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

US08467570B2 Tracking system with fused motion and object detection 有权
标题翻译：具有融合运动和物体检测的跟踪系统
公开(公告)号：US08467570B2
公开(公告)日：2013-06-18
申请号：US11562266
申请日：2006-11-21
申请人： Yunqian Ma , Qian Yu , Isaac Cohen
发明人： Yunqian Ma , Qian Yu , Isaac Cohen
IPC分类号： G06K9/00
CPC分类号： H04N7/18 , G06K9/00335 , G06K9/00785 , G06K9/4671 , G06K9/6218 , G06K9/6292
摘要： A detection system fusing motion detection and object detection for various applications such as tracking, identification, and so forth. In an application framework, model information may be developed and used to reduce the false alarm rate. With a background model, motion likelihood for each pixel, for instance, of a surveillance image, may be acquired. With a target model, object likelihood for each pixel of the image may also be acquired. By joining these two likelihood distributions, detection accuracy may be significantly improved over the use of just one likelihood distribution for detection in applications such as tracking.
摘要翻译：一种检测系统，可以对诸如跟踪，识别等的各种应用进行融合运动检测和物体检测。在应用框架中，可以开发模型信息并用于减少误报率。使用背景模型，可以获取每个像素（例如监视图像）的运动似然性。使用目标模型，也可以获取图像的每个像素的对象似然。通过加入这两个似然分布，可以比在诸如跟踪的应用中仅使用一个似然分布进行检测来显着改善检测精度。

2. 发明申请

US20080123900A1 SEAMLESS TRACKING FRAMEWORK USING HIERARCHICAL TRACKLET ASSOCIATION 审中-公开
标题翻译：无缝跟踪框架使用分层轨迹协会
公开(公告)号：US20080123900A1
公开(公告)日：2008-05-29
申请号：US11548185
申请日：2006-10-10
申请人： Yunqian Ma , Qian Yu , Isaac Cohen
发明人： Yunqian Ma , Qian Yu , Isaac Cohen
IPC分类号： G06K9/00
CPC分类号： G08B13/19608 , G06K9/32 , G06T7/215 , G06T7/277 , G06T7/292 , G06T2207/30232 , G06T2207/30241
摘要： A tracking system that may initially take image sequences from sensors and regions of interest computed automatically, or defined by the operator, or provided by another approach or way. Tracklets may be initialized from the provided regions of interest. The tracklets of the same target may be associated with each other to form another tracklet of another level. Tracklets may be merged to form tracks. Association of tracklets or tracks may be effected at various levels in a hierarchical manner. Also, association of observations, tracklets and tracks may be based on a computation of distance, i.e., similarity in motion and appearance.
摘要翻译：跟踪系统可以最初从传感器和感兴趣的区域中获取图像序列，这些图像序列自动地或由操作者定义，或者由另一种方法或方式提供。可以从所提供的感兴趣区域初始化轨迹。相同目标的轨迹可以彼此关联以形成另一级别的另一轨迹。轨迹可以合并形成曲目。轨迹或轨道的关联可以以各种层次的方式进行。此外，观察，轨迹和轨道的关联可以基于距离的计算，即运动和外观的相似性。

3. 发明申请

US20080002856A1 TRACKING SYSTEM WITH FUSED MOTION AND OBJECT DETECTION 有权
标题翻译：具有熔融运动和物体检测的跟踪系统
公开(公告)号：US20080002856A1
公开(公告)日：2008-01-03
申请号：US11562266
申请日：2006-11-21
申请人： Yunqian Ma , Qian Yu , Isaac Cohen
发明人： Yunqian Ma , Qian Yu , Isaac Cohen
IPC分类号： G06K9/00 , G01S13/00 , H04N7/18
CPC分类号： H04N7/18 , G06K9/00335 , G06K9/00785 , G06K9/4671 , G06K9/6218 , G06K9/6292
摘要： A detection system fusing motion detection and object detection for various applications such as tracking, identification, and so forth. In an application framework, model information may be developed and used to reduce the false alarm rate. With a background model, motion likelihood for each pixel, for instance, of a surveillance image, may be acquired. With a target model, object likelihood for each pixel of the image may also be acquired. By joining these two likelihood distributions, detection accuracy may be significantly improved over the use of just one likelihood distribution for detection in applications such as tracking.
摘要翻译：一种检测系统，可以对诸如跟踪，识别等的各种应用进行融合运动检测和物体检测。在应用框架中，可以开发模型信息并用于减少误报率。使用背景模型，可以获取每个像素（例如监视图像）的运动似然性。使用目标模型，也可以获取图像的每个像素的对象似然。通过加入这两个似然分布，可以比在诸如跟踪的应用中仅使用一个似然分布进行检测来显着改善检测精度。

