专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明申请

US20120050464A1 METHOD AND SYSTEM FOR ENHANCING 3D EFFECTS FOR 3D VIDEO RENDERING 有权
标题翻译：用于增强3D影像渲染效果的方法和系统
公开(公告)号：US20120050464A1
公开(公告)日：2012-03-01
申请号：US13077926
申请日：2011-03-31
申请人： Xuemin Chen , Nambi Seshadri , Jeyhan Karaoguz , Chris Boross
发明人： Xuemin Chen , Nambi Seshadri , Jeyhan Karaoguz , Chris Boross
IPC分类号： H04N13/00
CPC分类号： G06T19/20 , G06T15/205 , G06T2219/2016 , H04N13/122
摘要： A three-dimensional (3D) video rendering device monitors 3D effects associated with an object in a received 3D video image-by-image. The object may be re-located to a preferred location to adjust the associated 3D effects. Two-dimensional (2D) image data and corresponding depth information for the object at the current location are interpolated to the preferred location. A location difference and lighting condition changes corresponding to the re-location of the object are calculated to determine a view angle and lighting conditions for the object at the preferred location. 2D image data and depth information for the object at the preferred location are estimated based on the determined view angle and the determined lighting conditions for the object at the preferred location. The estimated 2D image data and the estimated corresponding depth information may be applied to the object at the preferred location to enhance the associated 3D effects for 3D video rendering.
摘要翻译：三维（3D）视频呈现设备监视与所接收的3D视频图像中的对象相关联的3D效果。可以将对象重新定位到优选位置以调整相关联的3D效果。将二维（2D）图像数据和当前位置处的对象的相应深度信息内插到优选位置。计算与对象的重新定位对应的位置差和照明条件变化，以确定在优选位置处的对象的视角和照明条件。基于所确定的视角和在优选位置处的对象的确定的照明条件来估计在优选位置处的对象的2D图像数据和深度信息。可以将估计的2D图像数据和估计的相应深度信息应用于优选位置处的对象，以增强用于3D视频呈现的相关3D效果。

12. 发明授权

US09071831B2 Method and system for noise cancellation and audio enhancement based on captured depth information 有权
标题翻译：基于捕获深度信息的噪声消除和音频增强方法和系统
公开(公告)号：US09071831B2
公开(公告)日：2015-06-30
申请号：US13174370
申请日：2011-06-30
申请人： Nambi Seshadri , Jeyhan Karaoguz , Chris Boross , Xuemin Chen
发明人： Nambi Seshadri , Jeyhan Karaoguz , Chris Boross , Xuemin Chen
IPC分类号： H04N5/232 , H04N5/217 , H04N13/02 , H04N5/357 , H04N13/00
CPC分类号： H03G3/20 , H04N5/23229 , H04N5/357 , H04N13/122 , H04N13/25 , H04N13/261 , H04R1/08 , H04R2499/11
摘要： A monoscopic camera comprising one or more image sensors and a depth sensor may generate video based on two-dimensional image data captured via the one or more image sensors and corresponding depth information captured via the depth sensor. The camera may process corresponding audio for the generated video based on the captured depth information. The audio processing may comprise mitigating noise in the corresponding audio, enhancing voice quality in the corresponding audio, and/or enhancing audio quality of the corresponding audio. The camera may be operable to determine, based on the captured depth information, one or more sound paths between a source of the corresponding audio and a microphone utilized to capture the corresponding audio emanating from the source. The processing of the audio may comprise removing portions of the captured audio arriving at the microphone via one or more reflection paths.
摘要翻译：包括一个或多个图像传感器和深度传感器的单视镜相机可以基于经由一个或多个图像传感器捕获的二维图像数据和经由深度传感器捕获的相应深度信息来生成视频。相机可以基于捕获的深度信息处理所生成的视频的相应音频。音频处理可以包括减轻相应音频中的噪声，增强相应音频中的语音质量和/或增强对应音频的音频质量。摄像机可操作以基于所捕获的深度信息来确定相应音频的源和用于捕获从源发出的对应音频的麦克风之间的一个或多个声音路径。音频的处理可以包括经由一个或多个反射路径去除到达麦克风的捕获音频的部分。

