2020-10-29
申请号：US16817419
申请日：2020-03-12
Inventor： Zhigang WANG , Jian WANG , Shilei WEN , Errui DING , Hao SUN
Abstract: The present disclosure provides a pedestrian re-identification method and apparatus, computer device and readable medium. The method comprises: collecting a target image and a to-be-identified image including a pedestrian image; obtaining a feature expression of the target image and a feature expression of the to-be-identified image respectively, based on a pre-trained feature extraction model; wherein the feature extraction model is obtained by training based on a self-attention feature of a base image as well as a co-attention feature of the base image relative to a reference image; identifying whether a pedestrian in the to-be-identified image is the same pedestrian as that in the target image according to the feature expression of the target image and the feature expression of the to-be-identified image. According to the pedestrian re-identification method of the present disclosure, the accuracy of the pedestrian re-identification can be effectively improved when the feature extraction model is used to perform the pedestrian re-identification.
-
公开(公告)号：US20220004801A1
公开(公告)日：2022-01-06
申请号：US17480053
申请日：2021-09-20
Inventor： Zhikang ZOU , Xiaoqing YE , Hao SUN
Abstract: The present disclosure provides an image processing method and apparatus, a training method for a neural network and apparatus, a device, and a medium. The implementation is: inputting a source domain image and a target domain image into a matching feature extraction network to extract a matching feature of the source domain image and a matching feature of the target domain image, wherein the matching feature of the source domain image and the matching feature of target domain image are mutually matching features in the source domain image and the target domain image, the source domain image is a simulated image generated through rendering based on object pose parameters, and the target domain image is a real image that is actually shot and applicable to training of object pose estimation; and providing the matching feature of the source domain image for the training of the object pose estimation.
-
公开(公告)号：US20210390731A1
公开(公告)日：2021-12-16
申请号：US17201665
申请日：2021-03-15
Inventor： Jian WANG , Zipeng LU , Hao SUN , Hongwu ZHANG , Shilei WEN , Errui DING
Abstract: A method and apparatus for positioning a key point, a device, and a storage medium are provided. The method may include: extracting a first feature map and a second feature map of a to-be-positioned image, the first feature map and the second feature map being different feature maps; determining, based on the first feature map, an initial position of a key point in the to-be-positioned image; determining, based on the second feature map, an offset of the key point; and adding the initial position of the key point with the offset of the key point to obtain a final position of the key point.
-
-
-
-
-
-
-
-
-
Search Results
27
records
(took 0.04 seconds)
