Browsing by Author "Ke, Ting-Yuan"

Now showing 1 - 2 of 2

Demo: A ROS-based Robot with Distributed Sensors for Seamless People Tracking
(2019-01-01)
Zhang, Ling-Yan
;
Wu, Kun-Ru
;
Ke, Ting-Yuan
;
Wang, Chih-Hsiang
;
Tseng, Yu-Chee
This paper presents a robot for people identification and tracking developed on robot operating system (ROS). It achieves modulized, light-weight, low-cost, and high-performance design goals even with the existence of distributed sensors. The key idea is to utilize wearable devices to enhance the people tracking capability of a robot through instant wireless communications and multi-sensory data fusion. Experimental results in a realistic environment demonstrate that our robot can keep tracking a specific person at a safe distance even without seeing the biological features of the person, who walks in a crowd with complex trajectories.
Who Takes What: Using RGB-D Camera and Inertial Sensor for Unmanned Monitor
(2019-01-01)
Kao, Hsin-Wei
;
Ke, Ting-Yuan
;
Lin, Kate Ching-Ju
;
Tseng, Yu-Ghee
;
資訊工程學系
Advanced Internet of Things (IoT) techniques have made human-environment interaction much easier. Existing solutions usually enable such interactions without knowing the identities of action performers. However, identifying users who are interacting with environments is a key to enable personalized service. To provide such add-on service, we propose WTW (who takes what), a system that identifies which user takes what object. Unlike traditional vision-based approaches, which are typically vulnerable to blockage, our WTW combines the feature information of three types of data, i.e., images, skeletons and IMU data, to enable reliable user-object matching and identification. By correlating the moving trajectory of a user monitored by inertial sensors with the movement of an object recorded in the video, our WTW reliably identifies a user and matches him/her with the object on action. Our prototype evaluation shows that WTW achieves a recognition rate of over 90% even in a crowd. The system is reliable even when users locate close by and take objects roughly at the same time.