Target Person Identification and Following Based on Omnidirectional Camera and LRF Sensor Fusion from a Moving Robot

2011 ◽  
Vol 23 (1) ◽  
pp. 163-172 ◽  
Author(s):  
Mehrez Kristou ◽  
◽  
Akihisa Ohya ◽  
Shin’ichi Yuta

In this paper, we introduce an approach to identify and follow a target person for a service robot application. The robot is equipped with LRF and omnidirectional camera. Our approach is based on multisensor fusion in which a person is identified using the panoramic image and tracked using the Laser Range Finder (LRF). A target person selection is implemented to improve the identification when multiple candidates are detected. Our approach is successfully implemented on a mobile robot. A simplified target person following behavior is implemented to focus on the proposed method’s efficiency. Several experiments are conducted and showed the effectiveness of our approach to identify and follow human in indoor environments.

2014 ◽  
Vol 19 (6) ◽  
pp. 1963-1976 ◽  
Author(s):  
Eui-Jung Jung ◽  
Jae Hoon Lee ◽  
Byung-Ju Yi ◽  
Jooyoung Park ◽  
Shinichi Yuta ◽  
...  

2014 ◽  
Vol 26 (1) ◽  
pp. 68-77 ◽  
Author(s):  
Masashi Awai ◽  
◽  
Atsushi Yamashita ◽  
Takahito Shimizu ◽  
Toru Kaneko ◽  
...  

In this paper, we propose a mobile robot system which has functions of person following and autonomous returning. The robot realizes these functions by analyzing information obtained with camera and laser range finder. Person following is performed by using HOG features, color information, and pattern of range data. Along with person following, a map of the ambient environment is generated from range data. Autonomous returning to the starting point is performed by applying potential method to the generated map. We verified the proposed method by experiment using a wheel mobile robot in an indoor environment.


2014 ◽  
Vol 939 ◽  
pp. 609-614 ◽  
Author(s):  
Liang Kuang Chen ◽  
Mao Yuan Hsiao

In this paper, we design a service robot which not only can plan road to a destination by itself, but also can take an elevator to every floor. For planning road, in order to solve the Hagisonic Stargazer Robot localization system problem which in large environment will need to set a lot of landmark and this way will increase the lead time and memory capacity. So we use the concept of road nodes to combine with Stargazer landmark and Dijkstra’s algorithm. Robot can localize by itself and can plan the shortest road to a destination. In dead region of Stargazer, we integrate with a laser range finder and e-compass to assist robot in navigation, and use the laser range finder simultaneously to avoid front obstacle. For taking elevator, we design a wireless control of independent mechanism. Robot can use Xbee transmit command to control servo motor to push elevator button and use RFID to determine whether the arrival task Floor. Last, we use Borland C++ Builder to design a Human–Computer interaction. People can operate monitor to choice receiver, and we add the functions of remote call and setting code which can increase the practicability of this service robots.


Sign in / Sign up

Export Citation Format

Share Document