Learning Depth-Aware Deep Representations for Robotic Perception

IEEE Robotics and Automation Letters

Volumn 2, Issue 2, 2017, Pages 468-475

  Porzi, Lorenzo ^a,b   Buló, Samuel Rota ^b   Penate Sanchez, Adrian ^c   Ricci, Elisa ^a,b   Moreno Noguer, Francesc ^d  

^a UNIVERSITY OF PERUGIA   (Italy)

^b FONDAZIONE BRUNO KESSLER   (Italy)

^c UNIVERSITY COLLEGE LONDON   (United Kingdom)

^d INSTITUT DE ROBÒTICA I INFORMÀTICA INDUSTRIAL CSIC UPC   (Spain)

Author keywords

RGB D perception; visual learning

Indexed keywords

NETWORK ARCHITECTURE; NEURAL NETWORKS; ROBOTICS; SEMANTICS;

CONTOUR DETECTION; CONVOLUTIONAL NEURAL NETWORK; DEEP ARCHITECTURES; FEATURE REPRESENTATION; OBJECT COORDINATES; ROBOTICS APPLICATIONS; SEMANTIC SEGMENTATION; VISUAL LEARNING;

OBJECT DETECTION;

EID: 85029592770     PISSN: None     EISSN: 23773766     Source Type: Journal    
DOI: 10.1109/LRA.2016.2637444     Document Type: Article

References (41)

