-
公开(公告)号：US11348338B2
公开(公告)日：2022-05-31
申请号：US17088962
申请日：2020-11-04
摘要： A crowd motion summarization method that provides a rich, real-time description of the crowd's characteristics from a video, such as, speed, orientation, count, spatial locations, and time. A feature tracking module receives each video frame and detects features (feature points) from the video frame. A crowd occupancy detection module receives the video frame and generates a binary crowd occupancy map having human pixel positions which indicate the human location versus non-human location, and generates a total human count of humans detected in the video frame. The feature tracking module generates feature tracking information for only those features contained in the human pixel positions which indicate the human location. In an example, the detected features are Kanade-Lucas-Tomasi (KLT) features. A feature-crowd matching module generates, using the feature tracking information and the total human count: crowd motion data. The method outputs the crowd motion data.
-
公开(公告)号：US11501415B2
公开(公告)日：2022-11-15
申请号：US17080714
申请日：2020-10-26
申请人： Zili Yi , Qiang Tang , Shekoofeh Azizi , Daesik Jang , Zhan Xu
发明人： Zili Yi , Qiang Tang , Shekoofeh Azizi , Daesik Jang , Zhan Xu
摘要： Methods and systems for high-resolution image inpainting are disclosed. An original high-resolution image to be inpainted is obtained, as well as an inpainting mask indicating an inside-mask area to be inpainted. The original high-resolution image is down-sampled to obtain a low-resolution image to be inpainted. Using a trained inpainting generator, a low-resolution inpainted image and a set of attention scores are generated from the low-resolution image. The attention scores represent the similarity between inside-mask regions and outside-mask regions. A high-frequency residual image is computed from the original high-resolution image. An aggregated high-frequency residual image is generated using the attention scores, including high-frequency residual information for the inside-mask area. A high-resolution inpainted image is outputted by combining the aggregated high-frequency residual image and a low-frequency inpainted image generated from the low-resolution inpainted image.
-
公开(公告)号：US20220138475A1
公开(公告)日：2022-05-05
申请号：US17088962
申请日：2020-11-04
摘要： A crowd motion summarization method that provides a rich, real-time description of the crowd's characteristics from a video, such as, speed, orientation, count, spatial locations, and time. A feature tracking module receives each video frame and detects features (feature points) from the video frame. A crowd occupancy detection module receives the video frame and generates a binary crowd occupancy map having human pixel positions which indicate the human location versus non-human location, and generates a total human count of humans detected in the video frame. The feature tracking module generates feature tracking information for only those features contained in the human pixel positions which indicate the human location. In an example, the detected features are
Kanade-Lucas-Tomasi (KLT) features. A feature-crowd matching module generates, using the feature tracking information and the total human count: crowd motion data. The method outputs the crowd motion data.-
公开(公告)号：US08965140B1
公开(公告)日：2015-02-24
申请号：US13018003
申请日：2011-01-31
申请人： Zhan Xu , David Victor Hobbs
发明人： Zhan Xu , David Victor Hobbs
CPC分类号： G06K9/38 , H04N19/119 , H04N19/12 , H04N19/137 , H04N19/14 , H04N19/176
摘要： A method and apparatus for encoding a frame from a mixed content image sequence. In one embodiment, the method, executed under the control of a processor configured with computer executable instructions, comprises (i) generating, by an encoding processor, an image type mask that divides the frame into an unchanged portion, an object portion and a picture portion; (ii) producing lossless encoded content, by the encoding processor, from the object portion and the image type mask; (iii) generating, by the encoding processor, a filtered facsimile from the frame, the filtered facsimile generated by retaining the picture portion and filling the unchanged portion and the object portion with neutral image data; and (iv) producing, by the encoding processor, lossy encoded content from the filtered facsimile.
摘要翻译： 一种用于从混合内容图像序列编码帧的方法和装置。 在一个实施例中，在配置有计算机可执行指令的处理器的控制下执行的方法包括（i）由编码处理器生成将帧划分为不变部分，对象部分和图片的图像类型掩码 一部分; （ii）由编码处理器从对象部分和图像类型掩码产生无损编码内容; （iii）通过编码处理器从帧生成经滤波的传真，通过保留图像部分并将未改变的部分和对象部分填充中立的图像数据产生的经滤波的传真; 以及（iv）由编码处理器从经过滤的传真机产生有损编码的内容。
-
公开(公告)号：US11915383B2
公开(公告)日：2024-02-27
申请号：US17367524
申请日：2021-07-05
申请人： Zili Yi , Qiang Tang , Vishnu Sanjay Ramiya Srinivasan , Zhan Xu
发明人： Zili Yi , Qiang Tang , Vishnu Sanjay Ramiya Srinivasan , Zhan Xu
CPC分类号： G06T3/0093 , G06T3/40 , G06T3/4046 , G06T3/4069 , G06T3/4076 , G06T11/60 , G06V40/162
摘要： Methods and systems for high-resolution image manipulation are disclosed. An original high-resolution image to be manipulated is obtained, as well as a driving signal indicating a manipulation result. The original high-resolution image is down-sampled to obtain a low-resolution image to be manipulated. Using a trained manipulation generator, a low-resolution manipulated image and a motion field are generated from the low-resolution image. The motion field represent pixel displacements of the low-resolution image to obtain the manipulation indicated by the driving signal. A high-frequency residual image is computed from the original high-resolution image. A high-frequency manipulated residual image is generated using the motion field. A high-resolution manipulated image is outputted by combining the high-frequency manipulated residual image and a low-frequency manipulated image generated from the low-resolution manipulated image by up-sampling.
