Active object recognition using hierarchical local-receptive-field-based extreme learning machine

In this paper, we develop a method to actively recognize objects by choosing a sequence of actions for an active camera that helps to discriminate between the objects in a dataset. Hierarchical local-receptive-field-based extreme learning machine architecture is developed to jointly learn the state representation and the reinforcement learning strategy. Experimental validation on the publicly available GERMS dataset shows the effectiveness of the proposed method.

[1]  Tsuhan Chen,et al.  Active view selection for object and pose recognition , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[2]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[3]  Haigang Zhang,et al.  Kernel online sequential ELM algorithm with sliding window subject to time-varying environments , 2018, Memetic Comput..

[4]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[5]  John K. Tsotsos,et al.  A Computational Learning Theory of Active Object Recognition Under Uncertainty , 2012, International Journal of Computer Vision.

[6]  Svetlana Lazebnik,et al.  Active Object Localization with Deep Reinforcement Learning , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  Gamini Dissanayake,et al.  Active recognition and pose estimation of household objects in clutter , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[8]  Xuesong Wang,et al.  Reinforcement Learning Based on Extreme Learning Machine , 2012, ICIC.

[9]  Alberto Pretto,et al.  Active Detection and Localization of Textureless Objects in Cluttered Environments , 2016, ArXiv.

[10]  Shom Prasad Das,et al.  Unsupervised extreme learning machine and support vector regression hybrid model for predicting energy commodity futures index , 2017, Memetic Comput..

[11]  Huijuan Lu,et al.  A kernel extreme learning machine algorithm based on improved particle swam optimization , 2017, Memetic Comput..

[12]  Gaurav S. Sukhatme,et al.  Active multi-view object recognition: A unifying view on online feature selection and view planning , 2016, Robotics Auton. Syst..

[13]  Xin Zhang,et al.  Rational and self-adaptive evolutionary extreme learning machine for electricity price forecast , 2016, Memetic Computing.

[14]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[15]  Nan Zhang,et al.  Unsupervised and semi-supervised extreme learning machine with wavelet kernel for high dimensional data , 2016, Memetic Computing.

[16]  Nan Liu,et al.  Voting based extreme learning machine , 2012, Inf. Sci..

[17]  Giorgio Metta,et al.  Active In-Hand Object Recognition on a Humanoid Robot , 2014, IEEE Transactions on Robotics.

[18]  Ah-Hwee Tan,et al.  Extreme learning machine terrain-based navigation for unmanned aerial vehicles , 2012, Neural Computing and Applications.

[19]  Roland Siegwart,et al.  Direct state-to-action mapping for high DOF robots using ELM , 2015, IROS 2015.

[20]  Nan Liu,et al.  Landmark recognition with sparse representation classification and extreme learning machine , 2015, J. Frankl. Inst..

[21]  Xiaodong Li,et al.  Extreme learning machine via free sparse transfer representation optimization , 2016, Memetic Comput..

[22]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[23]  Shengyong Chen,et al.  Active vision in robotic systems: A survey of recent developments , 2011, Int. J. Robotics Res..

[24]  Jianzhong Wang,et al.  Excavation Equipment Recognition Based on Novel Acoustic Statistical Features , 2017, IEEE Transactions on Cybernetics.

[25]  Tobias Kluth,et al.  Active Sensorimotor Object Recognition in Three-Dimensional Space , 2014, Spatial Cognition.

[26]  José Manuel López-Guede,et al.  A L-MCRS dynamics approximation by ELM for Reinforcement Learning , 2015, Neurocomputing.

[27]  Zhiping Lin,et al.  Extreme Learning Machines on High Dimensional and Large Data Applications: A Survey , 2015 .

[28]  Javier R. Movellan,et al.  Deep Q-learning for Active Recognition of GERMS: Baseline performance on a standardized dataset for active learning , 2015, BMVC.

[29]  Manuel Graña,et al.  STATE-ACTION VALUE FUNCTION MODELED BY ELM IN REINFORCEMENT LEARNING FOR HOSE CONTROL PROBLEMS , 2013 .