High-performance visual odometry with two-stage local binocular BA and GPU

Lü, Wei; Xiang, Zhiyu; Liu, Jilin

doi:10.1109/ivs.2013.6629614

Cited by 25 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As argued by Song et al this is in general not practical for automotive applications [1]. Alternative approaches keeping track solely of recent map information have become more popular in recent years [1], [4], [5], [5], [17].…”

Section: Related Workmentioning

confidence: 99%

“…This approach simplifies the fusion of ancillary sensors such as IMUs, but complicates the process to revert associations retroactively [20], [21], [22], [23]. The main alternative to this approach is to instead rely on a bundle adjustment step to refine the map and camera poses by minimizing the total reprojection error [24], [4], [11], [5].…”

Section: Related Workmentioning

confidence: 99%

“…Stereo systems, on the other hand, can rely on the known transformation between the two cameras to extract the metric scale and on the redundancy of the visual data to improve stability and robustness [4], [25], [17], [12], [5], [13].…”

Section: Related Workmentioning

confidence: 99%

“…The KITTI dataset in particular is currently the most popular one, partly thanks to the benchmark test made available by the authors [3]. The top performing visual-only systems to date are all stereo based papers [4], [17], [13], [5]. An exception to this rule is given by the work of Song et al which is among the best scoring systems despite relying on monocular data [1].…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Robust stereo visual odometry from monocular techniques

Persson

Piccini

Felsberg

et al. 2015

2015 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Abstract-Visual odometry is one of the most active topics in computer vision. The automotive industry is particularly interested in this field due to the appeal of achieving a high degree of accuracy with inexpensive sensors such as cameras. The best results on this task are currently achieved by systems based on a calibrated stereo camera rig, whereas monocular systems are generally lagging behind in terms of performance. We hypothesise that this is due to stereo visual odometry being an inherently easier problem, rather than than due to higher quality of the state of the art stereo based algorithms. Under this hypothesis, techniques developed for monocular visual odometry systems would be, in general, more refined and robust since they have to deal with an intrinsically more difficult problem.In this work we present a novel stereo visual odometry system for automotive applications based on advanced monocular techniques. We show that the generalization of these techniques to the stereo case result in a significant improvement of the robustness and accuracy of stereo based visual odometry. We support our claims by the system results on the well known KITTI benchmark, achieving the top rank for visual only systems * .

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Robust stereo visual odometry from monocular techniques

Persson

Piccini

Felsberg

et al. 2015

2015 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

show abstract

“…All the k t in this paper denotes the k instant of data fusion process. 2) Vision relative motion: The procedure of VNS mainly includes feature extraction, feature tracking, stereo matching, 3D reconstruction and motion estimation [9,10,11]. By 3D reconstruction, the coordinates of feature points in c-frame are are the vision relative motion parameters in c-frame, which can be calculated as follows: as:…”

Section: A Measurement Of the Relative Motion Differencementioning

confidence: 99%

An Improved INS/VNS Integrated Navigation Measurement Model for Lunar Rover

Xu¹,

Ning²

2014

Proceedings of the 2014 International Conference on Mechatronics, Electronic, Industrial and Control Engineering

View full text Add to dashboard Cite

Abstract-The INS/VNS integrated navigation is an important autonomous navigation method for lunar rovers.The INS/VNS models usually utilize the relative motion differences between the inertial and the vision as measurements. Traditional INS/VNS models make an approximation between definitions of the inertial measured attitude error and the misalignment angle to simplify the measurement model of relative rotation difference. This paper finds that the norm of the approximation error can exceed the norm of misalignment angle when the yaw is large, which cannot be ignored. Furthermore, an improved measurement model without that approximation is presented, in which the definition of inertial measured attitude error and the misalignment angle is accurately matched. Lunarbased simulation and earth-based experiment both demonstrate that the presented model is effective and the method used the proposed model can achieve higher accuracy of positions and attitudes than that used the traditional model.

show abstract

Active Stereo Vision

Hogue

Jenkin

2020

Computer Vision

View full text Add to dashboard Cite

High-performance visual odometry with two-stage local binocular BA and GPU

Cited by 25 publications

References 13 publications

Robust stereo visual odometry from monocular techniques

Robust stereo visual odometry from monocular techniques

An Improved INS/VNS Integrated Navigation Measurement Model for Lunar Rover

Active Stereo Vision

Contact Info

Product

Resources

About