Abstract
Vision-based localization is one of the major aspects of industrial and space robotics. Though many sensing modalities exist for motion estimation, cameras have been used widely due to its availability and reduced cost. Visual odometry estimates the motion parameters of a camera through the images it captures. Multiple sensing modalities are fused to improve estimation accuracy with increased cost. With the success of deep learning architectures in the area of computer vision, one of the recent paradigm shift occurred in visual odometry is estimating motion using non-geometric schemes by the end-to-end manner. The different stages of the traditional visual odometry pipeline are estimated as a single function mapping input images to output 6 DoF pose of the camera. There are many ways to apply deep learning in visual odometry, one of the common techniques is through transfer learning. In this work, analysis has been done on traditional DeepVO and ResNetVO by incorporating a novel architecture splitting and independent learning scheme. The estimation results show the efficacy of the proposed algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kottath R, Narkhede P, Kumar V, Karar V, Poddar S (2017) Multiple model adaptive complementary filter for attitude estimation. Aerosp Sci Technol 69:574–581
Ettinger SM (2001) Design and implementation of autonomous vision-guided micro air vehicles. University of Florida
Nistér D, Naroditsky O, Bergen J (2004) Visual odometry. In: Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition, 2004. CVPR 2004. IEEE
Roberts R et al (2008) Memory-based learning for visual odometry. In: 2008 IEEE international conference on robotics and automation. IEEE
Memisevic R (2013) Learning to relate images. IEEE Trans Pattern Anal Mach Intell 35(8):1829–1846
Poddar S, Kottath R, Karar V (2019) Motion estimation made easy: evolution and trends in visual odometry. In: Recent advances in computer vision. Springer, pp 305–331
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Sardana R, Kottath R, Karar V, Poddar S (2019) Joint forward-backward visual odometry for stereo cameras. arXiv preprint arXiv:1912.10293
Kottath R et al (2017) Inertia constrained visual odometry for navigational applications. In: 2017 Fourth international conference on image information processing (ICIIP). IEEE
Wang C, Yuan Y, Wang Q (2019) Learning by inertia: self-supervised monocular visual odometry for road vehicles. In: ICASSP 2019–2019 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE
Godard C, Mac Aodha O, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Zhou T et al (2017) Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Xu Y, Wang Y, Guo L (2018) Unsupervised ego-motion and dense depth estimation with monocular video. In: 2018 IEEE 18th international conference on communication technology (ICCT). IEEE
Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The kitti vision benchmark suite. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 3354–3361
Costante G, Ciarfuglia TA (2018) LS-VO: learning dense optical subspace for robust visual odometry estimation. IEEE Robot Autom Lett 3(3):1735–1742
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kottath, R., Kaw, R., Poddar, S., Bhondekar, A.P., Karar, V. (2021). Independent Learning of Motion Parameters for Deep Visual Odometry. In: Gunjan, V.K., Zurada, J.M. (eds) Proceedings of International Conference on Recent Trends in Machine Learning, IoT, Smart Cities and Applications. Advances in Intelligent Systems and Computing, vol 1245. Springer, Singapore. https://doi.org/10.1007/978-981-15-7234-0_74
Download citation
DOI: https://doi.org/10.1007/978-981-15-7234-0_74
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-7233-3
Online ISBN: 978-981-15-7234-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)