专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明申请

US20210150268A1 Method of using deep discriminate network model for person re-identification in image or video 有权
公开(公告)号：US20210150268A1
公开(公告)日：2021-05-20
申请号：US16622929
申请日：2018-01-23
申请人： Peking University Shenzhen Graduate School
发明人： Wenmin Wang , Yihao Zhang , Ronggang Wang , Ge Li , Shengfu Dong , Zhenyu Wang , Ying Li , Hui Zhao , Wen Gao
IPC分类号： G06K9/62 , G06K9/00 , G06N3/04 , G06N3/08
摘要： 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.

42. 发明申请

US20210150255A1 Method of bidirectional image-text retrieval based on multi-view joint embedding space 有权
公开(公告)号：US20210150255A1
公开(公告)日：2021-05-20
申请号：US16622570
申请日：2018-01-29
申请人： Peking University Shenzhen Graduate School
发明人： Wenmin Wang , Lu Ran , Ronggang Wang , Ge Li , Shengfu Dong , Zhenyu Wang , Ying Li , Hui Zhao , Wen Gao
IPC分类号： G06K9/62 , G06F40/30 , G06K9/72 , G06F40/205 , G06N3/04 , G06N3/08 , G06F16/583
摘要： 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.

43. 发明申请

US20210150194A1 Image feature extraction method for person re-identification 有权
公开(公告)号：US20210150194A1
公开(公告)日：2021-05-20
申请号：US16622586
申请日：2017-12-27
申请人： Peking University Shenzhen Graduate School
发明人： Wenmin Wang , Yihao Zhang , Ronggang Wang , Ge Li , Shengfu Dong , Zhenyu Wang , Ying Li , Wen Gao
IPC分类号： G06K9/00 , G06K9/62 , G06N20/00
摘要： An image feature extraction method for person re-identification includes performing person re-identification by means of aligned local descriptor extraction and graded global feature extraction; performing the aligned local descriptor extraction by processing an original image by affine transformation and performing a summation pooling operation on image block features of same regions to obtain an aligned local descriptor; reserving spatial information between inner blocks of the image for the aligned local descriptor; and performing the graded global feature extraction by grading a positioned pedestrian region block and solving a corresponding feature mean value to obtain a global feature. The method can resolve the problem of feature misalignment caused by posture changes of pedestrian, etc., and eliminate the effect of unrelated backgrounds on re-recognition, thus improving the precision and robustness of person re-identification.

44. 发明授权

US10798301B2 Panoramic image mapping method 有权
公开(公告)号：US10798301B2
公开(公告)日：2020-10-06
申请号：US16490373
申请日：2017-08-22
申请人： PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOL
发明人： Ronggang Wang , Yueming Wang , Zhenyu Wang , Wen Gao
IPC分类号： H04N7/00 , H04N5/232 , H04N19/182 , H04N19/597 , H04N13/00
摘要： Disclosed is a panoramic image mapping method and a corresponding reversely mapping method. Particularly, the mapping process includes mapping a panoramic image or a spherical surface corresponding to Video A: first, dividing the spherical surface into three areas based on the latitudes of the spherical surface, denoted as Area I, Area II, and Area III, respectively; mapping the three areas to a square plane I′, a rectangular plane II′, and a square plane III′, respectively; then, splicing the planes I′, II′ and III′ into a plane, wherein the resulting plane is the two-dimensional image or video B. Compared with the equirectangular mapping method, the method according to the present disclosure may effectively ameliorate oversampling in high-latitude areas and effectively lower the bit rate needed by coding and the complexity of decoding. The present disclosure relates to the field of virtual reality, which may be applied to panoramic images and videos.

45. 发明授权

US10796410B2 Panoramic image mapping method 有权
公开(公告)号：US10796410B2
公开(公告)日：2020-10-06
申请号：US16313731
申请日：2016-12-13
申请人： PEKING UNIVERSITY SHENZHEN GRADUATE SCHOOL
发明人： Ronggang Wang , Yueming Wang , Zhenyu Wang , Wen Gao
IPC分类号： G06K9/36 , G06T3/40
摘要： Disclosed is a panoramic image mapping method, wherein mapping regions and a non-mapping region are partitioned for an equirectangular panoramic image with a resolution of 2M×M, where only the partitioned mapping regions are mapped as square regions; the method comprises:, computing a vertical distance and a horizontal distance from a point on the square region to a center of the square region, a larger one of which being denoted as m; computing a distance n from the point to a zeroth (0th) point on a concentric square region; computing a longitude and a latitude corresponding to the point; computing a corresponding position (X, Y) in the equirectangular panoramic image to which the point is mapped; and then assigning a value to the point. The method may effectively reduce oversampling, thereby effectively reducing the number of pixels of the panoramic image and the code rate required for coding with little distortion.

46. 发明申请

US20200160048A1 Method for detecting pedestrians in image by using Gaussian penalty 审中-公开
公开(公告)号：US20200160048A1
公开(公告)日：2020-05-21
申请号：US16621385
申请日：2017-11-24
申请人： Peking University Shenzhen Graduate School
发明人： Wenmin Wang , Peilei Dong , Mengdi Fan , Ronggang Wang , Ge Li , Shengfu Dong , Zhenyu Wang , Ying Li , Hui Zhao , Wen Gao
IPC分类号： G06K9/00 , G06T7/70 , G06K9/62 , G06N3/08
摘要： 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.