13. 发明授权

US08810565B2 Method and system for utilizing depth information as an enhancement layer 有权
标题翻译：利用深度信息作为增强层的方法和系统
公开(公告)号：US08810565B2
公开(公告)日：2014-08-19
申请号：US13077868
申请日：2011-03-31
申请人： Jeyhan Karaoguz , Nambi Seshadri , Xuemin Chen , Chris Boross
发明人： Jeyhan Karaoguz , Nambi Seshadri , Xuemin Chen , Chris Boross
IPC分类号： G06T15/00 , G06T15/10
CPC分类号： H04N13/161 , H04N13/189 , H04N13/271 , H04N2213/003
摘要： A monoscopic 3D video generation device, which comprises one or more depth sensors, may be operable to store captured 2D video image data as a base layer and store captured corresponding depth information separately as an enhancement layer. The 2D video image data may be captured via one or more image sensors and the corresponding depth information may be captured via the one or more depth sensors in the monoscopic 3D video generation device. The monoscopic 3D video generation device may determine whether to transmit the enhancement layer to a video rendering device. The monoscopic 3D video generation device may encode the base layer. The monoscopic 3D video generation device may encode the enhancement layer based on the determination of transmitting the enhancement layer. The encoded base layer and/or the encoded enhancement layer may be transmitted to the video rendering device for 3D video rendering and/or 2D video rendering.
摘要翻译：包括一个或多个深度传感器的单视三维视频生成装置可以用于将拍摄的2D视频图像数据存储为基本层，并将所捕获的相应深度信息分别存储为增强层。可以经由一个或多个图像传感器捕获2D视频图像数据，并且可以经由单视场3D视频生成装置中的一个或多个深度传感器捕获相应的深度信息。单视三维视频生成设备可以确定是否将增强层发送到视频呈现设备。单视三维视频生成设备可以对基础层进行编码。单视三维视频生成设备可以基于传送增强层的确定来对增强层进行编码。编码的基础层和/或经编码的增强层可以被传输到视频呈现设备以用于3D视频呈现和/或2D视频呈现。

14. 发明申请

US20120050582A1 METHOD AND SYSTEM FOR NOISE CANCELLATION AND AUDIO ENHANCEMENT BASED ON CAPTURED DEPTH INFORMATION 有权
标题翻译：基于受影响的深度信息的噪声消除和音频增强的方法和系统
公开(公告)号：US20120050582A1
公开(公告)日：2012-03-01
申请号：US13174370
申请日：2011-06-30
申请人： Nambi Seshadri , Jeyhan Karaoguz , Chris Boross , Xuemin Chen
发明人： Nambi Seshadri , Jeyhan Karaoguz , Chris Boross , Xuemin Chen
IPC分类号： H04N5/217 , H04N5/228
CPC分类号： H03G3/20 , H04N5/23229 , H04N5/357 , H04N13/122 , H04N13/25 , H04N13/261 , H04R1/08 , H04R2499/11
摘要： A monoscopic camera comprising one or more image sensors and a depth sensor may generate video based on two-dimensional image data captured via the one or more image sensors and corresponding depth information captured via the depth sensor. The camera may process corresponding audio for the generated video based on the captured depth information. The audio processing may comprise mitigating noise in the corresponding audio, enhancing voice quality in the corresponding audio, and/or enhancing audio quality of the corresponding audio. The camera may be operable to determine, based on the captured depth information, one or more sound paths between a source of the corresponding audio and a microphone utilized to capture the corresponding audio emanating from the source. The processing of the audio may comprise removing portions of the captured audio arriving at the microphone via one or more reflection paths.
摘要翻译：包括一个或多个图像传感器和深度传感器的单视镜相机可以基于经由一个或多个图像传感器捕获的二维图像数据和经由深度传感器捕获的相应深度信息来生成视频。相机可以基于捕获的深度信息处理所生成的视频的相应音频。音频处理可以包括减轻相应音频中的噪声，增强相应音频中的语音质量和/或增强对应音频的音频质量。摄像机可操作以基于所捕获的深度信息来确定相应音频的源和用于捕获从源发出的对应音频的麦克风之间的一个或多个声音路径。音频的处理可以包括经由一个或多个反射路径去除到达麦克风的捕获音频的部分。