4. 发明申请

US20100013935A1 MULTIPLE TARGET TRACKING SYSTEM INCORPORATING MERGE, SPLIT AND REACQUISITION HYPOTHESES 审中-公开
标题翻译：多目标跟踪系统，包含合并，分割和反应假设
公开(公告)号：US20100013935A1
公开(公告)日：2010-01-21
申请号：US11761171
申请日：2007-06-11
申请人： Yunqian Ma , Qian Yu , Isaac Cohen
发明人： Yunqian Ma , Qian Yu , Isaac Cohen
IPC分类号： H04N5/225
CPC分类号： G06K9/32 , G06K9/00771 , G06T7/277 , G06T2207/30241
摘要： A tracking system having a video detector for associating observations of blobs and objects and deriving objects' or blobs' paths. Hypotheses may be computed by the system for merging, splitting and reacquisition of the observations. There may be objects tracked among the observations, and best paths selected as trajectories of corresponding objects. The observations may be placed in a sliding window containing a series of observations inferred from a collection of frames for improving the accuracy of the tracking (or data association). The processed observations and data may be represented graphically.
摘要翻译：跟踪系统具有视频检测器，用于将斑点和对象的观察结果相关联并导出对象或斑点的路径。系统可以通过系统计算假设来合并，分解和重新获取观测值。在观察中可能会跟踪对象，并选择最佳路径作为相应对象的轨迹。观察结果可以放置在滑动窗口中，其包含从帧集合推断的一系列观察结果，用于提高跟踪（或数据关联）的准确性。经处理的观察和数据可以用图形表示。

5. 发明授权

US08555445B2 Hydraulic driven jaw-type clutch impeller combination and swimming pool bottom hydraulic pushed automatic cleaner comprising same 有权
标题翻译：液压驱动颚式离合器叶轮组合和游泳池底部液压推动自动清洁器组成
公开(公告)号：US08555445B2
公开(公告)日：2013-10-15
申请号：US13499551
申请日：2010-06-29
申请人： Guilan Fu , Qian Yu , Jian Liu , Bichang Wang , Xinru Gong , Xianozhou Lv , Zhi Yi Zou
发明人： Guilan Fu , Qian Yu , Changsheng Zou , Jian Liu , Bichang Wang , Xinru Gong , Xianozhou Lv
IPC分类号： E04H4/16
CPC分类号： E04H4/1654
摘要： A swimming pool bottom hydraulic pushed automatic cleaner includes an underwater cleaner and a control power supply connected by a buoyancy cable. The underwater cleaner includes a housing cover, housing body, filter, double extension shaft motor assembly, hydraulic driven jaw-type clutch impeller combination, water inlet/outlet flow passage, wheel and bracket, an isolated hood and a cable with floaters. Along with the changing of the rotating direction of the motor, the impeller combination is engaged and disengaged under the action of hydraulic power to change the working state of the impeller, thereby changing water outlet of injection water flow and further changing the travel direction of the cleaner. The housing touches a wall to cause the cleaner to adjust the direction after touching the wall. Furthermore, two or more axial-flow pumps are arranged horizontally and parallelly, so that the cleaner has turning function and orderly complete coverage cleaning is realized.
摘要翻译：游泳池底部液压推动自动清洁器包括水下清洁器和通过浮力电缆连接的控制电源。水下清洁器包括壳体盖，壳体，过滤器，双延伸轴电机组件，液压驱动颚式离合器叶轮组合，进水/出口流动通道，轮和支架，隔离罩和带有浮子的电缆。随着电动机旋转方向的变化，叶轮组合在液压动力作用下接合和分离，改变了叶轮的工作状态，从而改变了注入水流的出水口，并进一步改变了清洁器。外壳接触墙壁，使吸尘器在接触墙壁后调整方向。此外，两个或更多个轴流泵被水平和平行布置，使得清洁器具有转向功能并且有序地完成覆盖清洁。

6. 发明授权

US08548404B2 Linearization of power amplifiers through digital in-band predistortion followed by analog predistortion 有权
标题翻译：通过数字带内预失真跟随模拟预失真来对功率放大器进行线性化
公开(公告)号：US08548404B2
公开(公告)日：2013-10-01
申请号：US13250635
申请日：2011-09-30
申请人： Qian Yu
发明人： Qian Yu
IPC分类号： H03C1/62
CPC分类号： H03F1/3241 , H03F1/3247 , H03F2200/321 , H04L25/03343
摘要： A system for implementing linearization of a radio frequency (RF) power amplifier (PA) in a base station, as well as various component circuitry for implementing said system. By means of a smart partitioning of the signal processing for predistortion between the analog domain and the digital domain, a more linear relationship between the digital input data and the output RF signal is achieved. Linearization of the PA's output signal is obtained using a mixed-signal apparatus. The digital baseband signal enters the RF signal source. The RF signal source comprises an in-band predistortion circuit, a micro-controller and digital modulator. The output of the digital modulator is an RF signal that enters the PA module. The PA module is composed of the PA and the RF power amplifier linearizer (RFPAL). The RFPAL comprises an RF predistortion circuit, and RF signal analyzer and a microcontroller.
摘要翻译：一种用于实现基站中的射频（RF）功率放大器（PA）的线性化的系统，以及用于实现所述系统的各种组件电路。通过对模拟域和数字域之间的预失真进行信号处理的智能划分，实现了数字输入数据与输出RF信号之间更为线性的关系。使用混合信号装置获得PA输出信号的线性化。数字基带信号进入RF信号源。 RF信号源包括带内预失真电路，微控制器和数字调制器。数字调制器的输出是进入PA模块的RF信号。 PA模块由PA和RF功率放大器线性化（RFPAL）组成。 RFPAL包括RF预失真电路，RF信号分析器和微控制器。

7. 发明授权

US08391548B1 Tracking multiple moving targets in digital video 有权
标题翻译：跟踪数字视频中的多个移动目标
公开(公告)号：US08391548B1
公开(公告)日：2013-03-05
申请号：US12470480
申请日：2009-05-21
申请人： Gerard Medioni , Qian Yu
发明人： Gerard Medioni , Qian Yu
IPC分类号： G06K9/00
CPC分类号： G06K9/00771
摘要： Tracking multiple targets can include making different observations based on multiple different frames of one or more digital video feeds, determining an initial cover based on the observations, performing one or more modifications to the initial cover to generate a final cover, and using the final cover to track multiple targets in the one or more digital video feeds. Performing one or more modifications to generate a final cover can include selecting one or more adjustments from a group that includes temporal cover adjustments and spatial cover adjustments, and can include using likelihood information indicative of similarities in motion and appearance to distinguish different targets in the frames.
摘要翻译：跟踪多个目标可以包括基于一个或多个数字视频馈送的多个不同帧来进行不同的观察，基于观察确定初始覆盖，对初始覆盖执行一个或多个修改以产生最终覆盖，并且使用最终覆盖以跟踪一个或多个数字视频馈送中的多个目标。执行一个或多个修改以生成最终封面可以包括从包括时间覆盖调整和空间覆盖调整的组中选择一个或多个调整，并且可以包括使用表示运动和外观的相似性的似然信息来区分帧中的不同目标。

8. 发明授权

US08374275B2 Method and system for communication channel optimization in a multiple-input multiple-output (MIMO) communication system 有权
标题翻译：多输入多输出（MIMO）通信系统中通信信道优化的方法和系统
公开(公告)号：US08374275B2
公开(公告)日：2013-02-12
申请号：US12514515
申请日：2007-06-23
申请人： Qian Yu , Ping Luo , Masayuki Hoshino
发明人： Qian Yu , Ping Luo , Masayuki Hoshino
IPC分类号： H04B7/02 , H04B7/06 , H04L27/00
CPC分类号： H04B7/0417 , H04B7/0452 , H04B7/0634 , H04B7/0639
摘要： A transmission method in a multiple-input multiple-output (MIMO) communication system, a transmitter in a MIMO communication system and a MIMO communication system are provided. The method comprises the steps of: receiving feedback data representing channel state information from respective receivers of the MIMO communication system; grouping the receivers into one or more groups based on the received feedback data; obtaining a precoding matrix for each group of receivers based on the received feedback data such that precoding vectors or sub-matrices in the precoding matrix associated with respective receivers of said each group of receivers are orthogonal to each other; and applying the precoding matrix to input signals for transmission to said each group of receivers.
摘要翻译：提供了多输入多输出（MIMO）通信系统中的传输方法，MIMO通信系统中的发射机和MIMO通信系统。该方法包括以下步骤：从MIMO通信系统的各个接收机接收表示信道状态信息的反馈数据; 基于接收到的反馈数据将接收机分组成一个或多个组; 基于所接收的反馈数据获得每组接收机的预编码矩阵，使得与所述每组接收机的各接收机相关联的预编码矩阵中的预编码向量或子矩阵彼此正交; 以及将预编码矩阵应用于输入信号以传输到所述每组接收机。