-
6.发明授权公开(公告)号：US11676390B2
公开(公告)日：2023-06-13
申请号：US17079084
申请日：2020-10-23
申请人： Qiang Tang , Zili Yi , Zhan Xu
发明人： Qiang Tang , Zili Yi , Zhan Xu
CPC分类号： G06V20/53 , G06T7/11 , G06V40/162 , G06V40/172 , G06T2207/20084 , G06T2207/30242 , G06V2201/07
摘要： Methods and systems for fully-automatic image processing to detect and remove unwanted people from a digital image of a photograph. The system includes the following modules: 1) Deep neural network (DNN)-based module for object segmentation and head pose estimation; 2) classification (or grouping) of wanted versus unwanted people based on information collected in the first module; 3) image inpainting of the unwanted people in the digital image. The classification module can be rules-based in an example. In an example, the DNN-based module generates, from the digital image: 1. A list of object category labels, 2. A list of object scores, 3. A list of binary masks, 4. A list of object bounding boxes, 5. A list of crowd instances, 6. A list of human head bounding boxes, and 7. A list of head poses (e.g., yaws, pitches, and rolls).
-
7.发明授权Method and system for remotely communicating a computer rendered image sequence 有权用于远程传达计算机渲染图像序列的方法和系统公开(公告)号：US08520734B1
公开(公告)日：2013-08-27
申请号：US12462235
申请日：2009-07-31
申请人： Zhan Xu
发明人： Zhan Xu
IPC分类号： H04N7/12
CPC分类号： H04N19/34 , H04N19/105 , H04N19/139 , H04N19/176 , H04N19/517
摘要： A method and system for communicating a computer rendered image sequence from a host computer to a remote computer. The method comprises determining, at the host computer, while performing a progressive encoding of an image portion of the computer rendered image sequence, motion of the image portion, wherein the progressive encoding comprises generating a lossy encoding of a frequency transform of the image portion and a first refinement encoding of the frequency transform; generating, at the host computer, a motion vector representing the motion; and communicating, from the host computer to the remote computer, the lossy encoding, the first refinement encoding, and the motion vector.
摘要翻译： 一种用于将计算机渲染的图像序列从主机传送到远程计算机的方法和系统。 所述方法包括在所述主机计算机执行所述计算机渲染图像序列的图像部分的逐行编码时，确定所述图像部分的运动，其中所述渐进编码包括生成所述图像部分的频率变换的有损编码，以及 频率变换的第一个细化编码; 在主机计算机生成表示运动的运动矢量; 并从主计算机向远程计算机传送有损编码，第一细化编码和运动矢量。
-
8.发明公开公开(公告)号：US20230252787A1
公开(公告)日：2023-08-10
申请号：US17592790
申请日：2022-02-04
申请人： Kevin James Cannons , Zhan XU , Minlong LU
发明人： Kevin James Cannons , Zhan XU , Minlong LU
CPC分类号： G06V20/50 , G06V10/225 , G06K9/6288 , G06V40/103 , G06T11/00 , G06N20/00 , G06T2210/12 , G06V10/82
摘要： Systems, methods, and computer-readable media for identifying a main group of people in an image via social relation recognition. The main group of people is identified within an image by identifying social relationships between people visible in the image. The identification of social relationships is performed by a Social Relation Recognition Network (SRRN) trained using deep learning. The SRRN combines two techniques for group identification, First Glance and Graph Reasoning, and fuses their outputs to generate a prediction of group membership. A group refinement module improves and filters the group membership after identification of an initial main group.
-
公开(公告)号：US20230019851A1
公开(公告)日：2023-01-19
申请号：US17367524
申请日：2021-07-05
申请人： Zili YI , Qiang TANG , Vishnu Sanjay RAMIYA SRINIVASAN , Zhan XU
发明人： Zili YI , Qiang TANG , Vishnu Sanjay RAMIYA SRINIVASAN , Zhan XU
摘要： Methods and systems for high-resolution image manipulation are disclosed. An original high-resolution image to be manipulated is obtained, as well as a driving signal indicating a manipulation result. The original high-resolution image is down-sampled to obtain a low-resolution image to be manipulated. Using a trained manipulation generator, a low-resolution manipulated image and a motion field are generated from the low-resolution image. The motion field represent pixel displacements of the low-resolution image to obtain the manipulation indicated by the driving signal. A high-frequency residual image is computed from the original high-resolution image. A high-frequency manipulated residual image is generated using the motion field. A high-resolution manipulated image is outputted by combining the high-frequency manipulated residual image and a low-frequency manipulated image generated from the low-resolution manipulated image by up-sampling.
-
10.发明申请公开(公告)号：US20220129682A1
公开(公告)日：2022-04-28
申请号：US17079084
申请日：2020-10-23
申请人： Qiang TANG , Zili YI , Zhan XU
发明人： Qiang TANG , Zili YI , Zhan XU
摘要： Methods and systems for fully-automatic image processing to detect and remove unwanted people from a digital image of a photograph. The system includes the following modules: 1) Deep neural network (DNN)-based module for object segmentation and head pose estimation; 2) classification (or grouping) of wanted versus unwanted people based on information collected in the first module; 3) image inpainting of the unwanted people in the digital image. The classification module can be rules-based in an example. In an example, the DNN-based module generates, from the digital image: 1. A list of object category labels, 2. A list of object scores, 3. A list of binary masks, 4. A list of object bounding boxes, 5. A list of crowd instances, 6. A list of human head bounding boxes, and 7. A list of head poses (e.g., yaws, pitches, and rolls).
-
-
-
-
-
-
-
-
-
搜索结果
13 条记录 (耗时 0.017 秒)
