Semantic Scene Mapping with Spatio-temporal Deep Neural Network for Robotic Applications
- 334 Downloads
Semantic scene mapping is a challenge and significant task for robotic application, such as autonomous navigation and robot-environment interaction. In this paper, we propose a semantic pixel-wise mapping system for potential robotic applications. The system includes a novel spatio-temporal deep neural network for semantic segmentation and a Simultaneous Localisation and Mapping (SLAM) algorithm for 3D point cloud map. Their combination yields a 3D semantic pixel-wise map. The proposed network consists of Convolutional Neural Networks (CNNs) with two streams: spatial stream with images as the input and temporal stream with image differences as the input. Due to the use of both spatial and temporal information, it is called spatio-temporal deep neural network, which shows a better performance in both accuracy and robustness in semantic segmentation. Further, only keyframes are selected for semantic segmentation in order to reduce the computational burden for video streams and improve the real-time performance. Based on the result of semantic segmentation, a 3D semantic map is built up by using the 3D point cloud map from a SLAM algorithm. The proposed spatio-temporal neural network is evaluated on both Cityscapes benchmark (a public dataset) and Essex Indoor benchmark (a dataset we labelled ourselves manually). Compared with the state-of-the-art spatial only neural networks, the proposed network achieves better performances in both pixel-wise accuracy and Intersection over Union (IoU) for scene segmentation. The constructed 3D semantic map with our methods is accurate and meaningful for robotic applications.
KeywordsDeep learning Spatio-temporal neural network 3D semantic map Robotics
The authors would like to thank Robin Dowling for his support in experiments.
The first author has been financially supported by scholarship from China Scholarship Council.
Compliance with Ethical Standards
Conflict of Interest
The authors declare that they have no conflict of interest.
Informed consent was obtained from all individual participants included in the study.
Human and Animal Rights
This article does not contain any studies with human or animal subjects performed by the any of the authors.
- 1.Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition; 2015. p. 1–9.Google Scholar
- 2.He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 770–8.Google Scholar
- 3.Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition; 2015. p. 3431–40.Google Scholar
- 4.Zhao H, Shi J, Qi X, Wang X, Jia J. 2016. Pyramid scene parsing network. arXiv:1612.01105.
- 8.Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. Proceedings of the 3rd international conference on learning representations; 2015. p. 1–14.Google Scholar
- 9.Liu W, Rabinovich A, Berg AC. 2015. Parsenet: looking wider to see better. arXiv:1506.04579.
- 10.Badrinarayanan V, Kendall A, Cipolla R. 2015. Segnet: a deep convolutional encoder-decoder architecture for image segmentation. arXiv:1511.00561.
- 11.Kendall A, Badrinarayanan V, Cipolla R. 2015. Bayesian segnet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv:1511.02680.
- 12.Zheng S, Jayasumana S, Romera-Paredes B, Vineet V, Su Z, Du D, Huang C, Torr PH. Conditional random fields as recurrent neural networks. Proceedings of the IEEE international conference on computer vision; 2015. p. 1529–37.Google Scholar
- 13.Arnab A, Jayasumana S, Zheng S, Torr PH. Higher order conditional random fields in deep neural networks. European conference on computer vision. Springer; 2016. p. 524–40.Google Scholar
- 14.Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L. Imagenet: a large-scale hierarchical image database. IEEE conference on computer vision and pattern recognition, 2009. CVPR 2009. IEEE; 2009. p. 248–55.Google Scholar
- 15.Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL. 2014. Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv:1412.7062.
- 16.Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL. 2016. Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. arXiv:1606.00915.
- 17.Chen L-C, Yang Y, Wang J, Xu W, Yuille AL. Attention to scale: scale-aware semantic image segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 3640–9.Google Scholar
- 19.Wu Z, Shen C, Hengel AVD. 2016. High-performance semantic segmentation using very deep fully convolutional networks. arXiv:1604.04339.
- 20.Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B. The cityscapes dataset for semantic urban scene understanding. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 3213–23.Google Scholar
- 21.Wu Z, Shen C, Hengel AVD. 2016. Wider or deeper: revisiting the resnet model for visual recognition. arXiv:1611.10080.
- 22.Zhou B, Zhao H, Puig X, Fidler S, Barriuso A, Torralba A. 2016. Semantic understanding of scenes through the ade20k dataset. arXiv:1608.05442.
- 24.Doborjeh ZG, Doborjeh MG, Kasabov N. Attentional bias pattern recognition in spiking neural networks from spatio-temporal EEG data. Cogn Comput, 2017:1–14.Google Scholar
- 25.Wang S, Clark R, Wen H, Trigoni N. DeepVO: towards end-to-end visual odometry with deep recurrent convolutional neural networks. 2017 IEEE international conference on robotics and automation (ICRA). IEEE; 2017. p. 2043–50.Google Scholar
- 26.Wang L, Xiong Y, Wang Z, Qiao Y. 2015. Towards good practices for very deep two-stream convnets. arXiv:1507.02159.
- 27.Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L. Temporal segment networks: towards good practices for deep action recognition. European conference on computer vision. Springer; 2016. p. 20–36.Google Scholar
- 28.Li R, Liu Q, Gui J, Gu D, Hu H. 2017. Indoor relocalization in challenging environments with dual-stream convolutional neural networks. IEEE Trans Autom Sci Eng.Google Scholar
- 29.Eitel A, Springenberg JT, Spinello L, Riedmiller M, Burgard W. Multimodal deep learning for robust RGB-d object recognition. 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE; 2015. p. 681–7.Google Scholar
- 30.Schwarz M, Schulz H, Behnke S. RGB-D object recognition and pose estimation based on pre-trained convolutional neural network features. 2015 IEEE international conference on robotics and automation (ICRA). IEEE; 2015. p. 1329–35.Google Scholar
- 31.Hazirbas C, Ma L, Domokos C, Cremers D. Fusenet: incorporating depth into semantic segmentation via fusion-based CNN architecture. Proceedings of ACCV; 2016.Google Scholar
- 32.Valada A, Oliveira G, Brox T, Burgard W. Towards robust semantic segmentation using deep fusion. Robotics: science and systems (RSS 2016) workshop, are the sceptics right? Limits and potentials of deep learning in robotics; 2016.Google Scholar
- 33.Valada A, Vertens J, Dhall A, Burgard W. Adapnet: adaptive semantic segmentation in adverse environmental conditions. 2017 IEEE international conference on robotics and automation (ICRA). IEEE; 2017.Google Scholar
- 35.Salas-Moreno RF, Glocken B, Kelly PH, Davison AJ. Dense planar slam. 2014 IEEE international symposium on mixed and augmented reality (ISMAR). IEEE; 2014. p. 157–64.Google Scholar
- 36.Salas-Moreno RF, Newcombe RA, Strasdat H, Kelly PH, Davison AJ. Slam++: simultaneous localisation and mapping at the level of objects. Proceedings of the IEEE conference on computer vision and pattern recognition; 2013. p. 1352–9.Google Scholar
- 37.Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T. Caffe: convolutional architecture for fast feature embedding. Proceedings of the ACM international conference on multimedia. ACM; 2014. p. 675–8.Google Scholar
- 38.Mur-Artal R, Tardós JD. Fast relocalisation and loop closing in keyframe-based SLAM. 2014 IEEE international conference on robotics and automation (ICRA). IEEE; 2014. p. 846–53.Google Scholar