-
1.发明申请公开(公告)号：US20210271892A1
公开(公告)日：2021-09-02
申请号：US17321237
申请日：2021-05-14
发明人： Jingmin Luo , Liang Qiao , Xiaolong Zhu
摘要： A computer device extracts a plurality of target windows from a target video. Each of the target windows comprises a respective plurality of consecutive video frames. For each of the target windows, the device performs action recognition on the respective plurality of consecutive video frames corresponding to the target window to obtain respective first action feature information of the target window. The device obtains a similarity between the first action feature information of the target window and preset feature information. The device determines, from the respective obtained similarities corresponding to the plurality of target windows, a highest first similarity and a first target window corresponding to the highest first similarity. The device also determines a dynamic action corresponding to the highest first similarity as the preset dynamic action in accordance with threshold settings.
-
2.发明授权公开(公告)号：US11961237B2
公开(公告)日：2024-04-16
申请号：US17330268
申请日：2021-05-25
发明人： Jingmin Luo , Xiaolong Zhu
CPC分类号： G06T7/11 , G06F18/214 , G06T5/002 , G06T7/194 , G06V10/28 , G06V10/34 , G06V40/20 , G06T2207/20081
摘要： Embodiments of this application disclose a foreground data generation method performed at a computer device. The method includes: obtaining a background image and a target image, the target image containing a target object and a background; removing the background from the target image according to the background image and the target image, to obtain initial foreground data of the target object in the target image; obtaining certain foreground data and uncertain data from the initial foreground data, wherein the uncertain data represents data whose value is between the certain foreground data and background data corresponding to the background; and segmenting the certain foreground data from the uncertain data, to obtain target foreground data of the target object in the target image.
-
公开(公告)号：US11907848B2
公开(公告)日：2024-02-20
申请号：US17330261
申请日：2021-05-25
发明人： Jingmin Luo , Xiaolong Zhu , Yitong Wang , Xing Ji
CPC分类号： G06N3/084 , G06T7/74 , G06V10/764 , G06V20/647 , G06V40/10 , G06V40/103 , G06V40/23
摘要： This application provides a method for training a pose recognition model performed at a computer device. The method includes: inputting a sample image labeled with human body key points into a feature map model included in a pose recognition model, to output a feature map of the sample image; inputting the feature map into a two-dimensional (2D) model included in the pose recognition model, to output 2D key point parameters used for representing a 2D human body pose; input a target human body feature map cropped from the feature map and the 2D key point parameter into a three-dimensional (3D) model included in the pose recognition model, to output 3D pose parameters used for representing a 3D human body pose; constructing a target loss function based on the 2D key point parameters and the 3D pose parameters; and updating the pose recognition model based on the target loss function.
-
公开(公告)号：US12020142B2
公开(公告)日：2024-06-25
申请号：US16659888
申请日：2019-10-22
发明人： Xiao Long Zhu , Yi Tong Wang , Kai Ning Huang , Lijian Mei , Shenghui Huang , Jingmin Luo
摘要： Embodiments of this application provide a neural network model deployment method, a prediction method and a device. The described features can implement deployment of a neural network model to improve the universality of the deployment of the neural network model to the terminal device by obtaining a layer definition and an operation parameter of each network layer of an initial neural network model, executing a target network layer corresponding to the network layers, applying relational connections amongst the target network layers using a net class, converting the operation parameters into a preset format, obtaining a target operation parameter based on the preset format, loading a corresponding target operation parameter in the target network layer, and obtaining a target neural network model based on the target operation parameter.
-
5.发明授权公开(公告)号：US11710351B2
公开(公告)日：2023-07-25
申请号：US17321237
申请日：2021-05-14
发明人： Jingmin Luo , Liang Qiao , Xiaolong Zhu
CPC分类号： G06V40/23 , G06T7/74 , G06V10/754 , G06V10/82 , G06V20/41 , G06V20/46 , G06V20/48 , G06V40/103 , G06V10/422
摘要： A computer device extracts a plurality of target windows from a target video. Each of the target windows comprises a respective plurality of consecutive video frames. For each of the target windows, the device performs action recognition on the respective plurality of consecutive video frames corresponding to the target window to obtain respective first action feature information of the target window. The device obtains a similarity between the first action feature information of the target window and preset feature information. The device determines, from the respective obtained similarities corresponding to the plurality of target windows, a highest first similarity and a first target window corresponding to the highest first similarity. The device also determines a dynamic action corresponding to the highest first similarity as the preset dynamic action in accordance with threshold settings.
