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

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.

[1]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[2]  Luís A. Alexandre.  3D Object Recognition Using Convolutional Neural Networks with Transfer Learning Between Input Channels , 2014, IAS.

[3]  David S. Touretzky,et al.  Advances in neural information processing systems 2 , 1989 .

[4]  Shiu Yin Yuen,et al.  A Novel Saliency Prediction Method Based on Fast Radial Symmetry Transform and Its Generalization , 2016, Cognitive Computation.

[5]  Antonio Torralba,et al.  Building the gist of a scene: the role of global image features in recognition. , 2006, Progress in brain research.

[6]  Bolei Zhou,et al.  Places: An Image Database for Deep Scene Understanding , 2016, ArXiv.

[7]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[8]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Jitendra Malik,et al.  Learning Rich Features from RGB-D Images for Object Detection and Segmentation , 2014, ECCV.

[10]  Wolfram Burgard,et al.  Multimodal deep learning for robust RGB-D object recognition , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[11]  Geoffrey E. Hinton,et al.  Deep Belief Networks for phone recognition , 2009 .

[12]  Neil M. Robertson,et al.  Visual Saliency from Image Features with Application to Compression , 2012, Cognitive Computation.

[13]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[14]  Lee Jiann-Der,et al.  Object recognition using a neural network with optimal feature extraction , 1997 .

[15]  IttiLaurent,et al.  Rapid Biologically-Inspired Scene Classification Using Features Shared with Visual Attention , 2007 .

[16]  Thomas Serre,et al.  A quantitative theory of immediate visual recognition. , 2007, Progress in brain research.

[17]  Gail A. Carpenter,et al.  ART-EMAP: A neural network architecture for object recognition by evidence accumulation , 1995, IEEE Trans. Neural Networks.

[18]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[19]  Lei Zhang,et al.  A New Spatio-Temporal Saliency-Based Video Object Segmentation , 2016, Cognitive Computation.

[20]  Yan Liu,et al.  Discriminative deep belief networks for visual data classification , 2011, Pattern Recognit..

[21]  Yoshua Bengio,et al.  Classification using discriminative restricted Boltzmann machines , 2008, ICML '08.

[22]  Martin Szummer,et al.  Indoor-outdoor image classification , 1998, Proceedings 1998 IEEE International Workshop on Content-Based Access of Image and Video Database.

[23]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[24]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[25]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[26]  Irving Biederman,et al.  On the Semantics of a Glance at a Scene , 2017 .

[27]  Jitendra Malik,et al.  Region-Based Convolutional Networks for Accurate Object Detection and Segmentation , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Yu Zhang,et al.  A Real-Time Active Pedestrian Tracking System Inspired by the Human Visual System , 2015, Cognitive Computation.

[29]  Jingjing Zhao,et al.  A Novel Biologically Inspired Visual Saliency Model , 2014, Cognitive Computation.

[30]  Nuno Vasconcelos,et al.  Saliency-based discriminant tracking , 2009, CVPR.

[31]  Bärbel Mertsching,et al.  Region-Based Artificial Visual Attention in Space and Time , 2013, Cognitive Computation.

[32]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[33]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[34]  Antonio Torralba,et al.  Recognizing indoor scenes , 2009, CVPR.

[35]  Nathalie Guyader,et al.  Improving Visual Saliency by Adding ‘Face Feature Map’ and ‘Center Bias’ , 2012, Cognitive Computation.

[36]  Svetlana Lazebnik,et al.  Scene recognition and weakly supervised object localization with deformable part-based models , 2011, 2011 International Conference on Computer Vision.

[37]  Patrick Le Callet,et al.  A coherent computational approach to model bottom-up visual attention , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Fuad E. Alsaadi,et al.  Deep Belief Networks for Quantitative Analysis of a Gold Immunochromatographic Strip , 2016, Cognitive Computation.

[39]  Jingjing Zhao,et al.  Biologically Motivated Model for Outdoor Scene Classification , 2013, Cognitive Computation.

[40]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[41]  Tijmen Tieleman,et al.  Training restricted Boltzmann machines using approximations to the likelihood gradient , 2008, ICML '08.

[42]  Miguel Á. Carreira-Perpiñán,et al.  On Contrastive Divergence Learning , 2005, AISTATS.

[43]  Gert Kootstra,et al.  Predicting Eye Fixations on Complex Visual Stimuli Using Local Symmetry , 2011, Cognitive Computation.

[44]  El-Houssine Bouyakhf,et al.  3D Object Categorization and Recognition based on Deep Belief Networks and Point Clouds , 2016, ICINCO.

[45]  Illah R. Nourbakhsh,et al.  Appearance-based place recognition for topological localization , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[46]  Laurent Itti,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Rapid Biologically-inspired Scene Classification Using Features Shared with Visual Attention , 2022 .

[47]  Yiannis Aloimonos,et al.  Active Segmentation , 2009, Int. J. Humanoid Robotics.

[48]  Xiaolong Wang,et al.  Discriminative Deep Belief Networks for image classification , 2010, 2010 IEEE International Conference on Image Processing.

[49]  Gang Wang,et al.  Learning Discriminative and Shareable Features for Scene Classification , 2014, ECCV.

[50]  Nathalie Guyader,et al.  Modelling Spatio-Temporal Saliency to Predict Gaze Direction for Short Videos , 2009, International Journal of Computer Vision.

[51]  Bolei Zhou,et al.  Learning Deep Features for Scene Recognition using Places Database , 2014, NIPS.

[52]  Andrew Y. Ng,et al.  Convolutional-Recursive Deep Learning for 3D Object Classification , 2012, NIPS.

[53]  Michael F. Lynch,et al.  Emotion: A Unified Mechanistic Interpretation from a Cognitive Architecture , 2015, Cognitive Computation.

[54]  Vincent Gripon,et al.  A Biologically Inspired Framework for Visual Information Processing and an Application on Modeling Bottom-Up Visual Attention , 2016, Cognitive Computation.

[55]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[56]  El-Houssine Bouyakhf,et al.  A novel incremental topological mapping using global visual features , 2018, Int. J. Comput. Vis. Robotics.

[57]  Mohammad Mehdi Homayounpour,et al.  Deep Belief Network Training Improvement Using Elite Samples Minimizing Free Energy , 2015, Int. J. Pattern Recognit. Artif. Intell..