Robust Invariant Features for Object Recognition, Pose Estimation and Topological Navigation

• 영문명: Robust Invariant Features for Object Recognition, Pose Estimation and Topological Navigation
• 발행기관: 한국과학기술원 인간친화 복지 로봇 시스템 연구센터
• 저자명: Zhe Lin In So Kweon
• 간행물 정보: 『International Journal of Assistive Robotics and Mechatronics』International Journal of Human-friendly Welfare Robotic Systems Vol.6 No.1, 28~35쪽, 전체 8쪽
• 주제분류: 공학 > 제어계측공학
• 파일형태: PDF
• 발행일자: 2005.04.01

영문 초록

  We present a new robust image feature detector for the object recognition and vision based mobile robot navigation. The proposed algorithm extracts highly robust and repeatable features based on the key idea of tracking and grouping multi-scale interest points and selecting a unique representative structure with the strongest response in both spatial and scale domains. Weighted Zernike moments are used as the local descriptor for feature representation. The experimental results and performance evaluation show that our feature detector has high repeatability and invariance to large scale, viewpoint and illumination changes. The efficiency and usefulness of the proposed feature detection method are also confirmed by the excellent performance on object recognition and mobile robot indoor navigation.

목차

Abstract
Ⅰ. INTRODUCTION
Ⅱ. THE FEATURE DETECTION FRAMEWORK
Ⅲ. RIF REGION DETECTOR
Ⅳ. RIF DESCRIPTOR
Ⅴ. OBJECT RECOGNITION AND POSE ESTIMATION
Ⅵ. TOPOLOGICALI NAVIGATION
Ⅶ. EXPERIMENTAL RESULTS
Ⅷ. CONCLUSION AND FUTURE WORKS
ACKNOWLEDGEMENTS
REFERENCES