Unsupervised Learning of Monocular Depth and Ego-Motion Using Multiple Masks

A new unsupervised learning method of depth and ego-motion using multiple masks from monocular video is proposed in this paper. The depth estimation network and the ego-motion estimation network are trained according to the constraints of depth and ego-motion without truth values. The main contribution of our method is to carefully consider the occlusion of the pixels generated when the adjacent frames are projected to each other, and the blank problem generated in the projection target imaging plane. Two fine masks are designed to solve most of the image pixel mismatch caused by the movement of the camera. In addition, some relatively rare circumstances are considered, and repeated masking is proposed. To some extent, the method is to use a geometric relationship to filter the mismatched pixels for training, making unsupervised learning more efficient and accurate. The experiments on KITTI dataset show our method achieves good performance in terms of depth and ego-motion. The generalization capability of our method is demonstrated by training on the low-quality uncalibrated bike video dataset and evaluating on KITTI dataset, and the results are still good.

[1]  Jan Kautz,et al.  Loss Functions for Image Restoration With Neural Networks , 2017, IEEE Transactions on Computational Imaging.

[2]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[3]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[4]  Anelia Angelova,et al.  Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  Federico Tombari,et al.  CNN-SLAM: Real-Time Dense Monocular SLAM with Learned Depth Prediction , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Oisin Mac Aodha,et al.  Unsupervised Monocular Depth Estimation with Left-Right Consistency , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Noah Snavely,et al.  Unsupervised Learning of Depth and Ego-Motion from Video , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

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

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

[12]  Nassir Navab,et al.  Deeper Depth Prediction with Fully Convolutional Residual Networks , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[13]  Dongbing Gu,et al.  UnDeepVO: Monocular Visual Odometry Through Unsupervised Deep Learning , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).