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

US09280742B1 Conceptual enhancement of automatic multimedia annotations 有权
标题翻译：自动多媒体注释的概念增强
公开(公告)号：US09280742B1
公开(公告)日：2016-03-08
申请号：US13604590
申请日：2012-09-05
申请人： Mehmet Emre Sargin , George Dan Toderici
发明人： Mehmet Emre Sargin , George Dan Toderici
IPC分类号： G06N5/04
CPC分类号： G06N5/04 , G06F17/30017 , G06K9/00 , G06K9/00744 , G06K9/6292 , G06K9/70 , G06N99/005 , G11B27/00
摘要： Methods and systems for suggesting one or more semantic tags for a media clip are disclosed. In one aspect, a media clip provided by a user is identified, and a first set of semantic tags is generated for the media clip based on a feature vector associated with the media clip. The first set of semantic tags is then provided to a classifier that is trained based on user selection of semantic tags. Further, a second set of semantic tags is obtained from the classifier and is suggested to the user for the media clip.
摘要翻译：公开了用于为媒体剪辑建议一个或多个语义标签的方法和系统。在一个方面中，识别由用户提供的媒体剪辑，并且基于与媒体剪辑相关联的特征向量为媒体剪辑生成第一组语义标签。然后将第一组语义标签提供给基于用户选择语义标签进行训练的分类器。此外，从分类器获得第二组语义标签，并向媒体剪辑的用户建议。

2. 发明授权

US08873841B2 Methods and apparatuses for facilitating gesture recognition 有权
标题翻译：用于促进手势识别的方法和装置
公开(公告)号：US08873841B2
公开(公告)日：2014-10-28
申请号：US13091901
申请日：2011-04-21
申请人： Jun Yang , Hawk-Yin Pang , Zhigang Liu
发明人： Jun Yang , Hawk-Yin Pang , Zhigang Liu
IPC分类号： G06K9/62 , G06F3/0346 , G06K9/00 , G06K9/22 , G06F3/01 , G06K9/70
CPC分类号： G06F3/017 , G06F3/0346 , G06K9/00355 , G06K9/22 , G06K9/70
摘要： Methods and apparatuses are provided for facilitating gesture recognition. A method may include constructing a matrix based at least in part on an input gesture and a template gesture. The method may further include determining whether a relationship determined based at least in part on the constructed matrix satisfies a predefined threshold. In an instance in which the relationship does not satisfy the predefined threshold, the method may also include eliminating the template gesture from further consideration for recognition of the input gesture. In an instance in which the relationship satisfies the predefined threshold, the method may further include determining a rotation matrix based at least in part on the constructed matrix.
摘要翻译：提供了用于促进手势识别的方法和装置。方法可以包括至少部分地基于输入手势和模板手势构建矩阵。该方法还可以包括确定至少部分地基于所构造的矩阵确定的关系是否满足预定阈值。在关系不满足预定义阈值的情况下，该方法还可以包括消除模板手势以进一步考虑以识别输入手势。在所述关系满足所述预定义阈值的情况下，所述方法还可以包括至少部分地基于所构建的矩阵来确定旋转矩阵。

3. 发明申请

US20190236331A1 METHOD, APPARATUS, AND STORAGE MEDIUM FOR DATA VERIFICATION 审中-公开
公开(公告)号：US20190236331A1
公开(公告)日：2019-08-01
申请号：US16376495
申请日：2019-04-05
申请人： Tencent Technology ( Shenzhen ) Company Ltd
发明人： Xiao XIAO
IPC分类号： G06K9/00 , H04L9/06 , G06K9/70
CPC分类号： G06K9/00087 , G06K9/00026 , G06K9/00067 , G06K9/70 , H04L9/0643
摘要： A data verification method is provided. Fingerprint information of N (N being an integer greater than 1) slices of to-be-sent data of a second device is received, the fingerprint information including first fingerprint information corresponding to an ith (i being an integer greater than 1) slice of the to-be-sent data and second fingerprint information corresponding to an (i−1)th slice of the to-be-sent data. The first fingerprint information is based on updating, by using the ith slice of the to-be-sent data, the second fingerprint information. An ith slice of data is received from the second device. The received second fingerprint information is updated by using the ith slice of data, to obtain third fingerprint information. Data verification failure indication information is transmitted to the second device in response to the third fingerprint information not matching the received first fingerprint information.

