公开(公告)号：US20160019683A1

公开(公告)日：2016-01-21

申请号：US14797667

申请日：2015-07-13

Applicant: Ganmei YOU ,  Yuan LIU ,  Zhongchao SHI ,  Yaojie LU ,  Gang WANG

Inventor： Ganmei YOU ,  Yuan LIU ,  Zhongchao SHI ,  Yaojie LU ,  Gang WANG

IPC: G06T7/00

CPC classification number: G06T7/74 ,  G06T2207/10021 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/30261

Abstract: Disclosed is an object detection method used to detect an object in an image pair corresponding to a current frame. The image pair includes an original image of the current frame and a disparity map of the same current frame. The original image of the current frame includes at least one of a grayscale image and a color image of the current frame. The object detection method comprises steps of obtaining a first detection object detected in the disparity map of the current frame; acquiring an original detection object detected in the original image of the current frame; correcting, based on the original detection object, the first detection object so as to obtain a second detection object; and outputting the second detection object.

Abstract translation: 公开了一种用于检测对应于当前帧的图像对中的对象的对象检测方法。 图像对包括当前帧的原始图像和相同当前帧的视差图。 当前帧的原始图像包括灰度图像和当前帧的彩色图像中的至少一个。 对象检测方法包括以下步骤：获得在当前帧的视差图中检测到的第一检测对象; 获取在当前帧的原始图像中检测到的原始检测对象; 基于原始检测对象来校正第一检测对象，以获得第二检测对象; 并输出第二检测对象。

公开(公告)号：US20140086451A1

公开(公告)日：2014-03-27

申请号：US14025008

申请日：2013-09-12

Applicant: Dianchao LIU ,  Yuan LIU ,  Tong LIU ,  Zhongchao SHI ,  Gang WANG

Inventor： Dianchao LIU ,  Yuan LIU ,  Tong LIU ,  Zhongchao SHI ,  Gang WANG

IPC: G06K9/00

CPC classification number: G06K9/00798 ,  G06K9/00208 ,  G06K9/00791 ,  G06K9/00805

Abstract: A method and an apparatus are disclosed for detecting a continuous road partition with a height, the method comprising the steps of: obtaining disparity maps having the continuous road partition, and U-disparity maps corresponding to the disparity maps; obtaining an intermediate detection result of the continuous road partition detected from the U-disparity maps of first N frames; and detecting the continuous road partition from the U-disparity map of a current frame, based on the obtained intermediate detection result.

Abstract translation: 公开了一种用于检测具有高度的连续道路分隔的方法和装置，所述方法包括以下步骤：获得具有连续道路划分的视差图和对应于视差图的U视差图; 从前N帧的U视差图中获取连续道路分区的中间检测结果; 并根据获得的中间检测结果，根据当前帧的U视差图检测连续道路分割。

公开(公告)号：US20130058528A1

公开(公告)日：2013-03-07

申请号：US13589393

申请日：2012-08-20

Applicant: Tong LIU ,  Zhongchao SHI ,  Cheng ZHONG ,  Yuan LIU ,  Yi CHEN

Inventor： Tong LIU ,  Zhongchao SHI ,  Cheng ZHONG ,  Yuan LIU ,  Yi CHEN

IPC: G06K9/00

CPC classification number: G06K9/00805 ,  G06K9/00798

Abstract: Disclosed are a method and a system for detecting a vehicle position by employing a polarization image. The method comprises a step of capturing a polarization image by using a polarization camera; a step of acquiring two road shoulders in the polarization image based on a difference between a road surface and each of the two road shoulders in the polarization image, and determining a part between the two road shoulders as the road surface; a step of detecting at least one vehicle bottom from the road surface based on a significant pixel value difference between each wheel and the road surface in the polarization image; and a step of generating a vehicle position from the vehicle bottom based on a pixel value difference between a vehicle outline corresponding to the vehicle bottom and background in the polarization image.

Abstract translation: 公开了一种通过采用偏振图像来检测车辆位置的方法和系统。 该方法包括通过使用偏振照相机捕获偏振图像的步骤; 基于所述偏振图像中的路面与所述两个路肩中的每一个之间的差异，在所述偏振图像中获取两个路肩的步骤，以及确定所述两个路肩之间的部分作为所述路面; 基于所述偏振图像中的每个车轮与所述路面之间的有效像素值差异，从所述路面检测至少一个车辆底部的步骤; 以及基于车辆底部对应的车辆轮廓与偏振图像中的背景之间的像素值差异，从车辆底部产生车辆位置的步骤。

公开(公告)号：US20110225172A1

公开(公告)日：2011-09-15

申请号：US13033016

申请日：2011-02-23

Applicant: Yuan LIU ,  Gang Wang ,  Tao Li ,  Yinghui Xu ,  Caizhi Zhu

Inventor： Yuan LIU ,  Gang Wang ,  Tao Li ,  Yinghui Xu ,  Caizhi Zhu

IPC: G06F17/30

CPC classification number: G06F17/30265

Abstract: Disclosed are a system, a method, and a computer-readable medium for seeking representative images in an image set. The method comprises a text feature extracting step of extracting text features of each of the plural images; a diversity data obtaining step of obtaining diversity data of the image set based on the text features; a representative score calculating method of calculating a representative score of each of the plural images based on the diversity data; and a representative image selecting step of selecting one or more of the images in the image set based on the representative score of the corresponding images.

