publication . Article . Preprint . 2017

DPC-Net: Deep Pose Correction for Visual Localization

Valentin Peretroukhin; Jonathan Kelly;
Open Access
  • Published: 10 Sep 2017 Journal: IEEE Robotics and Automation Letters, volume 3, pages 2,424-2,431 (eissn: 2377-3774, Copyright policy)
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We present a novel method to fuse the power of deep networks with the computational efficiency of geometric and probabilistic localization algorithms. In contrast to other methods that completely replace a classical visual estimator with a deep network, we propose an approach that uses a convolutional neural network to learn difficult-to-model corrections to the estimator from ground-truth training data. To this end, we derive a novel loss function for learning SE(3) corrections based on a matrix Lie groups approach, with a natural formulation for balancing translation and rotation errors. We use this loss to train a Deep Pose Correction network (DPC-Net) that p...
Subjects
free text keywords: Distortion (optics), Estimator, Visual localization, Computer vision, Visual odometry, Odometry, Artificial intelligence, business.industry, business, Probabilistic logic, Computer science, Convolutional neural network, Fuse (electrical), Pattern recognition, Computer Science - Computer Vision and Pattern Recognition
Related Organizations
26 references, page 1 of 2

[10] [11] [12] [1] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436-444, 2015.

[2] V Peretroukhin, J Kelly, and T. D. Barfoot, “Optimizing camera perspective for stereo visual odometry,” in Canadian Conference on Comp. and Robot Vision, May 2014, pp. 1-7.

[3] V Peretroukhin, W Vega-Brown, N Roy, and J Kelly, “PROBE-GK: Predictive robust estimation using generalized kernels,” in Proc. IEEE Int. Conf. Robot. Automat. (ICRA), May 2016, pp. 817-824.

[4] V Peretroukhin, L Clement, M Giamou, and J Kelly, “PROBE: Predictive robust estimation for visual-inertial navigation,” in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Syst. (IROS), 2015, pp. 3668-3675.

[5] G Costante, M Mancini, P Valigi, and T. A. Ciarfuglia, “Exploring representation learning with CNNs for Frame-to-Frame Ego-Motion estimation,” IEEE Robot. Autom. Letters, vol. 1, no. 1, pp. 18-25, Jan. 2016, ISSN: 2377-3766.

[6] R. Clark, S. Wang, H. Wen, A. Markham, and N. Trigoni, “VINet: Visual-Inertial odometry as a Sequence-to-Sequence learning problem,” 2017. arXiv: 1701.08376 [cs.CV].

[7] A. Kendall and R. Cipolla, “Geometric loss functions for camera pose regression with deep learning,” 2017. arXiv: 1704.00390 [cs.CV].

[8] I. Melekhov, J. Ylioinas, J. Kannala, and E. Rahtu, “Relative camera pose estimation using convolutional neural networks,” 2017. arXiv: 1702.01381 [cs.CV]. [OpenAIRE]

[9] G. L. Oliveira, N. Radwan, W. Burgard, and T. Brox, “Topometric localization with deep learning,” 2017. arXiv: 1706 . 08775 [cs.CV].

V. Peretroukhin, L. Clement, and J. Kelly, “Reducing drift in visual odometry by inferring sun direction using a bayesian convolutional neural network,” in Proc. IEEE Int. Conf. Robot. Automat. (ICRA), May 2017.

D Scaramuzza and F Fraundorfer, “Visual odometry [tutorial],” IEEE Robot. Autom. Mag., vol. 18, no. 4, pp. 80-92, Dec. 2011. C Cadena, L Carlone, H Carrillo, Y Latif, D Scaramuzza, J Neira, I Reid, and J. J. Leonard, “Past, present, and future of simultaneous localization and mapping: Toward the Robust-Perception age,” IEEE Trans. Rob., vol. 32, no. 6, pp. 1309-1332, Dec. 2016. [OpenAIRE]

00 (3.7 km)1 02 (5.1 km)2 05 (2.2 km)3 Corr. Type Translation (m) Rotation (deg) Translation (%) Rotation (millideg / m) [13] S Levine, C Finn, T Darrell, and P Abbeel, “End-to-end training of deep visuomotor policies,” J. Mach. Learn. Res., 2016.

[14] Y. Duan, X. Chen, R. Houthooft, J. Schulman, and P. Abbeel, “Benchmarking deep reinforcement learning for continuous control,” in Proc. Int. Conf. on Machine Learning, ser. ICML'16, 2016, pp. 1329-1338.

[15] F. Yang, W. Choi, and Y. Lin, “Exploit all the layers: Fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers,” in Proc. IEEE Int. Conf. Comp. Vision and Pattern Recognition (CVPR), 2016, pp. 2129-2137.

[16] N. Sunderhauf, S. Shirazi, A. Jacobson, F. Dayoub, E. Pepperell, B. Upcroft, and M. Milford, “Place recognition with ConvNet landmarks: Viewpoint-robust, condition-robust, training-free,” in Proc. Robotics: Science and Systems XII, Jul. 2015.

