Skip to main content

Discriminative Deep Belief Network for Indoor Environment Classification Using Global Visual Features

Abstract

Indoor environment classification, also known as indoor environment recognition, is a highly appreciated perceptual ability in mobile robots. In this paper, we present a novel approach which is centered on biologically inspired methods for recognition and representation of indoor environments. First, global visual features are extracted by using the GIST descriptor, and then we use the subsequent features for training the discriminative deep belief network (DDBN) classifier. DDBN employs a new deep architecture which is based on restricted Boltzmann machines (RBMs) and the joint density model. The back-propagation technique is used over the entire classifier to fine-tune the weights for an optimum classification. The acquired experimental results validate our approach as it performs well both in the real-world and in synthetic datasets and outperforms the Convolution Neural Networks (ConvNets) in terms of computational efficiency.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Notes

  1. http://categorizingplaces.com/dataset.html

  2. https://keras.io/

References

  1. Aboudib A, Gripon V, Coppin G. A biologically inspired framework for visual information processing and an application on modeling bottom-up visual attention. Cogn Comput. 2016;8:1–20.

    Article  Google Scholar 

  2. Ackley DH, Hinton GE, Sejnowski TJ. A learning algorithm for boltzmann machines*. Cogn Sci. 1985; 9(1):147–169.

    Article  Google Scholar 

  3. Alexandre LA. 3d object recognition using convolutional neural networks with transfer learning between input channels. Intelligent Autonomous Systems 13. Springer; 2016. p. 889–898.

  4. Bengio Y. Learning deep architectures for ai. Found TrendsⓇ Mach Learn. 2009;2(1):1–127.

    Article  Google Scholar 

  5. Biederman I. 1981. On the semantics of a glance at a scene.

  6. Carpenter GA, Ross WD. Art-emap: A neural network architecture for object recognition by evidence accumulation. IEEE Trans Neural Netw. 1995;6(4):805–818.

    Article  PubMed  CAS  Google Scholar 

  7. Carreira-Perpinan MA, Hinton GE. On contrastive divergence learning. Proceedings of the tenth international workshop on artificial intelligence and statistics. Citeseer; 2005. p. 33–40.

  8. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. 2009. CVPR 2009. IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2009. p. 248–255.

  9. Deng L, Yu D. Deep learning: methods and applications. Found Trends Signal Process. 2014;7(3–4):197–387.

    Article  Google Scholar 

  10. 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. 681–687.

  11. Girshick R, Donahue J, Darrell T, Malik J. Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans Pattern Anal Mach Intell. 2016;38(1):142–158.

    Article  PubMed  Google Scholar 

  12. Gupta S, Girshick R, Arbeláez P, Malik J. Learning rich features from rgb-d images for object detection and segmentation. European Conference on Computer Vision. Springer; 2014. p. 345–360.

  13. Harding P, Robertson NM. Visual saliency from image features with application to compression. Cogn Comput. 2013;5(1):76–98.

    Article  Google Scholar 

  14. Hinton GE. A practical guide to training restricted boltzmann machines. Neural Networks: Tricks of the Trade. Springer; 2012. p. 599–619.

  15. Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets. Neural Comput. 2006; 18(7):1527–1554.

    Article  PubMed  Google Scholar 

  16. Itti L, Koch C, Niebur E, et al. A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell 1998;20(11):1254–1259.

    Article  Google Scholar 

  17. 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. 675–678.

  18. Jiann-Der L. Object recognition using a neural network with optimal feature extraction. Math Comput Modell. 1997;25(12):105–117.

    Article  Google Scholar 

  19. Keyvanrad MA, Homayounpour MM. Deep belief network training improvement using elite samples minimizing free energy. (2014) arXiv:http://arXiv.org/abs/1411.4046.

  20. Kootstra G, de Boer B, Schomaker LR. Predicting eye fixations on complex visual stimuli using local symmetry. Cogn Comput. 2011;3(1):223–240.

    Article  Google Scholar 

  21. Larochelle H, Bengio Y. Classification using discriminative restricted boltzmann machines. Proceedings of the 25th international conference on Machine learning. ACM; 2008. p. 536–543.

  22. Lazebnik S, Schmid C, Ponce J. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE; 2006. p. 2169–2178.

  23. Le Meur O, Le Callet P, Barba D, Thoreau D. A coherent computational approach to model the bottom-up visual attention. IEEE Trans Pattern Anal Mach Intell 2006;28:802–817.

    Article  PubMed  Google Scholar 

  24. Liang J, Yuen SY. A novel saliency prediction method based on fast radial symmetry transform and its generalization. Cogn Comput. 2016;8:1–10.

    Article  CAS  Google Scholar 

  25. Liu Y, Zhou S, Chen Q. Discriminative deep belief networks for visual data classification. Pattern Recogn. 2011;44(10):2287–2296.

    Article  Google Scholar 

  26. Mahadevan V, Vasconcelos N. Saliency-based discriminant tracking. 2009. CVPR 2009. IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2009. p. 1007–1013.

  27. Marat S, Phuoc TH, Granjon L, Guyader N, Pellerin D, Guérin-Dugué A. Modelling spatio-temporal saliency to predict gaze direction for short videos. Int J Comput Vis 2009;82(3):231–243.

    Article  Google Scholar 

  28. Marat S, Rahman A, Pellerin D, Guyader N, Houzet D. Improving visual saliency by adding ‘face feature map’ and ‘center bias’. Cogn Comput. 2013;5(1):63–75.

    Article  Google Scholar 

  29. Mishra AK, Aloimonos Y. Active segmentation. Int J Humanoid Robot 2009;6(03):361–386.

    Article  Google Scholar 

  30. Mohamed Ar, Dahl G, Hinton G. Deep belief networks for phone recognition. Nips workshop on deep learning for speech recognition and related applications; 2009. p. 39.