4. 发明申请

US20150062321A1 DEVICE CONTROL BY FACIAL FEATURE RECOGNITION 审中-公开
标题翻译：通过面部特征识别的设备控制
公开(公告)号：US20150062321A1
公开(公告)日：2015-03-05
申请号：US14011505
申请日：2013-08-27
申请人： BLACKBERRY LIMITED
发明人： Peter Mankowski , Ryan Alexander Geris , Cornel Mercea
IPC分类号： G06K9/00 , G06F3/01 , G01S7/52
CPC分类号： G06K9/00375 , G01S7/539 , G01S15/025 , G01S15/42 , G01S15/50 , G01S15/89 , G06F3/013 , G06F3/017 , G06K9/00315 , G06K9/228 , G06K9/70
摘要： An electronic device is controlled by scanning a face at an ultrasonic frequency, by at least one audio speaker. Facial features are mapped based on the scanning and repetitive movements of the facial features are detected by mapping the facial features over time. Future locations of the facial features are predicted based on the detecting of the repetitive movements. Control movements of the facial features are detected based on the mapping of the facial features and the predicting of the future locations of the facial features. The electronic device is controlled based on the detecting of the control movements.
摘要翻译：通过至少一个音频扬声器以超声频率扫描面部来控制电子设备。面部特征基于扫描进行映射，并且通过随时间映射面部特征来检测面部特征的重复运动。基于重复运动的检测来预测面部特征的未来位置。基于面部特征的映射和面部特征的未来位置的预测来检测面部特征的控制移动。基于控制运动的检测来控制电子设备。

5. 发明申请

US20180239989A1 Type Prediction Method, Apparatus and Electronic Device for Recognizing an Object in an Image 审中-公开
公开(公告)号：US20180239989A1
公开(公告)日：2018-08-23
申请号：US15900572
申请日：2018-02-20
申请人： Alibaba Group Holding Limited
发明人： Pan Pan , Wei Liu , Min Li , Yingya Zhang , Xiansheng Hua
IPC分类号： G06K9/62 , G06K9/46 , G06K9/68 , G06K9/70
CPC分类号： G06K9/6282 , G06K9/00664 , G06K9/46 , G06K9/629 , G06K9/6292 , G06K9/685 , G06K9/70
摘要： Type prediction method, apparatus and electronic device for recognizing an object in an image are disclosed. The method may include processing an image to be processed using a full image recognition technique to obtain a first type prediction result of an object in the image to be processed; processing a subject area of the image to be processed using a feature recognition technique to obtain a second type prediction result of an object of the subject area; determining whether the first type prediction result matches the second type prediction result; if the first type prediction result matches the second type prediction result, determining a type of the object of the image to be processed to be the first type prediction result or the second type prediction result.

6. 发明授权

US08374388B2 Real-time tracking of non-rigid objects in image sequences for which the background may be changing 失效
标题翻译：实时跟踪背景可能正在改变的图像序列中的非刚性对象
公开(公告)号：US08374388B2
公开(公告)日：2013-02-12
申请号：US12317317
申请日：2008-12-22
申请人： Rustam Stolkin , Ionut Florescu
发明人： Rustam Stolkin , Ionut Florescu
IPC分类号： G06K9/00
CPC分类号： G06K9/3241 , G06K9/66 , G06K9/70 , G06T7/277 , G06T2207/10016
摘要： A method and apparatus is disclosed for tracking an arbitrarily moving object in a sequence of images where the background may be changing. The tracking is based on visual features, such as color or texture, where regions of images (such as those which represent the object being tracked or the background) can be characterized by statistical distributions of feature values. The method improves on the prior art by incorporating a means whereby characterizations of the background can be rapidly re-learned for each successive image frame. This makes the method robust against the scene changes that occur when the image capturing device moves. It also provides robustness in difficult tracking situations, such as when the tracked object passes in front of backgrounds with which it shares similar colors or other features. Furthermore, a method is disclosed for automatically detecting and correcting certain kinds of errors which may occur when employing this or other tracking methods.
摘要翻译：公开了用于跟踪背景可能在改变的图像序列中的任意移动的对象的方法和装置。跟踪基于诸如颜色或纹理的视觉特征，其中可以通过特征值的统计分布来表征图像区域（例如表示被跟踪对象或背景的区域）。该方法通过结合一种能够为每个连续的图像帧快速重新学习背景的特征的装置来改进现有技术。这使得该方法对于当图像捕获设备移动时发生的场景变化是鲁棒的。它还在困难的跟踪情况下提供鲁棒性，例如当被跟踪对象通过与其共享相似颜色或其他特征的背景前面时。此外，公开了一种用于自动检测和校正当采用这种或其他跟踪方法时可能发生的某些种类的错误的方法。

7. 发明申请

US20120272194A1 METHODS AND APPARATUSES FOR FACILITATING GESTURE RECOGNITION 有权
标题翻译：用于促进姿势识别的方法和装置
公开(公告)号：US20120272194A1
公开(公告)日：2012-10-25
申请号：US13091901
申请日：2011-04-21
申请人： Jun Yang , Hawk-Yin Pang , Zhigang Liu
发明人： Jun Yang , Hawk-Yin Pang , Zhigang Liu
IPC分类号： G06F3/033
CPC分类号： G06F3/017 , G06F3/0346 , G06K9/00355 , G06K9/22 , G06K9/70
摘要： Methods and apparatuses are provided for facilitating gesture recognition. A method may include constructing a matrix based at least in part on an input gesture and a template gesture. The method may further include determining whether a relationship determined based at least in part on the constructed matrix satisfies a predefined threshold. In an instance in which the relationship does not satisfy the predefined threshold, the method may also include eliminating the template gesture from further consideration for recognition of the input gesture. In an instance in which the relationship satisfies the predefined threshold, the method may further include determining a rotation matrix based at least in part on the constructed matrix. Corresponding apparatuses are also provided.
摘要翻译：提供了用于促进手势识别的方法和装置。方法可以包括至少部分地基于输入手势和模板手势构建矩阵。该方法还可以包括确定至少部分地基于所构造的矩阵确定的关系是否满足预定阈值。在关系不满足预定义阈值的情况下，该方法还可以包括消除模板手势以进一步考虑以识别输入手势。在所述关系满足所述预定义阈值的情况下，所述方法还可以包括至少部分地基于所构建的矩阵来确定旋转矩阵。还提供了相应的装置。