15. 发明申请

US20120050491A1 METHOD AND SYSTEM FOR ADJUSTING AUDIO BASED ON CAPTURED DEPTH INFORMATION 审中-公开
标题翻译：基于受影响的深度信息调整音频的方法和系统
公开(公告)号：US20120050491A1
公开(公告)日：2012-03-01
申请号：US13174344
申请日：2011-06-30
申请人： Nambi Seshadri , Jeyhan Karaoguz , Xuemin Chen , Chris Boross
发明人： Nambi Seshadri , Jeyhan Karaoguz , Xuemin Chen , Chris Boross
IPC分类号： H04N13/02
CPC分类号： H04N13/25 , H04N13/271
摘要： Two-dimensional image may be captured via one or more image sensors of a monoscopic camera and depth information may be captured via one or more depth sensors of the monoscopic camera. A video stream may be generated from the captured two-dimensional image data based on the captured depth information. Corresponding audio to accompany the generated video stream may be generated based on the captured depth information. The generated video stream may be a 3-D video stream. The generated corresponding audio may be adjusted based on the captured depth information. A location and/or movement of an object appearing in the captured two-dimensional image data may be determined based on the depth information and based on pixel data of the captured two-dimensional image data. Characteristics of the generated audio, such as volume, frequency, delay, and balance, may be adjusted based on the determined location and/or movement.
摘要翻译：可以通过单视镜相机的一个或多个图像传感器捕获二维图像，并且可以通过单视镜相机的一个或多个深度传感器捕获深度信息。可以基于所捕获的深度信息从所捕获的二维图像数据生成视频流。可以基于捕获的深度信息生成伴随所生成的视频流的相应音频。所生成的视频流可以是3-D视频流。可以基于所捕获的深度信息来调整所生成的对应音频。出现在拍摄的二维图像数据中的对象的位置和/或移动可以基于深度信息并且基于所捕获的二维图像数据的像素数据来确定。可以基于确定的位置和/或移动来调整生成的音频的特性，例如音量，频率，延迟和平衡。

16. 发明申请

US20120050481A1 METHOD AND SYSTEM FOR CREATING A 3D VIDEO FROM A MONOSCOPIC 2D VIDEO AND CORRESPONDING DEPTH INFORMATION 有权
标题翻译：用于从单视二维视频和相关深度信息创建3D视频的方法和系统
公开(公告)号：US20120050481A1
公开(公告)日：2012-03-01
申请号：US13077912
申请日：2011-03-31
申请人： Xuemin Chen , Nambi Seshadri , Jeyhan Karaoguz , Chris Boross
发明人： Xuemin Chen , Nambi Seshadri , Jeyhan Karaoguz , Chris Boross
IPC分类号： H04N13/02
CPC分类号： H04N13/261 , H04N13/178 , H04N13/271 , H04N19/115 , H04N19/167 , H04N19/33 , H04N19/597
摘要： Image sensors and a depth sensor of a monoscopic video sensing device are utilized to capture a 2D video and corresponding depth information. Regions of interest (ROIs) for the captured 2D video are selected based on the captured corresponding depth information. The monoscopic video sensing device selectively processes the captured 2D video and the captured corresponding depth information based on the selected ROIs. A 3D video is composed from the processed 2D video for display. The captured depth information that is synchronized to the captured 2D video is stored as metadata, and may be interpolated to match video resolution of the captured 2D video. The captured 2D video and the captured corresponding depth information are enhanced through scalable video coding. With 3D video rendering, relevant image/video components of the captured 2D video are selected based on the selected ROIs to compose the 3D video together with the corresponding depth information.
摘要翻译：图像传感器和单视频感测装置的深度传感器被用于捕获2D视频和相应的深度信息。基于所捕获的相应深度信息来选择所捕获的2D视频的感兴趣区域（ROI）。单视视频感测装置基于所选择的ROI选择性地处理所捕获的2D视频和捕获的相应的深度信息。 3D视频由处理的2D视频组成，用于显示。与拍摄的2D视频同步的拍摄深度信息被存储为元数据，并且可以被内插以匹配所捕获的2D视频的视频分辨率。捕获的2D视频和捕获的相应的深度信息通过可扩展视频编码而增强。利用3D视频呈现，基于所选择的ROI选择所捕获的2D视频的相关图像/视频分量，以组合3D视频以及相应的深度信息。