  31. Oliva A, Torralba A. Building the gist of a scene: The role of global image features in recognition. Progress Brain Res 2006;155:23–36.

    Article  Google Scholar 

  32. Ouadiay FZ, Zrira N, Bouyakhf EH, Himmi MM. 3d object categorization and recognition based on deep belief networks and point clouds. Proceedings of the 13th International Conference on Informatics in Control, Automation and Robotics; 2016. p. 311–318.

  33. Pandey M, Lazebnik S. Scene recognition and weakly supervised object localization with deformable part-based models. 2011 IEEE International Conference on Computer Vision (ICCV). IEEE; 2011. p. 1307–1314.

  34. Quattoni A, Torralba A. Recognizing indoor scenes. 2009. CVPR 2009. IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2009. p. 413–420.

  35. Ripley BD. Pattern recognition and neural networks. Cambridge: Cambridge University Press; 2007.

    Google Scholar 

  36. Serre T, Kreiman G, Kouh M, Cadieu C, Knoblich U, Poggio T. A quantitative theory of immediate visual recognition. Progress Brain Res 2007;165:33–56.

    Article  Google Scholar 

  37. Siagian C, Itti L. Rapid biologically-inspired scene classification using features shared with visual attention. IEEE Trans Pattern Anal Mach Intell 2007;29(2):300–312.

    Article  PubMed  Google Scholar 

  38. Siagian C, Itti L. Rapid biologically-inspired scene classification using features shared with visual attention. IEEE Trans Pattern Anal Mach Intell 2007;29(2):300–312.

    Article  PubMed  Google Scholar 

  39. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. (2014) arXiv:http://arXiv.org/abs/1409.1556.

  40. Socher R, Huval B, Bath B, Manning CD, Ng AY. Convolutional-recursive deep learning for 3d object classification. Advances in Neural Information Processing Systems; 2012. p. 665–673.

  41. Szummer M, Picard RW. Indoor-outdoor image classification. 1998. Proceedings., 1998 IEEE International Workshop on Content-Based Access of Image and Video Database. IEEE; 1998. p. 42–51.

  42. Tieleman T. Training restricted boltzmann machines using approximations to the likelihood gradient. Proceedings of the 25th international conference on Machine learning. ACM; 2008. p. 1064–1071.

  43. Tu Z, Abel A, Zhang L, Luo B, Hussain A. A new spatio-temporal saliency-based video object segmentation. Cogn Comput. 2016;8:1–19.

  44. Tünnermann J, Mertsching B. Region-based artificial visual attention in space and time. Cogn Comput 2014;6 (1):125–143.

    Article  Google Scholar 

  45. Ulrich I, Nourbakhsh I. Appearance-based place recognition for topological localization. 2000. Proceedings. ICRA’00. IEEE International Conference on Robotics and Automation. IEEE; 2000. p. 1023–1029.

  46. Wang Y, Zhao Q, Wang B, Wang S, Zhang Y, Guo W, Feng Z. A real-time active pedestrian tracking system inspired by the human visual system. Cogn Comput 2015;8:1–13.

    Google Scholar 

  47. Zeng N, Wang Z, Zhang H, Liu W, Alsaadi FE. Deep belief networks for quantitative analysis of a gold immunochromatographic strip. Cogn Comput 2016;8:1–9.

    Article  CAS  Google Scholar 

  48. Zhao J, Du C, Sun H, Liu X, Sun J. Biologically motivated model for outdoor scene classification. Cogn Comput 2015;7(1):20–33.

    Article  Google Scholar 

  49. Zhao J, Sun S, Liu X, Sun J, Yang A. A novel biologically inspired visual saliency model. Cogn Comput 2014;6(4):841–848.

    Article  Google Scholar 

  50. Zhou B, Khosla A, Lapedriza A, Torralba A, Oliva A. Places: An image database for deep scene understanding. (2016) arXiv:1610.02055.

  51. Zhou B, Lapedriza A, Xiao J, Torralba A, Oliva A. Learning deep features for scene recognition using places database. Advances in neural information processing systems; 2014. p. 487–495.

  52. Zhou S, Chen Q, Wang X. Discriminative deep belief networks for image classification. 2010 IEEE International Conference on Image Processing. IEEE; 2010. p. 1561–1564.

  53. Zrira N, Bouyakhf EH. 2016. A novel incremental topological mapping using global visual features. International Journal of Computational Vision and Robotics. In press.

  54. Zuo Z, Wang G, Shuai B, Zhao L, Yang Q, Jiang X. Learning discriminative and shareable features for scene classification. Computer Vision–ECCV 2014. Springer; 2014. p. 552–568.

Download references

Acknowledgments

The authors would like to thank Mr. Mohammad Ali Keyvanrad of Laboratory for Intelligent Multimedia Processing (LIMP), Amirkabir University of Technology, Tehran, Iran for his discussions and Matlab Toolbox which helped in the improvement of the paper.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Nabila Zrira.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflict of interest.

Informed Consent

All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the Helsinki Declaration of 1975, as revised in 2008 (5). Additional informed consent was obtained from all participants for which identifying information is included in this article.

Human and Animal Rights

This article does not contain any studies with human or animal subjects performed by any of the authors.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zrira, N., Khan, H.A. & Bouyakhf, E.H. Discriminative Deep Belief Network for Indoor Environment Classification Using Global Visual Features. Cogn Comput 10, 437–453 (2018). https://doi.org/10.1007/s12559-017-9534-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-017-9534-9

Keywords

  • Indoor environment
  • GIST descriptor
  • Discriminative Deep Belief Network (DDBN)
  • Back-propagation technique