8. 发明申请

US20180225554A1 SYSTEMS AND METHODS OF A COMPUTATIONAL FRAMEWORK FOR A DRIVER'S VISUAL ATTENTION USING A FULLY CONVOLUTIONAL ARCHITECTURE 审中-公开
公开(公告)号：US20180225554A1
公开(公告)日：2018-08-09
申请号：US15608523
申请日：2017-05-30
申请人： HONDA MOTOR CO., LTD.
发明人： Ashish TAWARI , Byeongkeun Kang
IPC分类号： G06K9/62 , G05D1/00
CPC分类号： G06K9/6278 , G05D1/0088 , G06K9/0061 , G06K9/00845 , G06K9/3233 , G06K9/4628 , G06K9/624 , G06K9/70
摘要： Systems and methods for estimating a saliency of one or more targets of a drive scene are provided. In some aspects, the system includes a memory that stores instructions for executing processes for estimating the saliency of the one or more targets of the drive scene. The system further includes a processor configured to execute the instructions. In various aspects, the processes include generating a Bayesian framework to model visual attention of a driver, the Bayesian framework comprising a bottom-up saliency element and a top-down saliency element. In various aspects, the processes also include generating a fully convolutional neural network, based on the Bayesian framework, to generate a visual saliency model of the one or more targets in the driving scene. In further aspects, the processes include outputting the visual saliency model to indicate features that attract attention of the driver.

9. 发明授权

US08976999B2 Vehicle detection apparatus 有权
标题翻译：车辆检测装置
公开(公告)号：US08976999B2
公开(公告)日：2015-03-10
申请号：US13365321
申请日：2012-02-03
申请人： Toru Saito
发明人： Toru Saito
IPC分类号： G06K9/00 , G08G1/04 , G06K9/32 , G06K9/70
CPC分类号： G08G1/04 , G06K9/00825 , G06K9/3233 , G06K9/70
摘要： A vehicle detection apparatus includes a lamp candidate extraction unit that extracts a pixel region that may correspond to a tail lamp of a vehicle from pixel regions that an integration processing unit creates by extracting and integrating pixels of an image as a lamp candidate and a grouping unit that regroups groups containing the lamp candidate of the groups generated by grouping position data detected by a position detection unit and then regroups all groups. In the regrouping processing, a threshold used for regrouping groups containing the lamp candidate is set easier for regrouping than a threshold used for subsequently regrouping all groups.
摘要翻译：车辆检测装置包括灯候选提取单元，其从通过提取和积分作为候选灯的图像的像素和积分单元提取积分积分处理单元创建的像素区域提取可对应于车辆尾灯的像素区域重新组合包含通过由位置检测单元检测到的位置数据分组生成的组的灯候补，然后重新组合所有组。在重新组合处理中，用于重新组合包含灯候选的组的阈值对于重新组合设置比用于随后重新组合所有组的阈值更容易。

10. 发明申请

US20120207348A1 VEHICLE DETECTION APPARATUS 有权
标题翻译：车辆检测装置
公开(公告)号：US20120207348A1
公开(公告)日：2012-08-16
申请号：US13365321
申请日：2012-02-03
申请人： Toru Saito
发明人： Toru Saito
IPC分类号： G06K9/62
CPC分类号： G08G1/04 , G06K9/00825 , G06K9/3233 , G06K9/70
摘要： A vehicle detection apparatus includes a lamp candidate extraction unit that extracts a pixel region that may correspond to a tail lamp of a vehicle from pixel regions that an integration processing unit creates by extracting and integrating pixels of an image as a lamp candidate and a grouping unit that regroups groups containing the lamp candidate of the groups generated by grouping position data detected by a position detection unit and then regroups all groups. In the regrouping processing, a threshold used for regrouping groups containing the lamp candidate is set easier for regrouping than a threshold used for subsequently regrouping all groups.
摘要翻译：车辆检测装置包括灯候选提取单元，其从通过提取和积分作为候选灯的图像的像素和积分单元提取积分积分处理单元创建的像素区域提取可对应于车辆尾灯的像素区域重新组合包含通过由位置检测单元检测到的位置数据分组生成的组的灯候补，然后重新组合所有组。在重新组合处理中，用于重新组合包含灯候选的组的阈值对于重新组合设置比用于随后重新组合所有组的阈值更容易。

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