17. 发明申请

US20120050480A1 METHOD AND SYSTEM FOR GENERATING THREE-DIMENSIONAL VIDEO UTILIZING A MONOSCOPIC CAMERA 审中-公开
标题翻译：用于生成使用单一摄像机的三维视频的方法和系统
公开(公告)号：US20120050480A1
公开(公告)日：2012-03-01
申请号：US13077900
申请日：2011-03-31
申请人： Nambi Seshadri , Jeyhan Karaoguz , Xuemin Chen , Chris Boross
发明人： Nambi Seshadri , Jeyhan Karaoguz , Xuemin Chen , Chris Boross
IPC分类号： H04N13/02
CPC分类号： H04N13/25 , H04N13/271
摘要： Aspects of a method and system for generating three-dimensional video utilizing a monoscopic camera are provided. A monoscopic camera may comprise one or more image sensors and one or more depth sensors. Two-dimensional image data may be captured via the image sensor(s) and depth information may be captured via the depth sensor(s). The depth sensor may utilize infrared waves transmitted by an emitter of the monoscopic camera. The monoscopic camera may be operable to utilize the captured depth information to generate a three-dimensional video stream from the captured two-dimensional image data. The monoscopic camera may be operable to synchronize the captured depth information with the captured two-dimensional image data. The monoscopic camera may be operable to generate a two-dimensional video stream from the captured two-dimensional image data. The monoscopic camera may be configurable to output the two-dimensional video stream and/or the three-dimensional video stream.
摘要翻译：提供了使用单视镜摄像机产生三维视频的方法和系统的方面。单视镜相机可以包括一个或多个图像传感器和一个或多个深度传感器。可以经由图像传感器捕获二维图像数据，并且可以经由深度传感器捕获深度信息。深度传感器可以利用由单视镜相机的发射器传输的红外波。单视镜相机可操作以利用所捕获的深度信息从捕获的二维图像数据生成三维视频流。单视摄像机可以可操作以将捕获的深度信息与所捕获的二维图像数据同步。单视镜相机可以用于从捕获的二维图像数据生成二维视频流。单视镜相机可以被配置为输出二维视频流和/或三维视频流。

18. 发明申请

US20120050264A1 Method and System for Utilizing Depth Information as an Enhancement Layer 有权
标题翻译：利用深度信息作为增强层的方法和系统
公开(公告)号：US20120050264A1
公开(公告)日：2012-03-01
申请号：US13077868
申请日：2011-03-31
申请人： Jeyhan Karaoguz , Nambi Seshadri , Xuemin Chen , Chris Boross
发明人： Jeyhan Karaoguz , Nambi Seshadri , Xuemin Chen , Chris Boross
IPC分类号： G06T15/00
CPC分类号： H04N13/161 , H04N13/189 , H04N13/271 , H04N2213/003
摘要： A monoscopic 3D video generation device, which comprises one or more depth sensors, may be operable to store captured 2D video image data as a base layer and store captured corresponding depth information separately as an enhancement layer. The 2D video image data may be captured via one or more image sensors and the corresponding depth information may be captured via the one or more depth sensors in the monoscopic 3D video generation device. The monoscopic 3D video generation device may determine whether to transmit the enhancement layer to a video rendering device. The monoscopic 3D video generation device may encode the base layer. The monoscopic 3D video generation device may encode the enhancement layer based on the determination of transmitting the enhancement layer. The encoded base layer and/or the encoded enhancement layer may be transmitted to the video rendering device for 3D video rendering and/or 2D video rendering.
摘要翻译：包括一个或多个深度传感器的单视三维视频生成装置可以用于将拍摄的2D视频图像数据存储为基本层，并将所捕获的相应深度信息分别存储为增强层。可以经由一个或多个图像传感器捕获2D视频图像数据，并且可以经由单视场3D视频生成装置中的一个或多个深度传感器捕获相应的深度信息。单视三维视频生成设备可以确定是否将增强层发送到视频呈现设备。单视三维视频生成设备可以对基础层进行编码。单视三维视频生成设备可以基于传送增强层的确定来对增强层进行编码。编码的基础层和/或经编码的增强层可以被传输到视频呈现设备以用于3D视频呈现和/或2D视频呈现。

