scholarly journals Development of Stereo Visual Odometry Based on Photogrammetric Feature Optimization

2019 ◽  
Vol 11 (1) ◽  
pp. 67 ◽  
Author(s):  
Sung-Joo Yoon ◽  
Taejung Kim
Keyword(s):  
Pose Estimation ◽  
Automobile Industry ◽  
Visual Odometry ◽  
Geometric Interpretation ◽  
Bundle Adjustment ◽  
Processing Technologies ◽  
Extraction Step ◽  
Feature Optimization ◽  
Institute Of Technology ◽  
Stereo Visual Odometry

One of the important image processing technologies is visual odometry (VO) technology. VO estimates platform motion through a sequence of images. VO is of interest in the virtual reality (VR) industry as well as the automobile industry because the construction cost is low. In this study, we developed stereo visual odometry (SVO) based on photogrammetric geometric interpretation. The proposed method performed feature optimization and pose estimation through photogrammetric bundle adjustment. After corresponding the point extraction step, the feature optimization was carried out with photogrammetry-based and vision-based optimization. Then, absolute orientation was performed for pose estimation through bundle adjustment. We used ten sequences provided by the Karlsruhe institute of technology and Toyota technological institute (KITTI) community. Through a two-step optimization process, we confirmed that the outliers, which were not removed by conventional outlier filters, were removed. We also were able to confirm the applicability of photogrammetric techniques to stereo visual odometry technology.

Stereo visual odometry with velocity constraint for ground vehicle applications

2021 ◽  
pp. 1-13
Author(s):  
Fei Liu ◽  
Yashar Balazadegan Sarvrood ◽  
Yue Liu ◽  
Yang Gao
Keyword(s):  
Angular Rate ◽  
Visual Odometry ◽  
Land Vehicles ◽  
Position Errors ◽  
Error Mitigation ◽  
Institute Of Technology ◽  
Velocity Constraints ◽  
The Right ◽  
Velocity Constraint ◽  
Stereo Visual Odometry

Abstract This paper proposes a novel method of error mitigation for stereo visual odometry (VO) applied in land vehicles. A non-holonomic constraint (NHC), which imposes physical constraint to the rightward velocity of a land vehicle, is implemented as an observation in an extended Kalman filter (EKF) to reduce the drift of stereo VO. The EKF state vector includes position errors in an Earth-centred, Earth-fixed (ECEF) frame, velocity errors in the camera frame, angular rate errors and attitude errors. All the related equations are described and presented in detail. In this approach, no additional sensors are used but NHC, namely velocity constraint in the right direction , is applied as an external measurement to improve the accuracy. Tests are conducted with the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) datasets. Results show that the relative horizontal positioning error improved from 0⋅63% to 0⋅22% on average with the application of the velocity constraints. The maximum and root mean square of the horizontal error with velocity constraints are both reduced to less than half of the error with stand-alone stereo VO.

scholarly journals ENHANCEMENT STRATEGIES FOR FRAME-TO-FRAME UAS STEREO VISUAL ODOMETRY

2016 ◽  
Vol XLI-B3 ◽  
pp. 511-518
Author(s):  
J. Kersten ◽  
V. Rodehorst
Keyword(s):  
Outlier Detection ◽  
Autonomous Navigation ◽  
Visual Odometry ◽  
Bundle Adjustment ◽  
Unmanned Aircraft ◽  
Estimation Errors ◽  
Keyframe Selection ◽  
Reduction Strategies ◽  
The Impact ◽  
Stereo Visual Odometry

Autonomous navigation of indoor unmanned aircraft systems (UAS) requires accurate pose estimations usually obtained from indirect measurements. Navigation based on inertial measurement units (IMU) is known to be affected by high drift rates. The incorporation of cameras provides complementary information due to the different underlying measurement principle. The scale ambiguity problem for monocular cameras is avoided when a light-weight stereo camera setup is used. However, also frame-to-frame stereo visual odometry (VO) approaches are known to accumulate pose estimation errors over time. Several valuable real-time capable techniques for outlier detection and drift reduction in frame-to-frame VO, for example robust relative orientation estimation using random sample consensus (RANSAC) and bundle adjustment, are available. This study addresses the problem of choosing appropriate VO components. We propose a frame-to-frame stereo VO method based on carefully selected components and parameters. This method is evaluated regarding the impact and value of different outlier detection and drift-reduction strategies, for example keyframe selection and sparse bundle adjustment (SBA), using reference benchmark data as well as own real stereo data. The experimental results demonstrate that our VO method is able to estimate quite accurate trajectories. Feature bucketing and keyframe selection are simple but effective strategies which further improve the VO results. Furthermore, introducing the stereo baseline constraint in pose graph optimization (PGO) leads to significant improvements.

scholarly journals ENHANCEMENT STRATEGIES FOR FRAME-TO-FRAME UAS STEREO VISUAL ODOMETRY

2016 ◽  
Vol XLI-B3 ◽  
pp. 511-518
Author(s):  
J. Kersten ◽  
V. Rodehorst
Keyword(s):  
Outlier Detection ◽  
Autonomous Navigation ◽  
Visual Odometry ◽  
Bundle Adjustment ◽  
Unmanned Aircraft ◽  
Estimation Errors ◽  
Keyframe Selection ◽  
Reduction Strategies ◽  
The Impact ◽  
Stereo Visual Odometry

