Navigation aiding using on-line mosaicking

This paper presents a procedure for improving the performance of an inertial navigation airborne system that uses the information obtained from an on-board camera and an algorithm for building on-line a mosaic of the scene observed by the camera. The system considered in the paper consists of a flying platform provided with a pan-tilt camera that scans the region over which the platform flies. The sequence of images obtained from the camera are "pasted" together using an image processing algorithm that results in a mosaic of the scanned terrain. Since the sequence of image is a result of the platform and camera motion, and the camera motion is assumed to be known, the calculations involved in computing the mosaic encode information on the motion of the platform. A measurement model is specified that uses the mosaic construction process to update the navigation algorithm and hence reduce navigation errors. Performance study is presented as a proof of concept for the procedure using a realistic model for the inertial measurement unit.

[1]  Richard Szeliski,et al.  Seamless Stitching using Multi-Perspective Plane Sweep , 2004 .

[2]  Salah Sukkarieh,et al.  Active airborne localisation and exploration in unknown environments using inertial SLAM , 2006, 2006 IEEE Aerospace Conference.

[3]  Shmuel Peleg,et al.  Panoramic mosaics by manifold projection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Xavier Cufí,et al.  Augmented state Kalman filtering for AUV navigation , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[5]  Yoram Bresler,et al.  On-Line Vehicle Motion Estimation from Visual Terrain Information Part I: Recursive Image Registration , 1986, IEEE Transactions on Aerospace and Electronic Systems.

[6]  P. Anandan,et al.  Mosaic based representations of video sequences and their applications , 1995, Proceedings of IEEE International Conference on Computer Vision.

[7]  Ehud Rivlin,et al.  Navigation Performance Enhancement Using Rotation and Translation Measurements from Online Mosaicking , 2007 .

[8]  Hector Rotstein,et al.  Partial Aircraft State Estimation from Visual Motion Using the Subspace Constraints Approach , 2001 .

[9]  Xun Xu,et al.  Mosaic-based positioning and improved motion-estimation methods for automatic navigation of submersible vehicles , 2002 .

[10]  Jonghyuk Kim,et al.  6DoF SLAM aided GNSS/INS Navigation in GNSS Denied and Unknown Environments , 2005 .

[11]  Kenichi Kanatani,et al.  Image mosaicing by stratified matching , 2004, Image Vis. Comput..

[12]  H. H. Wang,et al.  Video mosaicking along arbitrary vehicle paths , 1996, Proceedings of Symposium on Autonomous Underwater Vehicle Technology.

[13]  Richard Szeliski,et al.  Systems and Experiment Paper: Construction of Panoramic Image Mosaics with Global and Local Alignment , 2000, International Journal of Computer Vision.

[14]  P. Rousseeuw.  Least Median of Squares Regression , 1984 .

[15]  Allen R. Hanson,et al.  Generalized parallel-perspective stereo mosaics from airborne video , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[17]  Yoram Bresler,et al.  On-line Vehicle Motion Estimation from Visual Terrain Information Part II: Ground Velocity and Position Estimation , 1986, IEEE Transactions on Aerospace and Electronic Systems.

[18]  Sang Uk Lee,et al.  Integrated Position Estimation Using Aerial Image Sequences , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Shmuel Peleg,et al.  Mosaicing on Adaptive Manifolds , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Andrew Zisserman,et al.  Multiple View Geometry , 1999 .

[21]  Yaakov Oshman,et al.  Maximum a posteriori image registration/motion estimation , 1994 .

[22]  P. Perona,et al.  Recursive 3-D Visual Motion Estimation Using Subspace Constraints , 1997, International Journal of Computer Vision.

[23]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Pere Ridao,et al.  Towards a real-time vision-based navigation system for a small-class UUV , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[25]  Jason Jianjun Gu,et al.  Graph-based Automatic Consistent Image Mosaicking , 2004, 2004 IEEE International Conference on Robotics and Biomimetics.

[26]  Salah Sukkarieh,et al.  Bearing-Only SLAM for an Airborne Vehicle , 2005 .

[27]  Lihi Zelnik-Manor,et al.  Multiview Constraints on Homographies , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Ehud Rivlin,et al.  Pose and motion recovery from feature correspondences and a digital terrain map , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  R. Campos.  A proposal to estimate the motion of an underwater vehicle through visual mosaicking , 2001 .