专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US10133947B2 Object detection using location data and scale space representations of image data 有权
公开(公告)号：US10133947B2
公开(公告)日：2018-11-20
申请号：US14598892
申请日：2015-01-16
申请人： QUALCOMM Incorporated
发明人： Ruiduo Yang , Ning Bi , Sichao Yang , Xinzhou Wu , Feng Guo , Jianfeng Ren
IPC分类号： G06K9/00 , G06K9/20 , G06K9/32 , G06K9/42 , G06K9/68
摘要： An apparatus includes an object detector configured to receive image data of a scene viewed from the apparatus and including an object. The image data is associated with multiple scale space representations of the scene. The object detector is configured to detect the object responsive to location data and a first scale space representation of the multiple scale space representations.

2. 发明申请

US20170053167A1 SYSTEMS AND METHODS FOR OBJECT TRACKING 审中-公开
标题翻译：用于对象跟踪的系统和方法
公开(公告)号：US20170053167A1
公开(公告)日：2017-02-23
申请号：US14829406
申请日：2015-08-18
申请人： QUALCOMM Incorporated
发明人： Jianfeng Ren , Feng Guo , Ruiduo Yang
IPC分类号： G06K9/00 , G06T3/40 , G06K9/46
摘要： A method performed by an electronic device is described. The method includes obtaining a first frame of a scene. The method also includes performing object recognition of at least one object within a first bounding region of the first frame. The method further includes performing object tracking of the at least one object within the first bounding region of the first frame. The method additionally includes determining a second bounding region of a second frame based on the object tracking. The second frame is subsequent to the first frame. The method also includes determining whether the second bounding region is valid based on a predetermined object model.
摘要翻译：描述由电子设备执行的方法。该方法包括获得场景的第一帧。该方法还包括对第一帧的第一边界区域内的至少一个对象执行对象识别。所述方法还包括对所述第一帧的所述第一边界区域内的所述至少一个对象进行对象跟踪。该方法还包括基于对象跟踪来确定第二帧的第二边界区域。第二帧在第一帧之后。该方法还包括基于预定对象模型确定第二边界区域是否有效。

3. 发明授权

US11509837B2 Camera transition blending 有权
公开(公告)号：US11509837B2
公开(公告)日：2022-11-22
申请号：US17009285
申请日：2020-09-01
申请人： QUALCOMM Incorporated
发明人： Weiliang Liu , Shizhong Liu , Tao Ma , Jianfeng Ren
IPC分类号： H04N5/265 , G06T3/00 , H04N5/232 , H04N5/247
摘要： In general, techniques are described regarding initiating a recursive blending of a plurality of frames following a camera transition. One or more processors may, subsequent to a transition from a first camera mode to a second camera mode, blend one or more pixels of a first frame with one or more pixels of a second frame to produce a first blended frame, the first frame captured via a first camera, and the second frame captured via a second camera. The one or more processors may then output the first blended frame.

4. 发明申请

US20170161569A1 SYSTEM AND METHOD OF OBJECT DETECTION 有权
公开(公告)号：US20170161569A1
公开(公告)日：2017-06-08
申请号：US14837606
申请日：2015-08-27
申请人： QUALCOMM Incorporated
发明人： Jianfeng Ren , Ruiduo Yang , Feng Guo , Shili Xu , Shuxue Quan , Ning Bi
IPC分类号： G06K9/00 , G08G1/16 , G06K9/32
CPC分类号： G06K9/00798 , B60T7/22 , G06K9/00818 , G06K9/3233 , G06K9/325 , G08G1/16
摘要： A system and method of object detection are disclosed. In a particular implementation, a method of processing an image includes receiving, at a processor, image data associated with an image of a scene. The scene includes a road region. The method further includes detecting the road region based on the image data and determining a subset of the image data. The subset excludes at least a portion of the image data corresponding to the road region. The method further includes performing an object detection operation on the subset of the image data to detect an object. The object detection operation performed on the subset of the image data is exclusive of the at least a portion of the image data corresponding to the road region.

5. 发明授权

US09348560B2 Efficient execution of graph-based programs 有权
标题翻译：有效执行基于图表的程序
公开(公告)号：US09348560B2
公开(公告)日：2016-05-24
申请号：US14106539
申请日：2013-12-13
申请人： QUALCOMM Incorporated
发明人： Binglong Xie , Shuxue Quan , Ning Bi , Jianfeng Ren , Lei Xu , Ananthapadmanabhan Arasanipalai Kandhadai
IPC分类号： G06F9/44 , G06F9/50 , G06F9/45
CPC分类号： G06F8/34 , G06F8/451 , G06F9/50 , G06F9/5044 , Y02D10/22
摘要： A method includes accessing, at a computing device, data descriptive of a graph representing a program. The graph includes multiple nodes representing execution steps of the program and includes multiple edges representing data transfer steps. The method also includes determining at least two heterogeneous hardware resources of the computing device that are available to execute code represented by one or more of the nodes, and determining one or more paths from a source node to a sink node based on a topology of the graph. The method further includes scheduling execution of code at the at least two heterogeneous hardware resources. The code is represented by at least one of the multiple nodes, and the execution of the code is scheduled based on the one or more paths.
摘要翻译：一种方法包括在计算设备处访问描述代表节目的图形的数据。该图包括表示程序的执行步骤的多个节点，并且包括表示数据传送步骤的多个边。该方法还包括确定可用于执行由一个或多个节点表示的代码的计算设备的至少两个异构硬件资源，以及基于所述节点的拓扑来确定从源节点到汇聚节点的一个或多个路径图形。该方法还包括在至少两个异构硬件资源上调度代码的执行。代码由多个节点中的至少一个表示，并且基于一个或多个路径调度代码的执行。