Autonomous navigation of indoor unmanned aircraft systems (UAS) requires accurate pose estimations usually obtained from indirect measurements. Navigation based on inertial measurement units (IMU) is known to be affected by high drift rates. The incorporation of cameras provides complementary information due to the different underlying measurement principle. The scale ambiguity problem for monocular cameras is avoided when a light-weight stereo camera setup is used. However, also frame-to-frame stereo visual odometry (VO) approaches are known to accumulate pose estimation errors over time. Several valuable real-time capable techniques for outlier detection and drift reduction in frame-to-frame VO, for example robust relative orientation estimation using random sample consensus (RANSAC) and bundle adjustment, are available. This study addresses the problem of choosing appropriate VO components. We propose a frame-to-frame stereo VO method based on carefully selected components and parameters. This method is evaluated regarding the impact and value of different outlier detection and drift-reduction strategies, for example keyframe selection and sparse bundle adjustment (SBA), using reference benchmark data as well as own real stereo data. The experimental results demonstrate that our VO method is able to estimate quite accurate trajectories. Feature bucketing and keyframe selection are simple but effective strategies which further improve the VO results. Furthermore, introducing the stereo baseline constraint in pose graph optimization (PGO) leads to significant improvements.

scholarly journals Event-Based Stereo Visual Odometry

2021 ◽  
pp. 1-18
Author(s):  
Yi Zhou ◽  
Guillermo Gallego ◽  
Shaojie Shen
Keyword(s):  
Visual Odometry ◽  
Event Based ◽  
Stereo Visual Odometry

Towards Estimating Bias in Stereo Visual Odometry

2014 ◽  
Author(s):  
Sara Farboud-Sheshdeh ◽  
Timothy D. Barfoot ◽  
Raymond H. Kwong
Keyword(s):  
Visual Odometry ◽  
Stereo Visual Odometry

scholarly journals INTEGRATION OF A GENERALISED BUILDING MODEL INTO THE POSE ESTIMATION OF UAS IMAGES

2016 ◽  
Vol XLI-B1 ◽  
pp. 1057-1064 ◽  
Author(s):  
J. Unger ◽  
F. Rottensteiner ◽  
C. Heipke
Keyword(s):  
Pose Estimation ◽  
Image Sequence ◽  
Image Sequences ◽  
Bundle Adjustment ◽  
Unmanned Aerial System ◽  
Real Image ◽  
Building Model ◽  
Current State ◽  
Image Orientation

A hybrid bundle adjustment is presented that allows for the integration of a generalised building model into the pose estimation of image sequences. These images are captured by an Unmanned Aerial System (UAS) equipped with a camera flying in between the buildings. The relation between the building model and the images is described by distances between the object coordinates of the tie points and building model planes. Relations are found by a simple 3D distance criterion and are modelled as fictitious observations in a Gauss-Markov adjustment. The coordinates of model vertices are part of the adjustment as directly observed unknowns which allows for changes in the model. Results of first experiments using a synthetic and a real image sequence demonstrate improvements of the image orientation in comparison to an adjustment without the building model, but also reveal limitations of the current state of the method.

Stereo Visual Odometry for Urban Vehicles Using Ground Features

2015 ◽  
pp. 385-397 ◽  
Author(s):  
Arturo de la Escalera ◽  
Ebroul Izquierdo ◽  
David Martín ◽  
Fernando García ◽  
José María Armingol
Keyword(s):  
Visual Odometry ◽  
Stereo Visual Odometry

REAL-TIME PHOTOGRAMMETRY AT THE DIGITAL PHOTOGRAMMETRIC STATION (DIPS) OF ETH ZURICH

1987 ◽  
Vol 41 (2) ◽  
pp. 181-199 ◽  
Author(s):  
Armin W. Gruen ◽  
Horst A. Beyer
Keyword(s):  
Real Time ◽  
Three Dimensional ◽  
Development Program ◽  
Bundle Adjustment ◽  
Object Distance ◽  
Federal Institute ◽  
Adjustment Program ◽  
Three Dimensional Measurement ◽  
Institute Of Technology ◽  
Processing Steps

Real-time photogrammetry (RTP) is a non-contact three-dimensional measurement technique with a response time of one video cycle. As part of a research and development program for digital and real-time photogrammetry, the Institute of Geodesy and Photogrammety at the Swiss Federal Institute of Technology, Zurich, Switzerland, has established the Digital Photogrammetric Station (DIPS). The hardware and software of this development system is explained. Hardware aspects of solid-state cameras relevant to camera calibration for RTP are discussed. An off-line bundle adjustment program with additional parameters has been installed. An initial calibration and point positioning test using this program and existing image processing algorithms has been performed. The processing steps and results are analyzed. Accuracies, as computed from object space check points, in planimetry of 1:5000 or 0.09 pixel pitch, in depth of 0.08%c of object distance, have been achieved.

Sign in / Sign up

Export Citation Format

Share Document