Skip to main content Accessibility help
×
Home

Implementation and Analysis of Tightly Integrated INS/Stereo VO for Land Vehicle Navigation

  • Fei Liu (a1), Yashar Balazadegan Sarvrood (a1) and Yang Gao (a1)

Abstract

Tight integration of inertial sensors and stereo visual odometry to bridge Global Navigation Satellite System (GNSS) signal outages in challenging environments has drawn increasing attention. However, the details of how feature pixel coordinates from visual odometry can be directly used to limit the quick drift of inertial sensors in a tight integration implementation have rarely been provided in previous works. For instance, a key challenge in tight integration of inertial and stereo visual datasets is how to correct inertial sensor errors using the pixel measurements from visual odometry, however this has not been clearly demonstrated in existing literature. As a result, this would also affect the proper implementation of the integration algorithms and their performance assessment. This work develops and implements the tight integration of an Inertial Measurement Unit (IMU) and stereo cameras in a local-level frame. The results of the integrated solutions are also provided and analysed. Land vehicle testing results show that not only the position accuracy is improved, but also better azimuth and velocity estimation can be achieved, when compared to stand-alone INS or stereo visual odometry solutions.

Copyright

Corresponding author

References

Hide All
Asadi, E. and Bottasso, C.L. (2014). Tightly-coupled stereo vision-aided inertial navigation using feature-based motion sensors. Advanced Robotics, 28(11), 717729.
Bottasso, C.L., Leonello, D. and Milano, P. (2008). Vision-augmented inertial navigation by sensor fusion for an autonomous rotorcraft vehicle. In AHS International Specialists' Meeting on Unmanned Rotorcraft, 10281033.
Carrillo, L.R.G., López, A.E.D., Lozano, R. and Pégard, C. (2012). Combining stereo vision and inertial navigation system for a quad-rotor UAV. Journal of Intelligent & Robotic Systems, 65(1–4), 373387.
Geiger, A., Ziegler, J. and Stiller, C. (2011). Stereoscan: Dense 3d reconstruction in real-time. In Intelligent Vehicles Symposium (IV), 2011 IEEE. IEEE, pp. 963968.
Grewal, M.S., Weill, L.R. and Andrews, A.P. (2007). Global positioning systems, inertial navigation, and integration, John Wiley & Sons.
Hartley, R. and Zisserman, A. (2003). Multiple view geometry in computer vision, Cambridge University Press.
Jekeli, C. (2001). Inertial navigation systems with geodetic applications, Walter de Gruyter.
Kneip, L., Scaramuzza, D. and Siegwart, R. (2011). A novel parametrization of the perspective-three-point problem for a direct computation of absolute camera position and orientation. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 29692976.
Kong, X., Wu, W., Zhang, L. and Wang, Y. (2015). Tightly-Coupled Stereo Visual-Inertial Navigation Using Point and Line Features. Sensors, 15(6), 1281612833.
Konolige, K., Agrawal, M. and Sola, J. (2010). Large-scale visual odometry for rough terrain. In Robotics research. Springer, 201212.
Lepetit, V., Moreno-Noguer, F. and Fua, P. (2009). Epnp: An accurate o (n) solution to the pnp problem. International journal of computer vision, 81(2), 155166.
Liu, F., Sarvrood, Y.B. and Gao, Y. (2015). Tightly Coupled Stereo Vision Aided Inertial Navigation Using Continuously Tracked Features for Land Vehicles. In the 28th International Technical Meeting of The Satellite Division of the Institute of Navigation (ION GNSS + 2015). Tampa, 21272133.
Lowe, D.G. (2004). Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2), 91110.
Nistér, D. (2004). An efficient solution to the five-point relative pose problem. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 26(6), 756770.
Nistér, D., Naroditsky, O. and Bergen, J. (2004). Visual odometry. In Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on. IEEE, I-652.
Noureldin, A., Karamat, T.B. and Georgy, J. (2012). Fundamentals of inertial navigation, satellite-based positioning and their integration, Springer Science & Business Media.
Pankaj, D.S. and Nidamanuri, R.R. (2016). A Robust Estimation Technique for 3D Point Cloud Registration. Image Analysis & Stereology, 35(1), 1528.
Sarvrood, Y.B. and Gao, Y., 2014. Analysis and Reduction of Stereo Vision Alignment and Velocity Errors for Vision Navigation. In ION GNSS 2014. IEEE.
Scaramuzza, D. and Fraundorfer, F. (2011). Visual odometry Tutorial. Robotics & Automation Magazine, IEEE, 18(4), 8092.
Soloviev, A. and Miller, M.M. (2012). Navigation in difficult environments: multi-sensor fusion techniques. In Sensors: Theory, Algorithms, and Applications. Springer, 199229.
Strelow, D. (2004). Motion Estimation from Image and Inertial Measurements. The International Journal of Robotics Research, 23(12), 11571195.
Tardif, J.-P., George, M., Laverne, M., Kelly, A. and Stentz, A. (2010). A new approach to vision-aided inertial navigation. In Intelligent Robots and Systems (IROS), 2010 IEEE/RSJ International Conference on. IEEE, 41614168.
Tomasi, C. and Kanade, T. (1991). Detection and tracking of point features, School of Computer Science, Carnegie Mellon Univ. Pittsburgh.
Usenko, V., Engel, J., Stückler, J. and Cremers, D. (2016). Direct Visual-Inertial Odometry with Stereo Cameras. In 2016 IEEE International Conference on Robotics and Automation. 18851892.
Veth, M. and Raquet, J. (2007). Two-dimensional stochastic projections for tight integration of optical and inertial sensors for navigation, DTIC Document.
Xian, Z., Hu, X. and Lian, J. (2015). Fusing Stereo Camera and Low-Cost Inertial Measurement Unit for Autonomous Navigation in a Tightly-Coupled Approach. Journal of Navigation, 68(3), 434452.

Keywords

Metrics

Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed