会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 5. 发明授权
    • Proxy training data for human body tracking
    • 人体跟踪代理训练数据
    • US08213680B2
    • 2012-07-03
    • US12727787
    • 2010-03-19
    • Andrew FitzgibbonJamie ShottonMat CookRichard MooreMark Finnochio
    • Andrew FitzgibbonJamie ShottonMat CookRichard MooreMark Finnochio
    • G06K9/00H04N5/225
    • G06K9/6256G06K9/00335G06K9/6206
    • Synthesized body images are generated for a machine learning algorithm of a body joint tracking system. Frames from motion capture sequences are retargeted to several different body types, to leverage the motion capture sequences. To avoid providing redundant or similar frames to the machine learning algorithm, and to provide a compact yet highly variegated set of images, dissimilar frames can be identified using a similarity metric. The similarity metric is used to locate frames which are sufficiently distinct, according to a threshold distance. For realism, noise is added to the depth images based on noise sources which a real world depth camera would often experience. Other random variations can be introduced as well. For example, a degree of randomness can be added to retargeting. For each frame, the depth image and a corresponding classification image, with labeled body parts, are provided. 3-D scene elements can also be provided.
    • 为身体关节跟踪系统的机器学习算法生成合成身体图像。 来自运动捕捉序列的帧被重定向到几种不同的身体类型,以利用运动捕捉序列。 为了避免向机器学习算法提供冗余或相似的帧,并且为了提供紧凑但高度变化的图像集合,可以使用相似性度量来识别不同的帧。 相似性度量用于根据阈值距离定位足够明显的帧。 对于现实主义,基于真实世界深度相机经常会遇到的噪声源,将噪声添加到深度图像。 也可以引入其他随机变化。 例如,可以添加一定程度的随机性来重定向。 对于每个帧,提供深度图像和具有标记的身体部分的相应分类图像。 也可以提供3-D场景元素。
    • 6. 发明申请
    • PROXY TRAINING DATA FOR HUMAN BODY TRACKING
    • 代码训练数据用于人体跟踪
    • US20110228976A1
    • 2011-09-22
    • US12727787
    • 2010-03-19
    • Andrew FitzgibbonJamie ShottonMat CookRichard MooreMark Finnochio
    • Andrew FitzgibbonJamie ShottonMat CookRichard MooreMark Finnochio
    • G06K9/62G06K9/00
    • G06K9/6256G06K9/00335G06K9/6206
    • Synthesized body images are generated for a machine learning algorithm of a body joint tracking system. Frames from motion capture sequences are retargeted to several different body types, to leverage the motion capture sequences. To avoid providing redundant or similar frames to the machine learning algorithm, and to provide a compact yet highly variegated set of images, dissimilar frames can be identified using a similarity metric. The similarity metric is used to locate frames which are sufficiently distinct, according to a threshold distance. For realism, noise is added to the depth images based on noise sources which a real world depth camera would often experience. Other random variations can be introduced as well. For example, a degree of randomness can be added to retargeting. For each frame, the depth image and a corresponding classification image, with labeled body parts, are provided. 3-D scene elements can also be provided.
    • 为身体关节跟踪系统的机器学习算法生成合成身体图像。 来自运动捕捉序列的帧被重定向到几种不同的身体类型,以利用运动捕捉序列。 为了避免向机器学习算法提供冗余或相似的帧,并且为了提供紧凑但高度变化的图像集合,可以使用相似性度量来识别不同的帧。 相似性度量用于根据阈值距离定位足够明显的帧。 对于现实主义,基于真实世界深度相机经常会遇到的噪声源,将噪声添加到深度图像。 也可以引入其他随机变化。 例如,可以添加一定程度的随机性来重定向。 对于每个帧,提供深度图像和具有标记的身体部分的相应分类图像。 也可以提供3-D场景元素。
    • 7. 发明授权
    • Avocado skinning and pulping device
    • 鳄梨皮和制浆装置
    • US08967039B2
    • 2015-03-03
    • US13443802
    • 2012-04-10
    • Richard Moore
    • Richard Moore
    • A23N7/08A47J17/00A23N1/02A23N7/10
    • A23N1/02A23N7/08A23N7/10
    • An Avocado Skinning and Pulping Device. The avocado pulper has two grip belts approximately oval in shape and further having a plurality of grip plates around the grip belts. The grip plates are knurled thereby facilitating a grasping of an avocado as it is conveyed into the grip belts and rides through to the rear opening. A pivotable and adjustable belt guide within an inner section of each grip belt is adapted to exert maximum squeezing pressure on the avocado at the approximate middle section of the grip belts at which point the grip belts are in approximate contact with one another. Pulp is thereby squeezed from the avocado. The grip belts separate at the approximate rear defining space for releasing the skin of the avocado. A de-seeder adjacent to the front end opening of the grip belts removes the seed from the avocado prior to its entry into the maximum squeezing section.
    • 鳄梨皮和造纸设备。 鳄梨碎浆机具有大致椭圆形的两个夹持带,并且还具有围绕握持带的多个抓握板。 抓握板被滚花,从而便于在被输送到抓握带中并骑过去到后开口时抓取鳄梨。 在每个握持带的内部部分内的可枢转和可调节的带引导件适于在抓握带的大致中间部分处对鳄梨施加最大挤压压力,此时把手带彼此大致接触。 因此,纸浆从鳄梨中挤出。 握把带在大致后方定义的空间处分开,以释放鳄梨的皮肤。 与抓握带的前端开口相邻的脱粒机在进入最大挤压部分之前将种子从鳄梨中除去。
    • 8. 发明授权
    • Automatic termination path configuration
    • 自动终止路径配置
    • US08547964B2
    • 2013-10-01
    • US12551533
    • 2009-08-31
    • Michael F. DeConcilisRichard Moore
    • Michael F. DeConcilisRichard Moore
    • H04L12/56
    • H04Q3/66H04M7/128H04Q2213/13141H04Q2213/13353
    • There is provided herein a system and method for automatic configuration of data routings for use with electronic data such as phone calls, faxes, etc. In an exemplary embodiment, when more than one carrier might potentially terminate the transmission, the carriers are ordered based on some screening criterion (e.g., transmission price). Data transmissions are then assigned to the carriers based on the sorting order, with the second place and lower carriers (e.g., the higher priced carriers) not being selected unless the first carrier cannot complete the transaction. The switch instructions necessary to implement this scheme may be generated automatically.
    • 这里提供了用于自动配置用于电子数据(例如电话呼叫,传真等)的数据路由的系统和方法。在示例性实施例中,当多于一个运营商可能潜在地终止传输时,基于 一些筛选标准(如传输价格)。 然后,基于排序顺序将数据传输分配给​​载波,除非第一载波不能完成交易,否则第二位和低载波(例如,较高价格的载波)不被选择。 可以自动生成实现该方案所需的切换指令。