Abstract translation: 公开了一种用于在图像集中寻找代表性图像的系统，方法和计算机可读介质。 该方法包括提取多个图像中的每一个的文本特征的文本特征提取步骤; 分集数据获取步骤，基于所述文本特征获得所述图像集合的分集数据; 基于分集数据计算多个图像中的每一个的代表分数的代表分数计算方法; 以及代表图像选择步骤，基于相应图像的代表性分数来选择图像集中的一个或多个图像。

公开(公告)号：US20120033030A1

公开(公告)日：2012-02-09

申请号：US13273668

申请日：2011-10-14

Applicant: Yuan LIU ,  Jiaoli Wu ,  Guangyao Zhao ,  Jing Wang

Inventor： Yuan LIU ,  Jiaoli Wu ,  Guangyao Zhao ,  Jing Wang

IPC: H04N7/15

CPC classification number: H04N7/15

Abstract: A remote presenting system, includes: a plurality of displays, configured to display a remote image; an audio output apparatus, configured to output remote audio information; a multimedia communication terminal, configured to process and control audio/video information obtained by a local end and audio/video information sent by a remote end; a plurality of video cameras, configured to shoot a local video image and send the shot video image to the multimedia communication terminal to be processed; an audio collection apparatus, configured to collect local audio information, and send the collected audio information to the multimedia communication terminal; and a plurality of user locations, corresponding to the plurality of video cameras respectively, and respectively being in an approximately perpendicular relationship with optic axes of camera lenses of the plurality of video cameras.

Abstract translation: 一种远程呈现系统，包括：多个显示器，被配置为显示远程图像; 音频输出装置，被配置为输出远程音频信息; 多媒体通信终端，被配置为处理和控制由本端获得的音频/视频信息和由远程端发送的音频/视频信息; 多个摄像机，被配置为拍摄本地视频图像并将拍摄的视频图像发送到待处理的多媒体通信终端; 音频收集装置，被配置为收集本地音频信息，并将收集的音频信息发送到多媒体通信终端; 以及分别对应于所述多个摄像机的多个用户位置，并且分别与所述多个摄像机的相机透镜的光轴成大致垂直的关系。

公开(公告)号：US20110316963A1

公开(公告)日：2011-12-29

申请号：US13172193

申请日：2011-06-29

Applicant: Kai LI ,  Yuan LIU ,  Jing WANG ,  Honghong SU ,  Song ZHAO

Inventor： Kai LI ,  Yuan LIU ,  Jing WANG ,  Honghong SU ,  Song ZHAO

IPC: H04N7/14 ,  H04N13/02

CPC classification number: H04N21/4223 ,  H04N7/15 ,  H04N13/243 ,  H04N21/42203 ,  H04N21/4788

Abstract: A method and a device for generating 3-dimensional (3D) panoramic video streams, a videoconference method, and a videoconference device are disclosed. The method includes: obtaining depth information of at least two video images; obtaining image data in multiple depth positions from a corresponding video image according to the depth information of each video image; stitching data of the video images according to the obtained image data in multiple depth positions, and generating 3D panoramic video streams. The technical solution of the present invention provides users with high-resolution 3D panoramic seamless telepresence conference video images based on different display modes of different display devices.

Abstract translation: 公开了一种用于产生三维（3D）全景视频流的方法和装置，视频会议方法和视频会议装置。 该方法包括：获取至少两个视频图像的深度信息; 根据每个视频图像的深度信息从相应的视频图像获得多个深度位置的图像数据; 根据所获得的多个深度位置的图像数据拼接视频图像的数据，并生成3D全景视频流。 本发明的技术方案为用户提供了基于不同显示设备的不同显示模式的高分辨率3D全景无线远程呈现会议视频图像。

公开(公告)号：US20110229017A1

公开(公告)日：2011-09-22

申请号：US13005062

申请日：2011-01-12

Applicant: Yuan LIU ,  Tao LI ,  Yinghui XU ,  Yi CHEN ,  Lei ZHANG

Inventor： Yuan LIU ,  Tao LI ,  Yinghui XU ,  Yi CHEN ,  Lei ZHANG

IPC: G06K9/62 ,  G06K9/46 ,  G06K9/00

CPC classification number: G06F17/30038 ,  G06F17/30256

Abstract: Disclosed are a method and a system for adding annotations into an input medium file. The method comprises a step of creating annotation detection models based on training samples formed by existing media files having annotations; a step of extracting coexistence coefficients of any two annotations based on appearance frequencies of the annotations in the training samples; a step of inputting the input medium file; a step of extracting sense-of-vision features from the input medium file; a step of obtaining initial annotations of the input medium file; a step of acquiring candidate annotations based on the initial annotations and the coexistence coefficients of the annotations in the training samples; and a step of selecting a final annotation set from the candidate annotations based on the sense-of-vision features of the input medium file and the coexistence coefficients by using the annotation detection models.

