Abstract
We propose a novel architecture for learning camera poses from image sequences with an extended 2D LSTM (Long Short-Term Memory). Unlike most of the previous deep learning based VO (Visual Odometry) methods, our model predicts the pose per frame with temporal information from image sequences by adopting a forward-backward process. In addition, we use 3D tensors as basic structures to generate spatial information. The network learns poses in a bottom-up manner by coupling local and global constraints. Experiments demonstrate that on the public KITTI benchmark dataset, our architecture outperforms the state-of-the-art end-to-end methods in term of camera motion prediction and is comparable with model-based methods. The network generalizes well on the Málaga dataset without extra training or fine-tuning.
Keywords
This work was done when Fei Xue was a student in Key Laboraory of Machine Perception, Peking University. The work was supported by the National Key Research and Development Program of China (2017YFB1002601) and National Natural Science Foundation of China (61632003, 61771026).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Blanco-Claraco, J.L., Moreno-Dueñas, F.Á., González-Jiménez, J.: The Málaga urban dataset: high-rate stereo and LiDAR in a realistic urban scenario. IJRR 33, 207–214 (2014)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: ICEMNLP (2014)
Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. TPAMI 40(3), 611–625 (2018)
Engel, Jakob, Schöps, Thomas, Cremers, Daniel: LSD-SLAM: large-scale direct monocular SLAM. In: Fleet, David, Pajdla, Tomas, Schiele, Bernt, Tuytelaars, Tinne (eds.) ECCV 2014. LNCS, vol. 8690, pp. 834–849. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10605-2_54
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? CVPR, the KITTI vision benchmark suite (2012)
Geiger, A., Ziegler, J., Stiller, C.: StereoScan: dense 3D reconstruction in real-time. In: IV (2011)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Li, R., Wang, S., Long, Z., Gu, D.: UnDeepVO: monocular visual odometry through unsupervised deep learning. In: ICRA (2018)
Mur-Artal, R., Tardós, J.D.: ORB-SLAM2: An Open-source SLAM System for Monocular, Stereo, and RGB-D Cameras. T-RO (2017)
Paszke, A., Gross, S., Chintala, S., Chanan, G.: Pytorch (2017). https://github.com/pytorch/pytorch
Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. TSP 45(11), 2673–2681 (1997)
Shi, X., Chen, Z., Wang, H., Yeung, D., Wong, W., Woo, W.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: NIPS (2015)
Wang, S., Clark, R., Wen, H., Trigoni, N.: DeepVO: towards end-to-end visual odometry with deep recurrent convolutional neural networks. In: ICRA (2017)
Wang, S., Clark, R., Wen, H., Trigoni, N.: End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks. IJRR 37(4–5), 513–542 (2018)
Yang, N., Wang, R., Stückler, J., Cremers, D.: Deep virtual stereo odometry: leveraging deep depth prediction for monocular direct sparse odometry. In: ECCV (2018)
Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth optical flow and camera pose. In: CVPR (2018)
Zhan, H., Garg, R., Saroj Weerasekera, C., Li, K., Agarwal, H., Reid, I.: Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction. In: CVPR (2018)
Zhou, H., Ummenhofer, B., Brox, T.: DeepTAM: deep tracking and mapping. In: ECCV (2018)
Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR (2017)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Xue, F., Wang, X., Wang, Q., Wang, J., Zha, H. (2019). Visual Odometry with Deep Bidirectional Recurrent Neural Networks. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2019. Lecture Notes in Computer Science(), vol 11859. Springer, Cham. https://doi.org/10.1007/978-3-030-31726-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-31726-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-31725-6
Online ISBN: 978-3-030-31726-3
eBook Packages: Computer ScienceComputer Science (R0)