Kinect센서를 이용한 물체 인식 및 자세 추정을 위한 정확도 개선 방법
A Method for Improving Accuracy of Object Recognition and Pose Estimation by Using Kinect sensor
2
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
This paper presents a method of improving the pose recognition accuracy of objects by usingKinect sensor. First, by using the SURF algorithm, which is one of the most widely used local featurespoint algorithms, we modify inner parameters of the algorithm for efficient object recognition. Theproposed method is adjusting the distance between the box filter, modifying Hessian matrix, andeliminating improper key points. In the second, the object orientation is estimated based on thehomography. Finally the novel approach of Auto-scaling method is proposed to improve accuracy ofobject pose estimation. The proposed algorithm is experimentally tested with objects in the plane and itseffectiveness is validated.
Abstract
This paper presents a method of improving the pose recognition accuracy of objects by usingKinect sensor. First, by using the SURF algorithm, which is one of the most widely used local featurespoint algorithms, we modify inner parameters of the algorithm for efficient object recognition. Theproposed method is adjusting the distance between the box filter, modifying Hessian matrix, andeliminating improper key points. In the second, the object orientation is estimated based on thehomography. Finally the novel approach of Auto-scaling method is proposed to improve accuracy ofobject pose estimation. The proposed algorithm is experimentally tested with objects in the plane and itseffectiveness is validated.
참고문헌 (15)
- S. Calinon, "Learning and reproduction of gestures by imitation: An approach based on hidden Markov model and Gaussian mixture regression", IEEE Robotics and Automation Magazine, 17(2), pp.44~54 (2010)
- D. D. Tommaso, "A Tangible Interface for Transferring Skills - Using Perception and Projection Capabilities in Hurnan-Robot Collaboration Tasks", International Journal of Social Robotics, Special Issue on Learning from Demonstration, pp.1~12 (2012)
- K. Muelling, "Simulating Hurnan Table Tennis with a Biomimetic Robot Setup", Lecture Notes in Computer Science, 6226, pp.273~282 (2010)
- D. Forte, "On-line motion synthesis and adaptation using a trajectory database", Robotics and Autonomous Systems, 60(10), pp.1327~1339 (2012)
- 정민국, "센서 융합을 통한 환경지도 기반의 강인한 전역 위치추정", 로봇학회 논문지, 9(2), pp.96~103 (2014), 한국로봇학회[DOI]
- 박정혁, "실시간 햅틱 렌더링 기술을 통한 시각 장애인을 위한 원격현장감(Telepresence) 로봇 기술", 로봇학회 논문지, 8(3), pp.197~205 (2013), 한국로봇학회
- A. Weiss, "Home 3D body scans from noisy irnage and range data", IEEE International Conference on Computer Vision, Computer Vision and Pattern Recognition, pp.1951~1958 (2011)
- I. Oikonomidis, "Efficient model-based 3D tracking of hand articulations using Kinect", British Machine Vision Conference (2011)
- K. Khoshelham, "Accuracy and Resolution of Kinect Depth Data for Indoor Mapping Application", Sensors, pp.1437~1454 (2012)
- H. Bay, "SURF: Speeded Up Robust Features", European Conference on Computer Vision, 3951, pp.404~417 (2006)
- D. G. Lowe, "Distinctive Image Features from Scale invariant Key Point", International Journal of Computer Vision, 60(2), pp.91~110 (2004)
- M. A. Fischler, "Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography", Communication of the ACM, 24, pp.381~395 (1981)
- "Graphics and Media Lab. website"[URL]
- Z. Zhang, "Flexible camera calibration by viewing a plane from unknown orientation", IEEE International Conference on Computer Vision, pp.666~673 (1999)
- Deeper understanding of the homography decomposition for vision-based control, "E. Malis", INRIA Sophia-Antipolis, ~ (2005)