9. 发明授权

US08351649B1 Video feed target tracking 有权
标题翻译：视频Feed目标跟踪
公开(公告)号：US08351649B1
公开(公告)日：2013-01-08
申请号：US12416913
申请日：2009-04-01
申请人： Gerard Medioni , Qian Yu , Thang Ba Dinh
发明人： Gerard Medioni , Qian Yu , Thang Ba Dinh
IPC分类号： G06K9/00
CPC分类号： G06K9/6282 , G06K9/00771 , G06T7/251 , G06T2207/10016 , G06T2207/30201
摘要： Technologies for object tracking can include accessing a video feed that captures an object in at least a portion of the video feed; operating a generative tracker to capture appearance variations of the object operating a discriminative tracker to discriminate the object from the object's background, where operating the discriminative tracker can include using a sliding window to process data from the video feed, and advancing the sliding window to focus the discriminative tracker on recent appearance variations of the object; training the generative tracker and the discriminative tracker based on the video feed, where the training can include updating the generative tracker based on an output of the discriminative tracker, and updating the discriminative tracker based on an output of the generative tracker; and tracking the object with information based on an output from the generative tracker and an output from the discriminative tracker.
摘要翻译：用于对象跟踪的技术可以包括访问在视频馈送的至少一部分中捕获对象的视频馈送; 操作生成跟踪器以捕获操作鉴别跟踪器的对象的外观变化，以区分对象与对象的背景，其中操作鉴别性跟踪器可以包括使用滑动窗口来处理来自视频馈送的数据，以及将滑动窗口推进到焦点最近出现的对象变化的歧视性追踪器; 基于所述视频馈送来训练所述生成跟踪器和所述歧视性跟踪器，其中所述训练可以包括基于所述识别跟踪器的输出来更新所述生成跟踪器，以及基于所述生成跟踪器的输出来更新所述识别跟踪器; 以及基于来自生成跟踪器的输出和来自辨别性跟踪器的输出的信息来跟踪对象。

10. 发明授权

US08345930B2 Method for computing food volume in a method for analyzing food 有权
标题翻译：食物分析方法计算食物量的方法
公开(公告)号：US08345930B2
公开(公告)日：2013-01-01
申请号：US12758208
申请日：2010-04-12
申请人： Amir Tamrakar , Harpreet Singh Sawhney , Qian Yu , Ajay Divakaran
发明人： Amir Tamrakar , Harpreet Singh Sawhney , Qian Yu , Ajay Divakaran
IPC分类号： G06K9/00
CPC分类号： G06T7/0002 , G06T7/44 , G06T7/593 , G06T7/62 , G06T7/77 , G06T2207/20016 , G06T2207/30128
摘要： A computer-implemented method for estimating a volume of at least one food item on a food plate is disclosed. A first and second plurality of images are received from different positions above a food plate, wherein angular spacing between the positions of the first plurality of images is greater than angular spacing between the positions of the second plurality of images. A first set of poses of each of the first plurality of images is estimated. A second set of poses of each of the second plurality of images is estimated based on at least the first set of poses. A pair of images taken from each of the first and second plurality of images is rectified based on at least the first and second set of poses. A 3D point cloud is reconstructed based on at least the rectified pair of images. At least one surface of the at least one food item above the food plate is estimated based on at least the reconstructed 3D point cloud. The volume of the at least one food item is estimated based on the at least one surface.
摘要翻译：公开了一种用于估计食品板上的至少一种食品的体积的计算机实现的方法。从食品牌上方的不同位置接收第一和第二多个图像，其中第一多个图像的位置之间的角度间隔大于第二多个图像的位置之间的角度间隔。估计第一多个图像中的每一个的第一组姿势。基于至少第一组姿势来估计第二组多个图像中的每一个的第二组姿势。从第一和第二多个图像中的每一个拍摄的一对图像至少基于第一和第二组姿势进行整改。至少基于整流图像对来重构3D点云。基于至少重构的3D点云来估计食物板上方的至少一个食物的至少一个表面。基于至少一个表面来估计至少一个食物的体积。

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