RGB-D training for convolutional neural network with final fuzzy layer for depth weighting

This paper presents training of novel hybrid network based on three deep convolutional neural network architectures applied to object recognition, based on the depth information supplied for a RGBD camera. For this case, the depth information allows to set the dataset of training images of each network, its architecture and its characteristics, generating a dynamic recognition application by variation of the image capture point, whose final layer is determined by a diffuse inference system. The general architecture designed allows an efficient object recognition applicable to robotic mobile agents, whose perspective of the object varies when approaching or moving away from them, showing an overall performance of 90.19%.

[1]  Nabil Derbel,et al.  Fuzzy logic controllers design for omnidirectional mobile robot navigation , 2016, Appl. Soft Comput..

[2]  Rajiv V. Dharaskar,et al.  Video gestures identification and recognition using Fourier descriptor and general fuzzy minmax neural network for subset of Indian sign language , 2012, 2012 12th International Conference on Hybrid Intelligent Systems (HIS).

[3]  Vali Derhami,et al.  Supervised fuzzy reinforcement learning for robot navigation , 2016, Appl. Soft Comput..

[4]  Nei Kato,et al.  State-of-the-Art Deep Learning: Evolving Machine Intelligence Toward Tomorrow’s Intelligent Network Traffic Control Systems , 2017, IEEE Communications Surveys & Tutorials.

[5]  Hong Liu,et al.  Robot grasp detection using multimodal deep convolutional neural networks , 2016 .

[6]  Chung-Hsun Sun,et al.  Sequentially switched fuzzy-model-based control for wheeled mobile robot with visual odometry , 2017 .

[7]  Alireza Khosravi,et al.  On position/force tracking control problem of cooperative robot manipulators using adaptive fuzzy backstepping approach. , 2017, ISA transactions.

[8]  Gin-Der Wu,et al.  Type-2 fuzzy neural network for voice activity detection , 2016, 2016 International Conference on Fuzzy Theory and Its Applications (iFuzzy).

[9]  Ho-Joon Kim,et al.  Dynamic hand gesture recognition using a CNN model with 3D receptive fields , 2008, 2008 International Conference on Neural Networks and Signal Processing.

[10]  Weihong Wang,et al.  Research on robot path planning based on fuzzy neural network and particle swarm optimization , 2017, 2017 29th Chinese Control And Decision Conference (CCDC).

[11]  Joseph Redmon,et al.  Real-time grasp detection using convolutional neural networks , 2014, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[12]  Barbara Caputo,et al.  Learning Deep NBNN Representations for Robust Place Categorization , 2017, IEEE Robotics and Automation Letters.

[13]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[14]  Chalavadi Krishna Mohan,et al.  Human action recognition based on motion capture information using fuzzy convolution neural networks , 2015, 2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR).

[15]  Kresimir Fertalj,et al.  Graph Matching Using Hierarchical Fuzzy Graph Neural Networks , 2017, IEEE Transactions on Fuzzy Systems.

[16]  Adel M. Alimi,et al.  Interval type-2 beta fuzzy neural network for wheeled mobile robots obstacles avoidance , 2017, 2017 International Conference on Advanced Systems and Electric Technologies (IC_ASET).

[17]  Youyong Kong,et al.  A Hierarchical Fused Fuzzy Deep Neural Network for Data Classification , 2017, IEEE Transactions on Fuzzy Systems.

[18]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[19]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[20]  S. P. Singh,et al.  Hybrid clusteing algorithm and Neural Network classifier for satellite image classification , 2015, 2015 International Conference on Industrial Instrumentation and Control (ICIC).