47. 发明授权

US10531093B2 Method and system for video frame interpolation based on optical flow method 有权
公开(公告)号：US10531093B2
公开(公告)日：2020-01-07
申请号：US15574954
申请日：2015-05-25
申请人： Peking University Shenzhen Graduate School
发明人： Chuanxin Tang , Ronggang Wang , Zhenyu Wang , Wen Gao
IPC分类号： H04N19/139 , G06T3/40 , H04N7/01 , H04N19/537 , H04N19/553 , H04N19/513 , H04N19/117 , H04N19/33 , H04N19/543 , H04N19/577 , H04N5/14
摘要： A method and system for video frame interpolation based on an optical flow method is disclosed. The process includes calculating bidirectional motion vectors between two adjacent frames in a frame sequence of input video by using the optical flow method, judging reliabilities of the bidirectional motion vectors between the two adjacent frames, and processing a jagged problem and a noise problem in the optical flow method; marking “shielding” and “exposure” regions in the two adjacent frames, and updating an unreliable motion vector; with regard to the two adjacent frames, according to marking information about the “shielding” and “exposure” regions and the bidirectional motion vector field, mapping front and back frames to an interpolated frame to obtain a forward interpolated frame and a backward interpolated frame; synthesizing the forward interpolated frame and the backward interpolated frame into the interpolated frame; repairing a hole point in the interpolated frame to obtain a final interpolated frame. Since the optical flow method is based on pixels, disclosed method and system are more accurate and do not have blocking effect and other problems.

48. 发明授权

US10424075B2 Depth/disparity map post-processing method and device 有权
公开(公告)号：US10424075B2
公开(公告)日：2019-09-24
申请号：US15565877
申请日：2015-05-06
申请人： Peking University Shenzhen Graduate School
发明人： Jianbo Jiao , Ronggang Wang , Zhenyu Wang , Wenmin Wang , Wen Gao
IPC分类号： G06T7/50 , G06T5/50 , G06T7/11 , G06T7/13 , G06K9/46 , G06T5/00 , G06T5/20 , G06T5/40 , G06T7/136
摘要： A method and a device for post-processing depth/disparity maps adopt a strategy of combining edge information and segmentation information when detecting irregular edge regions. The method includes dividing a color image into super pixels when performing image segmentation on a color image; partitioning a grayscale range into a preset number of intervals, and for each super pixel, statistically obtaining a histogram of all the pixel points that fall within the intervals; determining, in a current super pixel, whether a ratio of the number of pixels contained in the interval having a maximum interval distribution value, to the total number of pixels in the current super pixel is less than the first threshold; and if so, further dividing the current super pixel using a color-based segmentation method. The disclosed method and device improve accuracy of color image division while ensuring image processing speed, thus improving detection accuracy of the irregular edge regions.

49. 发明授权

US10424054B2 Low-illumination image processing method and device 有权
公开(公告)号：US10424054B2
公开(公告)日：2019-09-24
申请号：US15736403
申请日：2015-06-26
申请人： Peking University Shenzhen Graduate School
发明人： Lin Li , Ronggang Wang , Chengzhou Tang , Zhenyu Wang , Wen Gao
IPC分类号： G06T5/00 , G06T7/11 , G06T7/90 , G06T7/40
摘要： A low-illumination image processing method and device address the problem of noise amplification in existing contrast enhancement techniques when applied to original low-illumination image. A noise suppression filter is additionally arranged before an operation of contrast enhancement, and smoothing processing is performed on an inverse color image of a low-illumination image by adopting a first filtering coefficient and a second filtering coefficient, so that image contrast is enhanced while random noise is suppressed. Texture and noise level parameter of an image are calculated according to a local characteristic inside block of the image. Weighted averaging is performed on a first smoothing image and a second smoothing image after smoothing processing according to the texture and noise level parameters. The texture image is obtained by performing texture structure extraction on a gradient image of an inverse color image, and the texture image is combined with a weighted image to sharpen the weighted image, to have an effect of enhancing image details. Therefore, the contrast of low-illumination image can be effectively enhanced, various types of noise can be filtered, and the image color and details can be retained at the same time to obtain a clear and vivid restored image.

50. 发明授权

US10339633B2 Method and device for super-resolution image reconstruction based on dictionary matching 有权
公开(公告)号：US10339633B2
公开(公告)日：2019-07-02
申请号：US15749554
申请日：2015-11-04
申请人： Peking University Shenzhen Graduate School
发明人： Yang Zhao , Ronggang Wang , Wen Gao , Zhenyu Wang , Wenmin Wang
IPC分类号： G06T3/40 , G06K9/46 , G06K9/62
摘要： The present application provides a method and a device for super-resolution image reconstruction based on dictionary matching. The method includes: establishing a matching dictionary library; inputting an image to be reconstructed into a multi-layer linear filter network; extracting a local characteristic of the image to be reconstructed; searching the matching dictionary library for a local characteristic of a low-resolution image block having the highest similarity with the local characteristic of the image to be reconstructed; searching the matching dictionary library for a residual of a combined sample where the local characteristic of the low-resolution image block with the highest similarity is located; performing interpolation amplification on the local characteristic of the low-resolution image block having the highest similarity; and adding the residual to a result of the interpolation amplification to obtain a reconstructed high-resolution image block. The local characteristics of the image to be reconstructed extracted by the multi-layer linear filter network have higher precision. Thus, a higher matching degree can be obtained during subsequent matching with the matching dictionary library, and the reconstructed image has a better quality. Therefore, the present invention can greatly improve the quality of the high-resolution image to be reconstructed.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式