Abstract translation: 公开了一种用于将注释添加到输入介质文件中的方法和系统。 该方法包括基于由具有注释的现有媒体文件形成的训练样本来创建注释检测模型的步骤; 基于训练样本中注释的出现频率，提取任意两个注释的共存系数的步骤; 输入输入媒体文件的步骤; 从输入介质文件中提取感觉视觉特征的步骤; 获取输入媒体文件的初始注释的步骤; 基于训练样本中注释的初始注释和共存系数获取候选注释的步骤; 以及通过使用注释检测模型，基于输入介质文件的视觉特征和共存系数从候选注释中选择最终注释集的步骤。

公开(公告)号：US20100329543A1

公开(公告)日：2010-12-30

申请号：US12874468

申请日：2010-09-02

Applicant: Kai LI ,  Jing WANG ,  Yuan LIU ,  Ping FANG

Inventor： Kai LI ,  Jing WANG ,  Yuan LIU ,  Ping FANG

IPC: G06T7/00

CPC classification number: G06T5/006 ,  G06T3/0068 ,  G06T2207/10012

Abstract: The present invention relates to a method and a system for rectifying images. An original stereo image pair is obtained, and the epipolar lines corresponding to the original stereo image pair are parallelized to obtain a first transformed stereo image pair. Epipolar lines corresponding to the first transformed stereo image pair are collinearized to obtain a second transformed stereo image pair. The present invention parallelizes and collinearizes the epipolar lines corresponding to the stereo image pair after the images are rectified.

Abstract translation: 本发明涉及一种整流图像的方法和系统。 获得原始立体图像对，并且对应于原始立体图像对的对极线被并行以获得第一变换立体图像对。 对应于第一变换立体图像对的对极线共线以获得第二变换立体图像对。 本发明在对图像进行整流之后，对应于立体图像对的对极线并行化并共线。

公开(公告)号：US20080304454A1

公开(公告)日：2008-12-11

申请号：US12193594

申请日：2008-08-18

Applicant: Hui ZHONG ,  Shu WANG ,  Yuan LIU

Inventor： Hui ZHONG ,  Shu WANG ,  Yuan LIU

IPC: H04Q7/00

CPC classification number: H04W36/0011 ,  H04W36/14 ,  H04W36/36

Abstract: A heterogeneous network includes a terminal side and a network side. The network side includes an original PoA and handover candidate PoAs. The terminal side is used to select the handover candidate PoAs, initiate a media independent handover request, terminate a connection with the original PoA, and establish a connection with the handover candidate PoAs. The original PoA is used to terminate the connection with the terminal side according to the media independent handover request initiated by the terminal side. The handover candidate PoAs is used to establish the connection with the terminal side according to the media independent handover request initiated by the terminal side. A method for handover between heterogeneous networks initiated by the terminal side and the network side based on the 802.21 architecture is also provided, which improves the processing of the handover process.

Abstract translation: 异构网络包括终端侧和网络侧。 网络侧包括原始PoA和切换候选PoA。 终端侧用于选择切换候选PoA，发起与媒体无关的切换请求，终止与原始PoA的连接，并建立与切换候选PoA的连接。 根据由终端侧发起的媒体独立切换请求，原始PoA用于终止与终端侧的连接。 切换候选PoA用于根据由终端侧发起的媒体独立切换请求来建立与终端侧的连接。 还提供了一种基于802.21架构由终端侧和网络侧发起的异构网络之间切换的方法，其改进了切换过程的处理。

公开(公告)号：US20120120185A1

公开(公告)日：2012-05-17

申请号：US13355019

申请日：2012-01-20

Applicant: Guangyao ZHAO ,  Jing WANG ,  Yuan LIU ,  Jinyong MA

Inventor： Guangyao ZHAO ,  Jing WANG ,  Yuan LIU ,  Jinyong MA

IPC: H04N7/14

CPC classification number: H04N7/144 ,  H04N7/157

Abstract: The present invention relates to the communications field and discloses a video communication method, apparatus, and system, which are invented to solve the problem that the prior art does not achieve consistent eye-to-eye video communication in a horizontal direction. The technical solutions of the present invention includes: obtaining video images of a participant from more than two different horizontal shooting angles, where a range of viewing angles of the participant is between the more than two different horizontal shooting angles; and sending the video images of the participant to a video communication remote end. The embodiments of the present invention may be applied in the video communication field.

Abstract translation: 本发明涉及通信领域，并且公开了一种视频通信方法，装置和系统，其被发明以解决现有技术在水平方向上不能实现一致的眼睛视频通信的问题。 本发明的技术方案包括：从多于两个不同的水平拍摄角度获得参与者的视频图像，其中参与者的视角范围在两个以上不同的水平拍摄角度之间; 并将参与者的视频图像发送到视频通信远程端。 本发明的实施例可以应用于视频通信领域。