Entity

Time filter

Source Type


Choi Y.W.,Yeungnam University | Kang T.H.,Pohang Institute of Intelligent Robotics | Saitov D.,Yeungnam University | Lee D.C.,Yeungnam University | Lee S.G.,Yeungnam University
Journal of Institute of Control, Robotics and Systems | Year: 2011

This paper proposes a hybrid image stabilizing system which uses both optical image stabilizing system based on EKF (Extended Kalman Filter) and digital image stabilization based on SURF (Speeded Up Robust Feature). Though image information is one of the most efficient data for object recognition, it is susceptible to noise which results from internal vibration as well as external factors. The blurred image obtained by the camera mounted on a robot makes it difficult for the robot to recognize its environment. The proposed system estimates shaking angle through EKF based on the information from inclinometer and gyro sensor to stabilize the image. In addition, extracting the feature points around rotation axis using SURF which is robust to change in scale or rotation enhances processing speed by removing unnecessary operations using Hessian matrix. The experimental results using the proposed hybrid system shows its effectiveness in extended frequency range. © ICROS 2011.


Lee J.-O.,Konkuk University | Lee K.-H.,Konkuk University | Park S.-H.,Pohang Institute of Intelligent Robotics | Im S.-G.,Konkuk University | Park J.,Konkuk University
Aircraft Engineering and Aerospace Technology | Year: 2011

Purpose - The purpose of this paper is to propose that the three-dimensional information of obstacles should be identified to allow unmanned aerial vehicles (UAVs) to detect and avoid obstacles existing in their flight path. Design/methodology/approach - First, the approximate outline of obstacles was detected using multi-scale-oriented patches (MOPS). At the same time, the spatial coordinates of feature points that exist in the internal outline of the obstacles were calculated through the scale-invariant feature transform (SIFT) algorithm. Finally, the results from MOPS and the results from the SIFT algorithm were merged to show the three-dimensional information of the obstacles. Findings - As the method proposed in this paper reconstructs only the approximate outline of obstacles, a quick calculation can be done. Moreover, as the outline information is combined through SIFT feature points, detailed three-dimensional information pertaining to the obstacles can be obtained. Practical implications - The proposed approach can be used efficiently in GPS-denied environments such as certain indoor environments. Originality/value - For the autonomous flight of small UAVs having a payload limit, this paper suggests a means of forming three-dimensional information about obstacles with images obtained from a monocular camera. © 2011 Emerald Group Publishing Limited. All rights reserved.


Yi S.,Korea University | Suh J.,Pohang Institute of Intelligent Robotics | Hong Y.,Pohang Institute of Intelligent Robotics | Hwang D.,ThinkLife Robotics Inc.
Proceedings of the SICE Annual Conference | Year: 2010

This paper presents an active ranging system based on laser structured-light image for mobile robot applications. The structured-light image processing is computationally efficient in comparison with the conventional stereo image processing, since the burdensome correspondence problem is avoided. In order to achieve robustness against environmental illumination noise, we propose an efficient image processing algorithm, i. e., integration of difference images with structured-light modulation. The proposed system has its own embedded image processing module and transmits final distance data to reduce the computational burden in main control system. © 2010 SICE.


Shin J.,Korea University | Yi S.,Korea University | Hong Y.,Pohang Institute of Intelligent Robotics | Suh J.,Pohang Institute of Intelligent Robotics
Journal of Institute of Control, Robotics and Systems | Year: 2010

In this paper, we proposed an omnidirectional ranging system that is able to obtain 360° all directional distances effectively based on structured light image. The omnidirectional ranging system consists of laser structured light source and a catadioptric omnidirectional camera with a curved mirror. The proposed integro-differential structured light image processing algorithm makes the ranging system robust against environmental illumination condition. The omnidirectional ranging system is useful for map-building and self-localization of a mobile robot. © ICROS 2010.


Jung K.,Pohang Institute of Intelligent Robotics | Shin S.,Sungkyunkwan University | Lee K.,Sungkyunkwan University | Park S.,Pohang Institute of Intelligent Robotics | And 3 more authors.
URAI 2011 - 2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence | Year: 2011

The miniature six-DOF force/torque sensor with CAN interface has been developed for the finger-tip of the dexterous robot hand. We designed the frame of sensor by FEM Analysis. The sensor consists of a transducer and a signal conditioning circuit. It is embedded in finger-tip sensor. We tested the performance of sensors by using a robot hand and a load cell. © 2011 IEEE.

Discover hidden collaborations