Indoor Image Recognition and Classification via Deep Convolutional Neural Network

Indoor navigation (or way finding) still presents a great challenge for autonomous robotic systems and for visually impaired people (VIP). Indeed, the VIP is often enabling to see visual cues such as informational signs, landmarks or geometrical shapes. A Deep Convolution Neural Network (DCNN) has been proven to be highly effective and has achieved an outstanding success comparing to other techniques in object recognition. This paper proposes a robust approach for objects’ classification using a DCNN model. Experimental results in real indoor images with natural illumination (the MCIn-door 20000 dataset) show that the proposed DCNN model achieves the accuracy of 93.7% in objects classification.

[1]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[2]  Raimondo Schettini,et al.  Robust smile detection using convolutional neural networks , 2016, J. Electronic Imaging.

[3]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[4]  Jae-Bok Song,et al.  Object recognition for SLAM in floor environments using a depth sensor , 2016, 2016 13th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI).

[5]  Mohamed Wajih Guerfala,et al.  Data classification using logarithmic spiral method based on RBF classifiers , 2016, 2017 International Conference on Information and Digital Technologies (IDT).

[6]  Ke Xie,et al.  A search-classify approach for cluttered indoor scene understanding , 2012, ACM Trans. Graph..

[7]  Hua Yang,et al.  Discriminative feature representation for image classification via multimodal multitask deep neural networks , 2017, J. Electronic Imaging.

[8]  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).

[9]  Stephen Gould,et al.  Discriminative learning with latent variables for cluttered indoor scene understanding , 2010, CACM.

[10]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[11]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[13]  Geoffrey E. Hinton,et al.  On the importance of initialization and momentum in deep learning , 2013, ICML.

[14]  Gang Wang,et al.  Door recognition and deep learning algorithm for visual based robot navigation , 2014, 2014 IEEE International Conference on Robotics and Biomimetics (ROBIO 2014).

[15]  Sven Behnke,et al.  RGB-D object recognition and pose estimation based on pre-trained convolutional neural network features , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[16]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[17]  Mohammed Bennamoun,et al.  RGB-D Object Recognition and Grasp Detection Using Hierarchical Cascaded Forests , 2017, IEEE Transactions on Robotics.

[18]  Sven Behnke,et al.  Combining Semantic and Geometric Features for Object Class Segmentation of Indoor Scenes , 2017, IEEE Robotics and Automation Letters.

[19]  Andreas Zell,et al.  Object Recognition and Tracking for Indoor Robots Using an RGB-D Sensor , 2014, IAS.

[20]  Derek Nowrouzezahrai,et al.  Learning hatching for pen-and-ink illustration of surfaces , 2012, TOGS.

[21]  Afef Abdelkrim,et al.  Machine learning framework for image classification , 2016, 2017 International Conference on Information and Digital Technologies (IDT).

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

[23]  Yonglong Luo,et al.  Indoor object recognition using pre-trained convolutional neural network , 2017, 2017 23rd International Conference on Automation and Computing (ICAC).

[24]  Martin A. Riedmiller,et al.  A learned feature descriptor for object recognition in RGB-D data , 2012, 2012 IEEE International Conference on Robotics and Automation.

[25]  Eric R. LaRose,et al.  MCIndoor20000: A fully-labeled image dataset to advance indoor objects detection , 2018, Data in brief.