-
6.发明授权公开(公告)号：US11501574B2
公开(公告)日：2022-11-15
申请号：US17073441
申请日：2020-10-19
发明人： Haozhi Huang , Xinyu Gong , Jingmin Luo , Xiaolong Zhu , Wei Liu
IPC分类号： G06V40/20 , G06T7/73 , H04L12/46 , H04L61/103 , H04L67/125 , H04L69/325 , H04N19/126 , H04N19/543 , H04N19/55 , H04N19/59 , H04N19/70 , H04N19/87 , G06V10/44 , G06V10/80 , G06V10/82
摘要： In a multi-person pose recognition method, a to-be-recognized image is obtained, and a circuitous pyramid network is constructed. The circuitous network pyramid includes parallel phases, and each phase includes downsampling network layers, upsampling network layers, and a first residual connection layer to connect the downsampling and upsampling network layers. The phases are interconnected by a second residual connection layer. The circuitous pyramid network is traversed, by extracting a feature map for each phase, and the feature map of the last phase is determined to be the feature map of the to-be-recognized image. Multi-pose recognition is then performed on the to-be-recognized image according to the feature map to obtain a pose recognition result for the to-be-recognized image.
-
公开(公告)号：US11417095B2
公开(公告)日：2022-08-16
申请号：US16685526
申请日：2019-11-15
发明人： Xiaolong Zhu , Kaining Huang , Jingmin Luo , Lijian Mei , Shenghui Huang , Yongsen Zheng , Yitong Wang , Haozhi Huang
摘要： An image recognition method is provided. The method includes obtaining predicted locations of joints of a target person in a to-be-recognized image based on a joint prediction model, where the joint prediction model is pre-constructed by: obtaining a plurality of sample images; inputting training features of the sample images and a body model feature to a neural network and obtaining predicted locations of joints in the sample images outputted by the neural network; updating a body extraction parameter and an alignment parameter; and inputting the training features of the sample images and the body model feature to the neural network to obtain the joint prediction model.
-
公开(公告)号：US11200680B2
公开(公告)日：2021-12-14
申请号：US16671747
申请日：2019-11-01
发明人： Xiaolong Zhu , Kaining Huang , Jingmin Luo , Lijian Mei , Shenghui Huang , Yongsen Zheng , Yitong Wang , Haozhi Huang
摘要： An image processing method and a related apparatus are provided. The method is applied to an image processing device, and includes: obtaining an original image, the original image including a foreground object; extracting a foreground region from the original image through a deep neural network; identifying pixels of the foreground object from the foreground region; forming a mask according to the pixels of the foreground object, the mask including mask values corresponding to the pixels of the foreground object; and extracting the foreground object from the original image according to the mask.
-
公开(公告)号：US10891799B2
公开(公告)日：2021-01-12
申请号：US16680058
申请日：2019-11-11
发明人： Xiaolong Zhu , Yitong Wang , Kaining Huang , Lijian Mei , Shenghui Huang , Jingmin Luo
摘要： An augmented reality processing method is provided for a terminal. The method includes: obtaining a plurality of frames of images, comprising a first image and a second image, which is a frame of an image immediately following the first image; obtaining a key point set of a first object in the first image; obtaining, through a neural network model, first pose key point sets respectively corresponding to a plurality of objects in the second image; determining a second pose key point set of the first object in the second image according to the key point set and a motion trend of the first object; using a target first pose key point set as a key point set of the first object in the second image; and generating an augmented information image according to the key point set of the first object in the second image.
-
-
-
-
-
-
-
-
搜索结果
9 条记录 (耗时 0.018 秒)
