-
公开(公告)号：US12206892B2
公开(公告)日：2025-01-21
申请号：US17768212
申请日：2019-10-25
Applicant: PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOL
Inventor： Ronggang Wang , Xi Xie , Kui Fan , Wen Gao
IPC: H04N19/577 , H04N19/105 , H04N19/159 , H04N19/176
Abstract: A method and a device for encoding or decoding based on an inter-frame prediction. The method includes steps of: determining a temporal motion vector prediction value of a to-be-processed coding unit, where the temporal motion vector prediction value is a temporal motion vector prediction value of a sub-block, a temporal motion vector of which is obtainable through prediction, in sub-blocks adjacent to the to-be-processed coding unit and/or sub-blocks in the to-be-processed coding unit; determining a motion vector residual prediction value of the to-be-processed coding unit according to the temporal motion vector prediction value; determining a motion vector of a sub-block in the to-be-processed coding unit according to the temporal motion vector prediction value and the motion vector residual prediction value and performing a motion compensation according to the motion vector of the sub-block in the to-be-processed coding unit to determine a prediction block of the to-be-processed coding unit.
-
公开(公告)号：US11350128B2
公开(公告)日：2022-05-31
申请号：US16641416
申请日：2019-02-19
Applicant: PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOL
Inventor： Ronggang Wang , Kui Fan , Guisen Xu , Zhenyu Wang , Wen Gao
IPC: H04N19/61 , H04N19/625 , H04N19/176
Abstract: The present application provides methods, systems, devices and computer-readable mediums for encoding and decoding transform. A method of the present application comprises: performing transform-encoding on a prediction residual block separately using a plurality of transform matrices, to obtain transformed residual blocks; based on the transformed residual block, determining, by a rate-distortion optimization decision, a transform matrix or a combination of transform matrices matching the residual characteristics of the prediction residual block from the plurality of transform matrices, and determining a transformed residual block to be outputted in a bitstream. Compared with the prior art, the method of the embodiments of the present invention performs a residual transform using transform matrices that are more closely matched with the residual characteristic, thereby improving the expression of the residual signal and improving the coding efficiency of the residual block.
-
公开(公告)号：US11227178B2
公开(公告)日：2022-01-18
申请号：US16336737
申请日：2017-11-24
Applicant: Peking University Shenzhen Graduate School
Inventor： Ge Li , Chunbiao Zhu , Wenmin Wang , Ronggang Wang , Tiejun Huang , Wen Gao
Abstract: A back-propagation significance detection method based on depth map mining, comprising: for an input image Io, at a preprocessing phase, obtaining a depth image Id and an image Cb with four background corners removed of the image Io; at a first processing phase, carrying out positioning detection on a significant region of the image by means of the obtained image Cb with four background corners removed and the obtained depth image Id to obtain the preliminary detection result S1 of a significant object in the image; then carrying out depth mining on a plurality of processing phases of the depth image Id to obtain corresponding significance detection results; and then optimizing the significance detection result mined in each processing phase by means of a back-propagation mechanism to obtain a final significance detection result map. The method can improve the detection accuracy of the significance object.
-
公开(公告)号：US11106951B2
公开(公告)日：2021-08-31
申请号：US16622570
申请日：2018-01-29
Applicant: Peking University Shenzhen Graduate School
Inventor： Wenmin Wang , Lu Ran , Ronggang Wang , Ge Li , Shengfu Dong , Zhenyu Wang , Ying Li , Hui Zhao , Wen Gao
IPC: G06K9/62 , G06K9/72 , G06F40/30 , G06F40/205 , G06F16/583 , G06N3/04 , G06N3/08
Abstract: A bidirectional image-text retrieval method based on a multi-view joint embedding space includes: performing retrieval with reference to a semantic association relationship at a global level and a local level, obtaining the semantic association relationship at the global level and the local level in a frame-sentence view and a region-phrase view, and obtaining semantic association information in a global level subspace of frame and sentence in the frame-sentence view, obtaining semantic association information in a local level subspace of region and phrase in the region-phrase view, processing data by a dual-branch neural network in the two views to obtain an isomorphic feature and embedding the same in a common space, and using a constraint condition to reserve an original semantic relationship of the data during training, and merging the two semantic association relationships using multi-view merging and sorting to obtain a more accurate semantic similarity between data.
-
5.发明授权公开(公告)号：US11100370B2
公开(公告)日：2021-08-24
申请号：US16622929
申请日：2018-01-23
Applicant: Peking University Shenzhen Graduate School
Inventor： Wenmin Wang , Yihao Zhang , Ronggang Wang , Ge Li , Shengfu Dong , Zhenyu Wang , Ying Li , Hui Zhao , Wen Gao
Abstract: Disclosed is a deep discriminative network for person re-identification in an image or a video. Concatenation are carried out on different input images on a color channel by constructing a deep discriminative network, and an obtained splicing result is defined as an original difference space of different images. The original difference space is sent into a convolutional network. The network outputs the similarity between two input images by learning difference information in the original difference space, thereby realizing person re-identification. The features of an individual image are not learnt, and concatenation are carried out on input images on a color channel at the beginning, and difference information is learnt on an original space of the images by using a designed network. By introducing an Inception module and embedding the same into a model, the learning ability of a network can be improved, and a better differentiation effect can be achieved.