19. 发明申请

US20120050484A1 METHOD AND SYSTEM FOR UTILIZING IMAGE SENSOR PIPELINE (ISP) FOR ENHANCING COLOR OF THE 3D IMAGE UTILIZING Z-DEPTH INFORMATION 有权
标题翻译：使用图像传感器管道（ISP）的方法和系统，用于增强使用Z深度信息的3D图像的颜色
公开(公告)号：US20120050484A1
公开(公告)日：2012-03-01
申请号：US13174430
申请日：2011-06-30
申请人： Chris Boross , Nambirajan Seshadri , Jeyhan Karaoguz , Xuemin Chen
发明人： Chris Boross , Nambirajan Seshadri , Jeyhan Karaoguz , Xuemin Chen
IPC分类号： H04N13/02
CPC分类号： H04N13/25 , H04N13/122 , H04N13/261 , H04N13/271
摘要： A monoscopic video camera may capture, via at least one image sensor, two-dimensional video, and may capture, via at least one depth sensor, corresponding depth information for the captured two-dimensional video. The monoscopic video camera may then configure color related processing of video information corresponding to objects in the captured 2D video based on the captured corresponding depth information. Configuring color processing may comprise setting and/or adjusting color information associated with the objects. In this regard, setting and/or adjusting color information may be based on shadow, shade, and/or edge related information associated with the objects, which may be generated and/or modified based on the captured corresponding depth information based on the captured corresponding depth information. Configuring color processing may be based on surrounding regions adjacent to the objects. The surrounding regions adjacent to the objects may be determined based on the captured corresponding depth information.
摘要翻译：单视摄像机可以经由至少一个图像传感器捕获二维视频，并且可以经由至少一个深度传感器捕获用于所捕获的二维视频的对应深度信息。然后，单视域摄像机可以基于所捕获的相应深度信息来配置与所捕获的2D视频中的对象相对应的视频信息的颜色相关处理。配置颜色处理可以包括设置和/或调整与对象相关联的颜色信息。在这方面，设置和/或调整颜色信息可以基于与对象相关联的阴影，阴影和/或边缘相关信息，其可以基于所捕获的相应深度信息基于所捕获的对应物来生成和/或修改深度信息。配置颜色处理可以基于与对象相邻的周围区域。可以基于捕获的相应深度信息来确定与对象相邻的周围区域。

20. 发明申请

US20120050483A1 METHOD AND SYSTEM FOR UTILIZING AN IMAGE SENSOR PIPELINE (ISP) FOR 3D IMAGING PROCESSING UTILIZING Z-DEPTH INFORMATION 审中-公开
标题翻译：使用图像传感器管道（ISP）进行三维成像处理的方法和系统，利用Z深度信息
公开(公告)号：US20120050483A1
公开(公告)日：2012-03-01
申请号：US13174364
申请日：2011-06-30
申请人： Chris Boross , Nambirajan Seshadri , Jeyhan Karaoguz , Xuemin Chen
发明人： Chris Boross , Nambirajan Seshadri , Jeyhan Karaoguz , Xuemin Chen
IPC分类号： H04N13/02
CPC分类号： H04N13/25 , H04N13/122 , H04N13/261 , H04N13/271
摘要： A monoscopic video camera may capture, via at least one image sensor, two-dimensional video, and may capture, via at least one depth sensor, corresponding depth information for the captured two-dimensional video. The monoscopic video camera may then detect and/or track objects in the captured two-dimensional video based on the captured corresponding depth information; and processing of image related information corresponding to the objects may be configured based on the detecting and/or tracking of the objects. Type and/or characteristics of each of the objects may be determined during the detecting and/or tracking. Identification of the type and/or characteristics of the objects may be performed based on one or more object recognition algorithms programmed into the monoscopic video camera. Configuration of processing of object image related information may be performed based on preset criteria and/or parameters associated with identified types and/or characteristics of the objects.
摘要翻译：单视摄像机可以经由至少一个图像传感器捕获二维视频，并且可以经由至少一个深度传感器捕获用于所捕获的二维视频的对应深度信息。然后，单视视频摄像机可以基于所捕获的对应深度信息来检测和/或跟踪所捕获的二维视频中的对象; 并且可以基于对象的检测和/或跟踪来配置与对象相对应的图像相关信息的处理。可以在检测和/或跟踪期间确定每个对象的类型和/或特征。可以基于编程到单视频摄像机中的一个或多个对象识别算法来执行对象的类型和/或特征的识别。可以基于与标识的类型和/或对象的特征相关联的预设标准和/或参数来执行对象图像相关信息的处理的配置。

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