公开(公告)号：US20140218516A1

公开(公告)日：2014-08-07

申请号：US13933074

申请日：2013-07-01

Applicant: Electronics and Telecommunications Research Institute

Inventor： Do-Hyung KIM ,  Ho sub YOON ,  Jae Yeon LEE ,  Kyu-Dae BAN ,  Woo han YUN ,  Youngwoo YOON ,  Jae Hong KIM ,  Young-Jo CHO ,  Suyoung CHI ,  Kye Kyung KIM

IPC: H04N7/18

CPC classification number: H04N7/18 ,  G06K9/00335 ,  G06K9/00369 ,  G06K9/00664

Abstract: A human information recognition method includes analyzing sensor data from multi-sensor resource placed in a recognition space to generate human information based on the sensor data, the human information including an identity, location and activity information of people existed in the recognition space. Further, the human information recognition method includes mixing the human information based on the sensor data with human information, the human information being acquired through interaction with the people existed in the recognition space; and storing a human model of the people existed in the recognition space depending on the mixed human information in a database unit.

Abstract translation: 一种人类信息识别方法，包括从放置在识别空间中的多传感器资源分析传感器数据，基于传感器数据生成人类信息，所述人类信息包括识别空间中存在的人的身份，位置和活动信息。 此外，人类信息识别方法包括将基于传感器数据的人类信息与人类信息进行混合，通过与存在于​​识别空间中的人相互作用来获取人类信息; 并且根据数据库单元中的混合人类信息，存储人的人类模型存在于识别空间中。

公开(公告)号：US20150092981A1

公开(公告)日：2015-04-02

申请号：US14162177

申请日：2014-01-23

Applicant: Electronics and Telecommunications Research Institute

Inventor： Do-Hyung KIM ,  Jae Hong KIM ,  Kye Kyung KIM ,  Youngwoo YOON ,  Woo han YUN ,  Ho sub YOON ,  Jae Yeon LEE ,  SUYOUNG CHI ,  Young-Jo CHO ,  Kyu-Dae BAN ,  Jong-Hyun PARK

IPC: G06K9/00 ,  G06K9/66 ,  G06K9/62

CPC classification number: G06K9/00342 ,  G06K9/6269 ,  G06K2009/4666

Abstract: An apparatus includes an image receiving module configured to collect a depth image provided from a camera, a human body detection module configured to detect a human body from the collected depth image, and an activity recognition module configured to recognize an action of the human body on the basis of a 3-dimensional action volume extracted from the human body and a previously learned action model.

Abstract translation: 一种装置，包括图像接收模块，被配置为收集从相机提供的深度图像，人体检测模块，被配置为从所收集的深度图像中检测人体;以及活动识别模块，被配置为识别人体的动作 从人体提取的三维动作体的基础和先前学习的动作模型。

公开(公告)号：US20140348380A1

公开(公告)日：2014-11-27

申请号：US14163265

申请日：2014-01-24

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Youngwoo YOON ,  Woo han YUN ,  Ho sub YOON ,  Jae Yeon LEE ,  Do-Hyung KIM ,  Jae Hong KIM ,  Jong-Hyun PARK

IPC: G06K9/00

CPC classification number: G06K9/32 ,  G06K2009/3291 ,  G06T7/246 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/30196 ,  G06T2207/30232

Abstract: A method for tracking an object in an object tracking apparatus includes receiving an image frame of an image; and detecting a target, a depth analogous obstacle and an appearance analogous obstacle; tracking the target, the depth analogous obstacle and the appearance analogous obstacle; when the detected target overlaps the depth analogous obstacle, comparing the variation of tracking score of the target with that of the depth analogous obstacle. Further, the method includes continuously tracking the target when the variation of tracking score of the target is below that of the depth analogous obstacle and processing a next frame when the variation of tracking score of the target is above that of the depth analogous obstacle; and re-detecting the target.

Abstract translation: 一种用于跟踪对象跟踪装置中的对象的方法包括：接收图像的图像帧; 并且检测目标，深度类似障碍物和外观类似障碍物; 跟踪目标，深度类似障碍和外观类似障碍; 当检测到的目标与深度类似障碍物重叠时，将目标的跟踪得分的变化与深度类似障碍物的变化进行比较。 此外，当目标的跟踪得分的变化低于深度类似障碍物的跟踪得分的变化并且当目标的跟踪得分的变化高于深度类似障碍物的变化时处理下一帧，该方法包括连续跟踪目标; 并重新检测目标。