26 references, page 1 of 2
Abstract
We present a novel method to fuse the power of deep networks with the computational efficiency of geometric and probabilistic localization algorithms. In contrast to other methods that completely replace a classical visual estimator with a deep network, we propose an approach that uses a convolutional neural network to learn difficult-to-model corrections to the estimator from ground-truth training data. To this end, we derive a novel loss function for learning SE(3) corrections based on a matrix Lie groups approach, with a natural formulation for balancing translation and rotation errors. We use this loss to train a Deep Pose Correction network (DPC-Net) that p...
Subjects
free text keywords: Distortion (optics), Estimator, Visual localization, Computer vision, Visual odometry, Odometry, Artificial intelligence, business.industry, business, Probabilistic logic, Computer science, Convolutional neural network, Fuse (electrical), Pattern recognition, Computer Science - Computer Vision and Pattern Recognition
Related Organizations
26 references, page 1 of 2

[10] [11] [12] [1] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436-444, 2015.

[2] V Peretroukhin, J Kelly, and T. D. Barfoot, “Optimizing camera perspective for stereo visual odometry,” in Canadian Conference on Comp. and Robot Vision, May 2014, pp. 1-7.

[3] V Peretroukhin, W Vega-Brown, N Roy, and J Kelly, “PROBE-GK: Predictive robust estimation using generalized kernels,” in Proc. IEEE Int. Conf. Robot. Automat. (ICRA), May 2016, pp. 817-824.

[4] V Peretroukhin, L Clement, M Giamou, and J Kelly, “PROBE: Predictive robust estimation for visual-inertial navigation,” in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Syst. (IROS), 2015, pp. 3668-3675.

[5] G Costante, M Mancini, P Valigi, and T. A. Ciarfuglia, “Exploring representation learning with CNNs for Frame-to-Frame Ego-Motion estimation,” IEEE Robot. Autom. Letters, vol. 1, no. 1, pp. 18-25, Jan. 2016, ISSN: 2377-3766.

[6] R. Clark, S. Wang, H. Wen, A. Markham, and N. Trigoni, “VINet: Visual-Inertial odometry as a Sequence-to-Sequence learning problem,” 2017. arXiv: 1701.08376 [cs.CV].

[7] A. Kendall and R. Cipolla, “Geometric loss functions for camera pose regression with deep learning,” 2017. arXiv: 1704.00390 [cs.CV].

[8] I. Melekhov, J. Ylioinas, J. Kannala, and E. Rahtu, “Relative camera pose estimation using convolutional neural networks,” 2017. arXiv: 1702.01381 [cs.CV]. [OpenAIRE]

[9] G. L. Oliveira, N. Radwan, W. Burgard, and T. Brox, “Topometric localization with deep learning,” 2017. arXiv: 1706 . 08775 [cs.CV].

V. Peretroukhin, L. Clement, and J. Kelly, “Reducing drift in visual odometry by inferring sun direction using a bayesian convolutional neural network,” in Proc. IEEE Int. Conf. Robot. Automat. (ICRA), May 2017.

D Scaramuzza and F Fraundorfer, “Visual odometry [tutorial],” IEEE Robot. Autom. Mag., vol. 18, no. 4, pp. 80-92, Dec. 2011. C Cadena, L Carlone, H Carrillo, Y Latif, D Scaramuzza, J Neira, I Reid, and J. J. Leonard, “Past, present, and future of simultaneous localization and mapping: Toward the Robust-Perception age,” IEEE Trans. Rob., vol. 32, no. 6, pp. 1309-1332, Dec. 2016. [OpenAIRE]

00 (3.7 km)1 02 (5.1 km)2 05 (2.2 km)3 Corr. Type Translation (m) Rotation (deg) Translation (%) Rotation (millideg / m) [13] S Levine, C Finn, T Darrell, and P Abbeel, “End-to-end training of deep visuomotor policies,” J. Mach. Learn. Res., 2016.

[14] Y. Duan, X. Chen, R. Houthooft, J. Schulman, and P. Abbeel, “Benchmarking deep reinforcement learning for continuous control,” in Proc. Int. Conf. on Machine Learning, ser. ICML'16, 2016, pp. 1329-1338.

[15] F. Yang, W. Choi, and Y. Lin, “Exploit all the layers: Fast and accurate cnn object detector with scale dependent pooling and cascaded rejection classifiers,” in Proc. IEEE Int. Conf. Comp. Vision and Pattern Recognition (CVPR), 2016, pp. 2129-2137.

[16] N. Sunderhauf, S. Shirazi, A. Jacobson, F. Dayoub, E. Pepperell, B. Upcroft, and M. Milford, “Place recognition with ConvNet landmarks: Viewpoint-robust, condition-robust, training-free,” in Proc. Robotics: Science and Systems XII, Jul. 2015.

26 references, page 1 of 2
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue