Visual Odometry using Convolutional Neural Networks

Visual odometry is the process of tracking an agent’s motion over time using a visual sensor. The visual odometry problem has only been recently solved using traditional, non-machine-learning techniques. Despite the success of neural networks at many related problems such as object recognition, feature detection, and optical flow, visual odometry still has not been solved with a deep learning technique. This paper attempts to implement several Convolutional Neural Networks to solve the visual odometry problem and compare slight variations in data preprocessing. The work presented is a step toward reaching a legitimate neural network solution.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Michael Gassner,et al.  SVO: Semidirect Visual Odometry for Monocular and Multicamera Systems , 2017, IEEE Transactions on Robotics.

[3]  Tom Drummond,et al.  Faster and Better: A Machine Learning Approach to Corner Detection , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Debashish Chakravarty,et al.  DeepVO: A Deep Learning approach for Monocular Visual Odometry , 2016, ArXiv.

[5]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[7]  Daniel Cremers,et al.  Semi-dense visual odometry for AR on a smartphone , 2014, 2014 IEEE International Symposium on Mixed and Augmented Reality (ISMAR).

[8]  J. M. M. Montiel,et al.  ORB-SLAM: A Versatile and Accurate Monocular SLAM System , 2015, IEEE Transactions on Robotics.

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[11]  Haifeng Li,et al.  Robust monocular visual odometry using optical flows for mobile robots , 2016, CCC 2016.

[12]  Kilian Q. Weinberger,et al.  Snapshot Ensembles: Train 1, get M for free , 2017, ICLR.

[13]  Juan D. Tardós,et al.  ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras , 2016, IEEE Transactions on Robotics.

[14]  Jitendra Malik,et al.  Learning to See by Moving , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[15]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Thomas Brox,et al.  FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[18]  Andreas Geiger,et al.  Are we ready for autonomous driving? The KITTI vision benchmark suite , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Thomas Brox,et al.  FlowNet: Learning Optical Flow with Convolutional Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[20]  John D. Hunter,et al.  Matplotlib: A 2D Graphics Environment , 2007, Computing in Science & Engineering.

[21]  Berin Martini,et al.  Hardware accelerated convolutional neural networks for synthetic vision systems , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[22]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[23]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..