UWB 및 비전 센서 융합 기반고정밀 실내 위치 추정 시스템
High-Precision Indoor Positioning System Based on UWB and Vision Sensor Fusion
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
자율주행 기술이 발전함에 따라 GPS 없는 좁은 실내 환경에서도 차량 네비게이션을 가능하게 하는 위치 추정 기술의 중요성이대두되고 있다. 본 논문은 UWB와 단안 카메라라는 두 가지 센서 융합 기반 실내 위치 추정 시스템을 제안한다. 제안하는 시스템은먼저, 단안 카메라로 획득한 연속 이미지 데이터 간 특징점 매칭을 기반으로 카메라의 움직임 추정 및 동시 지도 생성을 하는 SLAM추정값과 고정된 좌표에서 송신하여 수신되는 3개 이상의 UWB 데이터의 삼각측량 기법에 의한 추정값을 획득한다. 두 추정값을획득한 후, 좌표변환과 확장 칼만 필터 기법에 따라 매칭 및 보정하여 최종 위치를 예측한다. 제안하는 시스템은 실험 결과 측위 오차 9cm라는 고정밀 성능을 보였다.
Abstract
With the advancement of autonomous driving technology, the importance of high-precision positioning technologiescapable of navigation in narrow indoor environments without GPS (Global Positioning System) has becomeincreasingly prominent. This paper proposes a high-precision indoor positioning system based on the fusion oftwo sensors: UWB and a monocular camera. The proposed system first acquires estimates using SLAM (SimultaneousLocalization and Mapping) based on feature point matching between consecutive image data obtained from themonocular camera, which estimates the camera's movement and simultaneously creates a map. Additionally,estimates are obtained from the triangulation method using data from three or more UWB transmitters andreceivers at fixed coordinates. After obtaining these estimates, the final position is predicted by matching andcorrecting the data according to coordinate transformation and EKF (Extended Kalman Filter). The proposedsystem demonstrated high-precision performance with a positioning error of less than 9cm in experimental results.
참고문헌 (16)
- F. Zafari, "A Survey of Indoor Localization Systems and Technologies", IEEE Communications Surveys & Tutorials, 21(3), pp.2568~2599 (2019)[DOI]
- R. F. Brena, "Evolution of indoor positioning technologies : A survey", Journal of Sensors (2017)[DOI]
- I. Skog, "In-Car Positioning and Navigation Technologies-A Survey", IEEE Transactions on Intelligent Transportation Systems, 10(1), pp.4~21 (2009)[DOI]
- S. He, "Wi-Fi Fingerprint-Based Indoor Positioning : Recent Advances and Comparisons", IEEE Communications Surveys & Tutorials, 18(1), pp.466~490 (2016)[DOI]
- Liu, "An UWB", Vision Fusion Scheme for Determining Pedestrians’ Indoor Location, 2020, pp.(4), ~
- C. Campos, "ORB-SLAM3 : An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM", IEEE Transactions on Robotics, 37(6), pp.1874~1890 (2021)[DOI]
- Decawave, "DWM1001 System Overview" (2017), Decawave Ltd
- Decawave, "Application of Ultra-Wideband for Real-Time Location Systems" (2016), Decawave Ltd
- M. Charlier, "Scheduling UWB Ranging and Backbone Communications in a Pure Wireless Indoor Positioning System", IoT, (3), pp.219~258[DOI]
- E. Rublee, "ORB : An efficient alternative to SIFT or SURF", International Conference on Computer Vision (ICCV), pp.2564~2571 (2011)
- L. Zong, "An improved method of real-time camera pose estimation based on descriptor tracking", IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), pp.903~908 (2017)
- R. Mur-Artal, "ORB-SLAM : A Versatile and Accurate Monocular SLAM System", IEEE Transactions on Robotics, 31(5), pp.1147~1163 (2015)[DOI]
- V. Lepetit, "EPnP : An accurate O(n)solution to the PnP problem", Int. J. Comput. Vision, 81(2), pp.155~166 (2009)[DOI]
- "ORB-SLAM3"[URL]
- "Kudan 3D-Lidar SLAM in Action:Vehicle-Based Mapping in an Urban area"[URL]
- Liu, Fei, "An UWB", Vision Fusion Scheme for Determining Pedestrians’ Indoor Location, 2020, pp.20(4), 1139~