-
Patent Agency Ranking
公开(公告)号：US11948400B2
公开(公告)日：2024-04-02
申请号：US18344877
申请日：2023-06-30
CPC classification number: G06V40/23 , G06T7/248 , G06T7/277 , G06V10/462 , G06V10/82 , G06V20/46 , G06V20/52 , G08B21/043 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/30196
Abstract: An action detection method based on a human skeleton feature and a storage medium belong to the field of computer vision, and the method includes: for each person, extracting a series of body keypoints in every frame of the video as the human skeleton feature; calculating a body structure center point and approximating rigid motion area by using the human skeleton feature as a calculated value from the skeleton feature state, and predicting an estimated value in the next frame; performing target matching according to the estimated and calculated value, correlating the human skeleton feature belonging to the same target to obtain a skeleton feature sequence, and then correlating features of each keypoint in the temporal domain to obtain a spatial-temporal domain skeleton feature; inputting the skeleton feature into an action detection model to obtain an action category. In the disclosure, the accuracy of action detection is improved.
-
公开(公告)号：US20240080439A1
公开(公告)日：2024-03-07
申请号：US18447252
申请日：2023-08-09
Inventor： Li Yu , Zhewen Sun
IPC: H04N19/105 , H04N19/119 , H04N19/147 , H04N19/176 , H04N19/96
CPC classification number: H04N19/105 , H04N19/119 , H04N19/147 , H04N19/176 , H04N19/96
Abstract: An intra-frame predictive coding method, medium and system for a 360-degree video belong to video coding field are provided. The method includes: inputting features of a coding unit (CU) block to be partitioned into a neural network when intra-frame block partition (IFBP) is performed on a current CU block (CCUB), skipping a partition mode that the output of the neural network is smaller than threshold, and obtaining a plurality of IFBP schemes; determining a length n of a rough mode decision candidate list according to a CU feature and a texture feature of the sub-CU block when an intra-frame angle mode is decided to decide the intra-frame angle mode and to fill pixels in each IFBP scheme; calculating rate distortion optimization (RDO) loss between each IFBP scheme and the CCUB after pixel filling and performing intra-frame coding predictive coding on the CCUB based on the scheme.
-
公开(公告)号：US20240021019A1
公开(公告)日：2024-01-18
申请号：US18344877
申请日：2023-06-30
CPC classification number: G06V40/23 , G06T7/248 , G06T7/277 , G06V10/82 , G06V20/46 , G06V20/52 , G06V10/462 , G08B21/043 , G06T2207/30196 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084
Abstract: An action detection method based on a human skeleton feature and a storage medium belong to the field of computer vision, and the method includes: for each person, extracting a series of body keypoints in every frame of the video as the human skeleton feature; calculating a body structure center point and approximating rigid motion area by using the human skeleton feature as a calculated value from the skeleton feature state, and predicting an estimated value in the next frame; performing target matching according to the estimated and calculated value, correlating the human skeleton feature belonging to the same target to obtain a skeleton feature sequence, and then correlating features of each keypoint in the temporal domain to obtain a spatial-temporal domain skeleton feature; inputting the skeleton feature into an action detection model to obtain an action category. In the disclosure, the accuracy of action detection is improved.
-
公开(公告)号：US12015767B2
公开(公告)日：2024-06-18
申请号：US18447252
申请日：2023-08-09
Inventor： Li Yu , Zhewen Sun
IPC: H04N19/105 , H04N19/119 , H04N19/147 , H04N19/176 , H04N19/96
CPC classification number: H04N19/105 , H04N19/119 , H04N19/147 , H04N19/176 , H04N19/96
Abstract: An intra-frame predictive coding method, medium and system for a 360-degree video belong to video coding field are provided. The method includes: inputting features of a coding unit (CU) block to be partitioned into a neural network when intra-frame block partition (IFBP) is performed on a current CU block (CCUB), skipping a partition mode that the output of the neural network is smaller than threshold, and obtaining a plurality of IFBP schemes; determining a length n of a rough mode decision candidate list according to a CU feature and a texture feature of the sub-CU block when an intra-frame angle mode is decided to decide the intra-frame angle mode and to fill pixels in each IFBP scheme; calculating rate distortion optimization (RDO) loss between each IFBP scheme and the CCUB after pixel filling and performing intra-frame coding predictive coding on the CCUB based on the scheme.
-
5.发明授权公开(公告)号：US11837021B1
公开(公告)日：2023-12-05
申请号：US18346760
申请日：2023-07-03
Inventor： Li Yu , Shuangjiang He , Huijuan Zhao
IPC: G06V40/16 , G06V10/764 , G06V10/80 , G06V10/774
CPC classification number: G06V40/176 , G06V10/764 , G06V10/774 , G06V10/806 , G06V40/165 , G06V40/172
Abstract: Disclosed is a compound expression recognition method with few samples of multi-domain adversarial learning. To extract compound expression features with diversity and complexity with few samples, multiple small sample datasets are fused, and divided into expression sub-domains, and multi-domain adversarial learning is performed to improve the performance of compound expression recognition. Based on the generative adversarial network framework, the face domain and the contour-independent compound expression domain are fused in the generative network to enhance diversity and complexity, and two discriminators are designed to guide the generator. The face discriminator uses the face domain to guide the generator and identify the generator to generate expression-independent face identity attributes, so that the generator has identity diversity. The compound expression fusing discriminator fuses the basic expression domain and the contour-related compound expression domain together to guide the generator and identify the complexity of the expressions generated by the generator.
-
-
-
-
Search Results
5
records
(took 0.014 seconds)
