Loosely Coupled Kalman Filtering for Fusion of Visual Odometry and Inertial Navigation

Date

2013-07-12

Author

Sirtkaya, Salim
Seymen, Burak
Alatan, Abdullah Aydın

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

382
views

0
downloads

Visual Odometry (VO) is the process of estimating the motion of a system using single or stereo cameras. Performance of VO is comparable to that of wheel odometers and GPS under certain conditions; therefore it is an accepted choice for integration with inertial navigation systems especially in GPS denied environments. In general, VO is integrated with the inertial sensors in a state estimation framework. Despite the various instances of estimation filters, the underlying concepts remain the same, an assumed kinematic model of the system is combined with measurements of the states of that system. The drawback of using kinematic models for state transition is that the state estimate will only be as good as the precision of the model used in the filter. A common approach in navigation community is to use an error propagation model of the navigation solution using inertial sensor instead of an assumed dynamical model. High rate IMU will trace the dynamic better than an assumed model. In this paper, we propose a loosely coupled indirect feedback Kalman filter integration for visual odometry and inertial navigation system that is based on error propagation model and takes into account different characteristics of individual sensors for optimum performance, reliability and robustness. Two measurement models are derived for the accumulated and incremental visual odometry measurements. A practical measurement model approach is proposed for the delta position and attitude change measurements that inherently includes delayed-state. The non-Gaussian, non-stationary and correlated error characteristics of VO, that is not suitable to model in a standard Kalman filter, is tackled with averaging the measurements over a Kalman period and utilizing a sigma-test within the filter.

URI

https://hdl.handle.net/11511/52767

Collections

Department of Electrical and Electronics Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

3D Object Modeling by Structured Light and Stereo Vision Ozenc, Ugur; Tastan, Oguzhan; GÜLLÜ, MEHMET KEMAL (2015-05-19) In this paper, we demonstrate a 3D object modeling system utilizing a setup which consists of two CMOS cameras and a DLP projector by making use of structured light and stereo vision. The calibration of the system is carried out using calibration pattern. The images are taken with stereo camera pair by projecting structured light onto the object and the correspondence problem is solved by both epipolar constraint of stereo vision and gray code constraint of structured light. The first experimental results s...
Opti-acoustic stereo imaging Saç, Hakan; Leblebicioğlu, Mehmet Kemal; Salor Durna, Özgül; Department of Electrical and Electronics Engineering (2012) In this thesis, opti-acoustic stereo imaging, which is the deployment of two-dimensional (2D) high frequency imaging sonar with the electro-optical camera in calibrated stereo configuration, is studied. Optical cameras give detailed images in clear waters. However, in dark or turbid waters, information coming from electro-optical sensor is insufficient for accurate scene perception. Imaging sonars, also known as acoustic cameras, can provide enhanced target details under these scenarios. To illustrate these...
Good features to correlate for visual tracking Gündoğdu, Erhan; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2017) Estimating object motion is one of the key components of video processing and the first step in applications which require video representation. Visual object tracking is one way of extracting this component, and it is one of the major problems in the field of computer vision. Numerous discriminative and generative machine learning approaches have been employed to solve this problem. Recently, correlation filter based (CFB) approaches have been popular due to their computational efficiency and notable perfo...
Method and Apparatus for Frame Interpolation Alatan , Abdullah Aydın; Gedik, Osman Serdar (USP, 2010) The invention generally provides a method and apparatus for up-converting the frame rate of a digital video signal, the method comprising: receiving a digital video signal containing a first frame and a second frame; finding in one of the received frames, matches for objects in the other of the received frames; utilising 3 dimensional position data in respect of the objects within the frames to determine 3 dimensional movement matrices for the matched objects; using the 3 dimensional movement matrices, dete...
Manual and auto calibration of stereo camera systems Özuysal, Mustafa; Halıcı, Uğur; Department of Electrical and Electronics Engineering (2004) To make three dimensional measurements using a stereo camera system, the intrinsic and extrinsic calibration of the system should be obtained. Furthermore, to allow zooming, intrinsic parameters should be re-estimated using only scene constraints. In this study both manual and autocalibration algorithms are implemented and tested. The implemented manual calibration system is used to calculate the parameters of the calibration with the help of a planar calibration object. The method is tested on different in...

Citation Formats

S. Sirtkaya, B. Seymen, and A. A. Alatan, “Loosely Coupled Kalman Filtering for Fusion of Visual Odometry and Inertial Navigation,” 2013, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/52767.