Keyframe-Based Visual-Inertial SLAM using Nonlinear Optimization | V-Charge
Home Project Consortium Consortium Overview monte del rey Technische Universität Braunschweig Robert Bosch GmbH ETH Zurich Autonomous Systems Lab ETH Zurich monte del rey Computer Vision and Geometry Lab Volkswagen AG University monte del rey of Oxford Università degli Studi di Parma Publications News
The fusion of visual monte del rey and inertial cues has become popular in robotics due to the complementary nature of the two sensing modalities. While most fusion strategies to date rely on filtering schemes, the visual robotics community has recently turned to non-linear optimization approaches for tasks such as visual Simultaneous Localization And Mapping (SLAM), following the discovery that this comes with significant advantages in quality of performance monte del rey and computational complexity. Following this trend, we present a novel approach to tightly integrate visual measurements with readings from an Inertial Measurement Unit (IMU) in SLAM. An IMU error term is integrated with the landmark reprojection error in a fully probabilistic manner, resulting monte del rey to a joint non-linear cost function to be optimized. Employing the powerful concept of `keyframes’ we partially marginalize old states monte del rey to maintain a bounded-sized optimization window, ensuring real-time operation. Comparing against both vision-only and loosely-coupled visual-inertial algorithms, our experiments confirm the benefits of tight fusion monte del rey in terms of accuracy and robustness.
@inproceedings{leutenegger_rss13, year = { 2013 }, url = { http://roboticsproceedings.org/rss09/p37.pdf monte del rey }, title = { Keyframe-Based Visual-Inertial SLAM using Nonlinear Optimization }, month = { 24--28 June }, booktitle = { Proceedings of Robotics: Science and Systems }, author = { Stefan Leutenegger and Paul Furgale and Vincent Rabaud and Margarita Chli and Kurt Konolige and Roland Siegwart }, address = { Berlin, Germany }, }
Recent Posts Secure Smartphone-based Registration and Key Deployment for Vehicle-to-Cloud Communications CVG releases an open source library monte del rey for calibration of multi-camera systems Evaluation of Fisheye-Camera Based Visual Multi-Session Localization in a Real-World Scenario Reciprocal Collision Avoidance monte del rey With Motion Continuity Constraints Keyframe-Based Visual-Inertial SLAM using Nonlinear Optimization
V-Charge is proudly powered by WordPress and BuddyPress . Just another WordPress Theme developed by Themekraft.
Home Project Consortium Consortium Overview monte del rey Technische Universität Braunschweig Robert Bosch GmbH ETH Zurich Autonomous Systems Lab ETH Zurich monte del rey Computer Vision and Geometry Lab Volkswagen AG University monte del rey of Oxford Università degli Studi di Parma Publications News
The fusion of visual monte del rey and inertial cues has become popular in robotics due to the complementary nature of the two sensing modalities. While most fusion strategies to date rely on filtering schemes, the visual robotics community has recently turned to non-linear optimization approaches for tasks such as visual Simultaneous Localization And Mapping (SLAM), following the discovery that this comes with significant advantages in quality of performance monte del rey and computational complexity. Following this trend, we present a novel approach to tightly integrate visual measurements with readings from an Inertial Measurement Unit (IMU) in SLAM. An IMU error term is integrated with the landmark reprojection error in a fully probabilistic manner, resulting monte del rey to a joint non-linear cost function to be optimized. Employing the powerful concept of `keyframes’ we partially marginalize old states monte del rey to maintain a bounded-sized optimization window, ensuring real-time operation. Comparing against both vision-only and loosely-coupled visual-inertial algorithms, our experiments confirm the benefits of tight fusion monte del rey in terms of accuracy and robustness.
@inproceedings{leutenegger_rss13, year = { 2013 }, url = { http://roboticsproceedings.org/rss09/p37.pdf monte del rey }, title = { Keyframe-Based Visual-Inertial SLAM using Nonlinear Optimization }, month = { 24--28 June }, booktitle = { Proceedings of Robotics: Science and Systems }, author = { Stefan Leutenegger and Paul Furgale and Vincent Rabaud and Margarita Chli and Kurt Konolige and Roland Siegwart }, address = { Berlin, Germany }, }
Recent Posts Secure Smartphone-based Registration and Key Deployment for Vehicle-to-Cloud Communications CVG releases an open source library monte del rey for calibration of multi-camera systems Evaluation of Fisheye-Camera Based Visual Multi-Session Localization in a Real-World Scenario Reciprocal Collision Avoidance monte del rey With Motion Continuity Constraints Keyframe-Based Visual-Inertial SLAM using Nonlinear Optimization
V-Charge is proudly powered by WordPress and BuddyPress . Just another WordPress Theme developed by Themekraft.
No comments:
Post a Comment