-
Patent Agency Ranking
公开(公告)号：US11030444B2
公开(公告)日：2021-06-08
申请号：US16621385
申请日：2017-11-24
Applicant: Peking University Shenzhen Graduate School
Inventor： Wenmin Wang , Peilei Dong , Mengdi Fan , Ronggang Wang , Ge Li , Shengfu Dong , Zhenyu Wang , Ying Li , Hui Zhao , Wen Gao
Abstract: Disclosed is a method for detecting pedestrians in an image by using Gaussian penalty. Initial pedestrian boundary box is screened using a Gaussian penalty, to improve the pedestrian detection performance, especially sheltered pedestrians in an image. The method includes acquiring a training data set, a test data set and pedestrian labels of a pedestrian detection image; using the training data set for training to obtain a detection model by using a pedestrian detection method, and acquiring initial pedestrian boundary box and confidence degrees and coordinates thereof; performing Gaussian penalty on the confidence degrees of the pedestrian boundary box, to obtain confidence degree of the pedestrian boundary box after the penalty; and obtaining final pedestrian boundary boxes by screening the pedestrian boundary boxes. Thus, repeated boundary boxes of a single pedestrian are removed while reserving boundary boxes of sheltered pedestrians, thereby realizing the detection of the pedestrians in an image.
-
公开(公告)号：US10755390B2
公开(公告)日：2020-08-25
申请号：US16098732
申请日：2016-07-15
Applicant: PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOL
Inventor： Ronggang Wang , Xinxin Zhang , Zhenyu Wang , Wen Gao
Abstract: An image deblurring method based on light streak information in an image is provided, wherein shape information of a blur kernel is obtained based on a light streak in a motion blur image and image restoration is constrained by combining the shape information, a natural image and the blur kernel to thereby obtain an accurate blur kernel and a high-quality restored image. The method specifically comprises: selecting an optimum image patch including an optimum light streak; extracting shape information of a blur kernel from the optimum image patch including the optimum light streak; performing blur kernel estimation to obtain the final blur kernel; performing non-blind deconvolution and restoring a sharp restored image as a final deblurred image. The present disclosure establishes a blurry image test set of captured images including light streaks and a method to obtain an accurate blur kernel and a high quality restore image.
-
公开(公告)号：US10425656B2
公开(公告)日：2019-09-24
申请号：US15746932
申请日：2016-01-19
Applicant: Peking University Shenzhen Graduate School
Inventor： Zhenyu Wang , Ronggang Wang , Xiubao Jiang , Wen Gao
IPC: H04N11/02 , H04N19/513 , H04N19/176 , H04N19/59 , H04N19/597 , H04N19/523
Abstract: A video encoding and decoding method, and its inter-frame prediction method, device and system thereof are disclosed. The inter-frame prediction method includes obtaining a motion vector of the current image block and related spatial position of a current pixel, obtaining a motion vector of the current pixel according to the motion vector of the current image block and the related spatial position of the current pixel; and obtaining a predicted value of the current pixel according to the motion vector of the current pixel. The method considers both the motion vector of the current image block and the related spatial position information of the current pixel during inter-frame prediction. The method can accommodate lens distortion characteristics of different images and zoom-in/zoom-out produced when the object moves in pictures, thereby improving the calculation accuracy of pixels' motion vectors, and improving inter-frame prediction performance and compression efficiency in video encoding and decoding.
-
公开(公告)号：US10297016B2
公开(公告)日：2019-05-21
申请号：US16089493
申请日：2017-01-05
Applicant: Peking University Shenzhen Graduate School
Inventor： Ge Li , Xianghao Zang , Wenmin Wang , Ronggang Wang
Abstract: Disclosed is a video background removal method, which relates to the technical field of video analysis, and in particular to a background removal method based on an image block, a Gaussian mixture model and a random process. Firstly, the concept of blocks is defined, and a foreground and a background are determined by means of comparing a difference between blocks; a threshold value is automatically adjusted by using a Gaussian mixture model, and at the same time, the background is updated by using the idea of random process; and finally, an experiment is made on a BMC dataset, and a result shows that this method surpasses most of the current advanced algorithms, and the accuracy is very high. This method has wide applicability, can be applied to monitor video background subtraction, and is applied very importantly in the field of video analysis.
-
公开(公告)号：US20190139186A1
公开(公告)日：2019-05-09
申请号：US16307329
申请日：2016-12-05
Applicant: PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOL
Inventor： Ronggang Wang , Shen Zhang , Zhenyu Wang , Wen Gao
Abstract: Embodiments of the present disclosure provide a method for accelerating CDVS extraction process based on a GPGPU platform, wherein for the stages of feature detection and local descriptor computation of the CDVS extraction process, operation logics and parallelism strategies of respective inter-pixel parallelism sub-procedures and respective inter-feature point parallelism sub-procedures are implemented by leveraging an OpenCL general-purpose parallelism programming framework, and acceleration is achieved by leveraging a GPU's parallelism computation capability; including: partitioning computing tasks for a GPU and a CPU; reconstructing an image scale pyramid storage model; assigning parallelism strategies to respective sub-procedures for the GPU; and applying local memory to mitigate the access bottleneck. The technical solution of the present disclosure may accelerate the CDVS extraction process and significantly enhances the extraction performance.
-
-
-
-
-
-
-
-
-
Search Results
76
records
(took 0.024 seconds)
