Abstract
Depth estimation from monocular image plays an essential role in artificial intelligence, which is one of the important ways for sensing the operating environment in automatic-driving system or advanced driving assistant system. The most recent approaches have gained significant improvement for depth prediction based on convolutional neural networks (CNNs). In this paper, a novel framework of CNNs is proposed for monocular depth estimation based on deep ordinal regression network (DORN) and a U-net structure. The new model is trained, verified in process and tested on 5000 images from a simulation experiment platform provide by “Grand Theft Auto”. To eliminate or at least largely reduce the impact from ground truth with no depth values, three different training strategies were employed for network optimization. We developed an effective weighted training strategy for depth prediction to improve the estimation accuracy. The comparison of evaluations over our results and DORN demonstrated the effectiveness of our method. The results showed that the proposed method achieved state-of-the-art performances.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rupprecht LC, Belagiannis V, Tombari F, Navab N (2016) Deeper depth prediction with fully convolutional residual networks. In: Fourth international conference on 3D Vision (3DV), vol 1, pp 239–248
Shelhamer E, Long J, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640–651
Tateno K, Tombari F, Laina I, Navab N (2017) CNN-SLAM: real-time dense monocular SLAM with learned depth prediction. In: IEEE conference on computer vision and pattern recognition, pp 6565–6574
Wang P, Shen X, Lin Z, Cohen S, Yuille A (2015) Towards unified depth and semantic prediction from a single image. In: IEEE conference on computer vision and pattern recognition
Li B, Dai Y, He M (2018) Monocular depth estimation with hierarchical fusion of dilated CNNs and soft-weighted-sum inference. Pattern Recogn 83:328–339
Cao Y, Wu Z, Shen C (2018) Estimating depth from monocular images as classification using deep fully convolutional residual networks. IEEE Trans Circuits Syst Video Technol 28(11):3174–3182
Li R, Xian K, Shen C, Cao Z, Lu H, Hang L (2018) Deep attention-based classification network for robust depth prediction. In: IEEE conference on computer vision and pattern recognition (CVPR)
Liu F, Shen C, Lin G (2015) Deep convolutional neural fields for depth estimation from a single image. In: IEEE conference on computer vision and pattern recognition
Li B, Shen C, Dai Y, Hengel AVD, He M (2015) Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs. In: IEEE conference on computer vision and pattern recognition
Dan X, Ricci E, Ouyang W, Wang X, Sebe N (2017) Multi-scale continuous CRFs as sequential deep networks for monocular depth estimation. In: IEEE conference on computer vision and pattern recognition
Fu H, Gong M, Wang C, Batmanghelich K, Tao D (2018) Deep ordinal regression network for monocular depth estimation. In: IEEE conference on computer vision and pattern recognition, pp 2002–2011
Chen W, Zhao F, Yang D, Jia D (2015) Single-image depth perception in the wild. In: IEEE conference on computer vision and pattern recognition
Garg R, Vijay Kumar BG, Carneiro G, Reid I (2016) Unsupervised CNN for single view depth estimation: geometry to the rescue. In: European conference on computer vision
Godard C, Aodha OM, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency. In: IEEE conference on computer vision and pattern recognition
Kuznietsov GJ, Stückler J, Leibe B (2017) Semi-supervised deep learning for monocular depth map prediction. In: IEEE conference on computer vision and pattern recognition
Uhrig J, Schneider N, Schneider L, Franke U, Brox T, Geiger A (2017) Sparsity invariant CNNs. In: 2017 international conference on 3D Vision (3DV), pp 11–20
Fischer RP, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: IEEE conference on computer vision and pattern recognition
Chollet F, Keras. In: GitHub. https://github.com/fchollet/keras
Abadi M et al (2016) TensorFlow: large-scale machine learning on heterogeneous distributed systems. In: Distributed, parallel, and cluster computing
Sanner MF (1999) Python: a programming language for software integration and development. J Mol Graph Model 17(1):57–61
Meng L (2014) Acceleration method of 3D medical images registration based on compute unified device architecture. Bio-Med Mater Eng 24(1):1109–1116
Acknowledgements
this research is supported by Natural Science Foundation of Beijing “Research on the Planning Decision Making Supporting Approaches of Healthy City Planning of Beijing Based on the Analysis of Social Sensing Data” (No. 8182027), and open fund of Institute for China Sustainable Urbanization, Tsinghua University:“Pre-study on new urban development strategy integrating multi-source big data” (TUCSU-K-17026-01). We are also grateful for the computational resources provided by GTA.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kang, J. et al. (2020). An Improved Convolutional Neural Network for Monocular Depth Estimation. In: Wang, W., Baumann, M., Jiang, X. (eds) Green, Smart and Connected Transportation Systems. Lecture Notes in Electrical Engineering, vol 617. Springer, Singapore. https://doi.org/10.1007/978-981-15-0644-4_94
Download citation
DOI: https://doi.org/10.1007/978-981-15-0644-4_94
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-0643-7
Online ISBN: 978-981-15-0644-4
eBook Packages: EngineeringEngineering (R0)