국소 집단 최적화 기법을 적용한 비정형 해저면 환경에서의 비주얼 SLAM
Visual SLAM using Local Bundle Optimization in Unstructured Seafloor Environment
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
As computer vision algorithms are developed on a continuous basis, the visual informationfrom vision sensors has been widely used in the context of simultaneous localization and mapping(SLAM), called visual SLAM, which utilizes relative motion information between images. Thisresearch addresses a visual SLAM framework for online localization and mapping in an unstructuredseabed environment that can be applied to a low-cost unmanned underwater vehicle equipped with asingle monocular camera as a major measurement sensor. Typically, an image motion model with apredefined dimensionality can be corrupted by errors due to the violation of the model assumptions,which may lead to performance degradation of the visual SLAM estimation. To deal with the erroneousimage motion model, this study employs a local bundle optimization (LBO) scheme when a closed loopis detected. The results of comparison between visual SLAM estimation with LBO and the other caseare presented to validate the effectiveness of the proposed methodology.
Abstract
As computer vision algorithms are developed on a continuous basis, the visual informationfrom vision sensors has been widely used in the context of simultaneous localization and mapping(SLAM), called visual SLAM, which utilizes relative motion information between images. Thisresearch addresses a visual SLAM framework for online localization and mapping in an unstructuredseabed environment that can be applied to a low-cost unmanned underwater vehicle equipped with asingle monocular camera as a major measurement sensor. Typically, an image motion model with apredefined dimensionality can be corrupted by errors due to the violation of the model assumptions,which may lead to performance degradation of the visual SLAM estimation. To deal with the erroneousimage motion model, this study employs a local bundle optimization (LBO) scheme when a closed loopis detected. The results of comparison between visual SLAM estimation with LBO and the other caseare presented to validate the effectiveness of the proposed methodology.
참고문헌 (16)
- 김태윤, "라오-블랙웰라이즈드 입자필터를 이용한 지형참조 수중항법", 제어.로봇.시스템학회 논문지, 19(8), pp.682~687 (2013), 제어·로봇·시스템학회[DOI]
- K. Richmond, "Real-time visual mosaicking and navigation on the seafloor", 박사, pp.2009
- R. Garcia, "Augmented state Kalman filtering for AUV navigation", Proc. IEEE International Conference on Robotics and Automation, 4, pp.4010~4015 (2002)
- N. Gracias, "Mosaic based navigation for autonomous underwater vehicles", IEEE Journal of Oceanic Engineering, 28(4), pp.609~624 (2003)
- R. M. Eustice, "Visually Augmented Navigation for Autonomous Underwater Vehicles", IEEE Journal of Oceanic Engineering, 33(2), pp.103~122 (2008)
- A. Kim, "Active Visual SLAM with Exploration for Autonomous Underwater Navigation", 박사, pp.2012
- 남창주, "광범위 환경에서 EKF-SLAM의 일관성 향상을 위한 새로운 관찰모델", 로봇학회 논문지, 7(1), pp.29~34 (2012), 한국로봇학회
- 장국현, "직선기반 SLAM에서의 루프결합", 로봇학회 논문지, 7(2), pp.120~128 (2012), 한국로봇학회[DOI]
- C. Harris, "A combined corner and edge detector", Proc. 4th Alvey Vision Conference, pp.147~151 (1988)
- D. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints", International Journal of Computer Vision, 60(2), pp.91~110 (2004)
- H. Bay, "SURF: Speeded Up Robust Features", Proc. European Conference on Computer Vision, pp.404~417 (2006)
- S. Leutenegger, "BRISK: Binary Robust Invariant Scalable Keypoints", Proc. International Conference on Computer Vision, pp.2548~2555 (2011)
- R. Hartley, "Multiple View Geometry in Computer Vision, 2nd ed" (2004), Cambridge University Press
- O. D. Faugeras, "Motion and structure from motion in a piecewise planar environment", International Journal of Pattern Recognition and Artificial Intelligence, 2(3), pp.485~508 (1988)
- R. Haralick, "Propagating covariance in computer vision", International Journal of Pattern Recognition and Artificial Intelligence, 10(5), pp.561~572 (1996)
- T. Coleman, "Optimization toolbox for use with Matlab" (1999), The MathWorks, Inc.