6. 发明申请

US20220292630A1 TRANSFORM MATRIX LEARNING FOR MULTI-SENSOR IMAGE CAPTURE DEVICES 有权
公开(公告)号：US20220292630A1
公开(公告)日：2022-09-15
申请号：US17201660
申请日：2021-03-15
申请人： QUALCOMM Incorporated
发明人： Shizhong Liu , Jincheng Huang , Weiliang Liu , Jianfeng Ren , Sahul Madanayakanahalli Phaniraj Venkatesh
IPC分类号： G06T3/00 , G06T7/571 , G06T7/521 , H04N5/247 , H04N5/268 , G06T5/50
摘要： Artefacts in a sequence of image frames may be reduced or eliminated through modification of an input image frame to match another image frame in the sequence, such as by geometrically warping to generate a corrected image frame with a field of view matched to another frame in sequence of frames with the image frame. The warping may be performed based on a model generated from data regarding the multi-sensor device. The disparity between image frames may be modeled based on image captures from the first and second image sensor for scenes at varying depths. The model may be used to predict disparity values for captured images, and those predicted disparity values used to reduce artefacts resulting from image sensor switching. The predicted disparity values may be used in image conditions resulting in erroneous actual disparity values.

7. 发明申请

US20220150420A1 SPATIAL ALIGNMENT TRANSFORM WITHOUT FOV LOSS 有权
公开(公告)号：US20220150420A1
公开(公告)日：2022-05-12
申请号：US17094052
申请日：2020-11-10
申请人： QUALCOMM Incorporated
发明人： Jianfeng Ren , Shizhong Liu , Weiliang Liu , Kuan-Chen Pan , Nikhil Uchil , Wei Zou
IPC分类号： H04N5/262 , G06T3/00 , H04N5/232 , H04N5/225
摘要： This disclosure provides devices, methods, computer-readable medium, and means for spatial alignment transform. In some aspects, a device may perform operations including capturing a first image of a scene using a first sensor at a first zoom ratio, capturing a second image of the scene using a second sensor at a second zoom ratio, the first image having a different field-of-view (FOV) than the second image, determining a translation matrix based on one or more spatial misalignments between the first image and the second image, determining a confidence associated with the translation matrix, in response to the confidence being greater than a confidence threshold, determining a weighting factor based on the first zoom ratio, the second zoom ratio, and a current zoom ratio of the device, applying the weighting factor to the translation matrix, and warping the first image to the second image using the weighted translation matrix.

8. 发明申请

US20210360172A1 CAMERA TRANSITION BLENDING 有权
公开(公告)号：US20210360172A1
公开(公告)日：2021-11-18
申请号：US17009285
申请日：2020-09-01
申请人： QUALCOMM Incorporated
发明人： Weiliang Liu , Shizhong Liu , Tao Ma , Jianfeng Ren
IPC分类号： H04N5/265 , G06T3/00 , H04N5/232
摘要： In general, techniques are described regarding initiating a recursive blending of a plurality of frames following a camera transition. One or more processors may, subsequent to a transition from a first camera mode to a second camera mode, blend one or more pixels of a first frame with one or more pixels of a second frame to produce a first blended frame, the first frame captured via a first camera, and the second frame captured via a second camera. The one or more processors may then output the first blended frame.

9. 发明申请

US20170310972A1 METHODS AND SYSTEMS OF GENERATING A BACKGROUND PICTURE FOR VIDEO CODING 审中-公开
公开(公告)号：US20170310972A1
公开(公告)日：2017-10-26
申请号：US15134183
申请日：2016-04-20
申请人： QUALCOMM Incorporated
发明人： Lei Wang , Ying Chen , Ning Bi , Xuerui Zhang , Lei Ma , Chinchuan Chiu , Jianfeng Ren
IPC分类号： H04N19/159 , H04N19/182 , H04N19/172 , H04N19/58 , H04N19/105
CPC分类号： H04N19/159 , G06T7/254 , H04N19/105 , H04N19/172 , H04N19/182 , H04N19/23 , H04N19/58
摘要： Techniques and systems are provided for generating a background picture. The background picture can be used for coding one or more pictures. For example, a method of generating a background picture includes generating a long-term background model for one or more pixels of a background picture. The long-term background model includes a statistical model for detecting long-term motion of the one or more pixels in a sequence of pictures. The method further includes generating a short-term background model for the one or more pixels of the background picture. The short-term background model detects short-term motion of the one or more pixels between two or more pictures. The method further includes determining a value for the one or more pixels of the background picture using the long-term background model and the short-term background model.

10. 发明授权

US11405563B2 Spatial alignment transform without FOV loss 有权
公开(公告)号：US11405563B2
公开(公告)日：2022-08-02
申请号：US17094052
申请日：2020-11-10
申请人： QUALCOMM Incorporated
发明人： Jianfeng Ren , Shizhong Liu , Weiliang Liu , Kuan-Chen Pan , Nikhil Uchil , Wei Zou
IPC分类号： H04N5/262 , H04N5/225 , H04N5/232 , G06T3/00
摘要： This disclosure provides devices, methods, computer-readable medium, and means for spatial alignment transform. In some aspects, a device may perform operations including capturing a first image of a scene using a first sensor at a first zoom ratio, capturing a second image of the scene using a second sensor at a second zoom ratio, the first image having a different field-of-view (FOV) than the second image, determining a translation matrix based on one or more spatial misalignments between the first image and the second image, determining a confidence associated with the translation matrix, in response to the confidence being greater than a confidence threshold, determining a weighting factor based on the first zoom ratio, the second zoom ratio, and a current zoom ratio of the device, applying the weighting factor to the translation matrix, and warping the first image to the second image using the weighted translation matrix.

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