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. 发明申请

US20110228976A1 PROXY TRAINING DATA FOR HUMAN BODY TRACKING 有权
标题翻译：代码训练数据用于人体跟踪
公开(公告)号：US20110228976A1
公开(公告)日：2011-09-22
申请号：US12727787
申请日：2010-03-19
申请人： Andrew Fitzgibbon , Jamie Shotton , Mat Cook , Richard Moore , Mark Finnochio
发明人： Andrew Fitzgibbon , Jamie Shotton , Mat Cook , Richard Moore , Mark Finnochio
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/6256 , G06K9/00335 , G06K9/6206
摘要： 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.
摘要翻译：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。

2. 发明授权

US08213680B2 Proxy training data for human body tracking 有权
标题翻译：人体跟踪代理训练数据
公开(公告)号：US08213680B2
公开(公告)日：2012-07-03
申请号：US12727787
申请日：2010-03-19
申请人： Andrew Fitzgibbon , Jamie Shotton , Mat Cook , Richard Moore , Mark Finnochio
发明人： Andrew Fitzgibbon , Jamie Shotton , Mat Cook , Richard Moore , Mark Finnochio
IPC分类号： G06K9/00 , H04N5/225
CPC分类号： G06K9/6256 , G06K9/00335 , G06K9/6206
摘要： 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.
摘要翻译：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。

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