1. D. Eigen, C. Puhrsch, and R. Fergus, "Depth map prediction from a single image using amulti-scale deep network," in Proc. Adv. Neural Inf. Process. Syst., 2014, pp. 2366-2374.
2. S. Yang, D. Maturana, and S. Scherer, "Real-time 3D scene layout from a single image using convolutional neural networks," in Proc. Int. Conf. Robot. Autom., 2016, pp. 2183-2189.
3. P. Alcantarilla, S. Stent, G. Ros, R. Arroyo, and R. Gherardi, "Street-view change detection with deconvolutional networks," in Proc. Robot. Sci. Syst., 2016, doi:10.15607/RSS.2016.XII.044.
4. N. Suenderhauf et al., "Place recognition with convnet landmarks: Viewpoint-robust, condition-robust, training-free," in Proc. Robot. Sci. Syst., 2015, doi:10.15607/RSS.2015.XI.022.
5. A. Kendall and R. Cipolla, "Modelling uncertainty in deep learning for camera relocalization," in Proc. Int. Conf. Robot. Autom., 2016, pp. 4762-4769.
6. A. Rubio et al., "Efficient monocular pose estimation for complex 3D models," in Proc. Int. Conf. Robot. Autom., 2015, pp. 1397-1402.
7. S. Gupta, R. Girshick, P. Arbeláez, and J. Malik, "Learning rich features from RGB-D images for object detection and segmentation," in Proc. Eur. Conf. Comput. Vis., 2014, pp. 345-360.
8. D. Maturana and S. Scherer, "Voxnet: A 3D convolutional neural network for real-time object recognition," in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2015, pp. 922-928.
9. A. Eitel, J. T. Springenberg, L. Spinello, M. Riedmiller, and W. Burgard, "Multimodal deep learning for robust RGB-D object recognition," in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2015, pp. 681-687.
10. H. Schulz, N. Höft, and S. Behnke, "Depth and height aware semantic RGB-D perception with convolutional neural networks," in Proc. Eur. Symp. Artif. Neural Netw., 2015, pp. 463-468.
11. E. Johns, S. Leutenegger, and A. J. Davison, "Deep learning a grasp function for grasping under gripper pose uncertainty," in Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 2016, pp. 4461-4468.
12. A. Myers, C. L. Teo, C. Fermüller, and Y. Aloimonos, "Affordance detection of tool parts from geometric features," in Proc. Int. Conf. Robot. Autom., 2015, pp. 1374-1381.
13. E. Brachmann, A. Krull, F. Michel, S. Gumhold, J. Shotton, and C. Rother, "Learning 6D object pose estimation using 3D object coordinates," in Proc. 13th Eur. Conf. Comput. Vis., 2014, pp. 536-551.
14. A. Krull, E. Brachmann, F. Michel, M. Y. Yang, S. Gumhold, and C. Rother, "Learning analysis-by-synthesis for 6D pose estimation in RGB-D images," in Proc. Int. Conf. Comput. Vis., 2015, pp. 954-962.
15. P. Dollar and L. Zitnick, "Structured forests for fast edge detection," in Proc. Int. Conf. Comput. Vis., 2013, pp. 1841-1848.
16. S. Xie and Z. Tu, "Holistically-nested edge detection," in Proc. Int. Conf. Comput. Vis., 2015, pp. 1395-1403.
17. M. Jaderberg, K. Simonyan, A. Zisserman, and K. Kavukcuoglu, "Spatial transformer networks," in Proc. Adv. Neural Inf. Process. Syst., 2015, pp. 2017-2025.
18. J. Bruna and S. Mallat, "Invariant scattering convolution networks," IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, no. 8, pp. 1872-1886, Aug. 2013.
19. C. Couprie, C. Farabet, L. Najman, and Y. LeCun, "Indoor semantic segmentation using depth information," in Proc. Int. Conf. Learn. Representations, 2013, pp. 1-8.
20. E. Johns, S. Leutenegger, and A. J. Davison, "Pairwise decomposition of image sequences for active multi-view recognition," in Proc. Int. Conf. Comput. Vis. Pattern Recognit., 2016, pp. 3813-3822.
21. S. Gupta, P. Arbeláez, R. Girshick, and J. Malik, "Aligning 3D models to RGB-D images of cluttered scenes," in Proc. Int. Conf. Comput. Vis. Pattern Recognit., 2015, pp. 4731-4740.
22. A. Wang, J. Cai, J. Lu, and T.-J. Cham, "MMSS: Multi-modal sharable and specific feature learning for RGB-D object recognition," in Proc. Int. Conf. Comput. Vis., 2015, pp. 1125-1133.
23. P. Wohlhart and V. Lepetit, "Learning descriptors for object recognition and 3D pose estimation," in Proc. Int. Conf. Comput. Vis. Pattern Recognit., 2015, pp. 3109-3118.
24. R. Gens and P. M. Domingos, "Deep symmetry networks," in Proc. 27th Int. Conf. Neural Inf. Process. Syst., 2014, pp. 2537-2545.
25. D. Laptev, N. Savinov, J. M. Buhmann, and M. Pollefeys, "Ti-pooling: Transformation-invariant pooling for feature learning in convolutional neural networks," in Proc. Int. Conf. Comput. Vis. Pattern Recognit., 2016, pp. 289-297.
26. K. He, X. Zhang, S. Ren, and J. Sun, "Spatial pyramid pooling in deep convolutional networks for visual recognition," in Proc. 13th Eur. Conf. Comput. Vis., 2014, pp. 346-361.
27. L.-C. Chen, Y. Yang, J. Wang, W. Xu, and A. L. Yuille, "Attention to scale: Scale-aware semantic image segmentation," in Proc. Int. Conf. Comput. Vis. Pattern Recognit., 2015, pp. 3640-3649.
28. M. F. Stollenga, J. Masci, F. Gomez, and J. Schmidhuber, "Deep networks with internal selective attention through feedback connections," in Proc. Adv. Neural Inf. Process. Syst., 2014, pp. 3545-3553.
29. D. Eigen and R. Fergus, "Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture," in Proc. Int. Conf. Comput. Vis., 2015, pp. 2650-2658.
30. S. Li, J. Xing, Z. Niu, S. Shan, and S. Yan, "Shape driven kernel adaptation in convolutional neural network for robust facial traits recognition," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2015, pp. 222-230.
31. A. C. Muller and S. Behnke, "Learning depth-sensitive conditional random fields for semantic segmentation of RGB-D images," in Proc. 2014 IEEE Int. Conf. Robot. Autom., 2014, pp. 6232-6237.
32. M. Holschneider, R. Kronland-Martinet, J. Morlet, and P. Tchamitchian, "A real-time algorithm for signal analysis with the help of the wavelet transform," in Wavelets. New York, NY, USA: Springer, 1990, pp. 286-297.
33. S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," in Proc. Int. Conf. Mach. Learn., 2015, pp. 448-456.
34. S. Hinterstoisser et al., "Multimodal templates for real-time detection of texture-less objects in heavily cluttered scenes," in Proc. 2011 Int. Conf. Comput. Vis., 2011, pp. 858-865.
35. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," in Proc. Int. Conf. Learn. Representations, 2014, pp. 1-8.
36. V. Badrinarayanan, A. Handa, and R. Cipolla, "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation," arXiv preprint arXiv:1511.00561, 2015.
37. J. Jose Tarrio and S. Pedre, "Realtime edge-based visual odometry for a monocular camera," in Proc. 2015 IEEE Int. Conf. Comput. Vis., 2015, pp. 702-710.
38. L. Bose and A. Richards, "Fast depth edge detection and edge based RGB-D SLAM," in Proc. 2016 IEEE Int. Conf. Robot. Autom., 2016, pp. 1323-1330.
39. P. K. Nathan Silberman, D. Hoiem, and R. Fergus, "Indoor segmentation and support inference from RGBD images," in Proc. 12th Eur. Conf. Comput. Vis., 2012, pp. 746-760.
40. P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik, "Contour detection and hierarchical image segmentation," IEEE Trans. Pattern Anal. Mach., vol. 33, no. 5, pp. 898-916, May 2011.
41. R. Xiaofeng and L. Bo, "Discriminatively trained sparse code gradients for contour detection," in Proc. 25th Int. Conf. Neural Inf. Process. Syst., 2012, pp. 584-592.