Memetic Computing

, Volume 10, Issue 2, pp 233–241 | Cite as

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

  • Huaping LiuEmail author
  • Fengxue Li
  • Xinying Xu
  • Fuchun Sun
Regular Research Paper


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.


Extreme learning machine Local receptive field Q-learning Active object recognition 



This work was supported in part by the National Natural Science Foundation of China under Grants U1613212, 61673238, 91420302, and 61327809, in part by the National High-Tech Research and Development Plan under Grant 2015AA042306, and in part by the National Science & Technology Pillar Program during the 12th Five-year Plan Period (No.2015BAK12B03).


  1. 1.
    Chen S, Li Y, Kwok NM (2008) Active vision in robotic systems: a survey of recent developments. Int J Robot Res 30:1343–1377CrossRefGoogle Scholar
  2. 2.
    Jia Z, jen Chang Y, Chen T (2009) Active view selection for object and pose recognition. In: ICCVW, pp 641–648Google Scholar
  3. 3.
    Nakath D, Kluth T, Reineking T, Zetzsche C, Schill K (2014) Active sensorimotor object recognition in three-dimensional space. Spat Cogn IX:312–324Google Scholar
  4. 4.
    Andreopoulos A, Tsotsos JK (2013) A computational learning theory of active object recognition under uncertainty. Int J Comput Vis 10:95–142MathSciNetCrossRefGoogle Scholar
  5. 5.
    Browatzki B, Tikhanoff V, Metta G, Bulthoff HH, Wallraven C (2014) Active in-hand object recognition on a humanoid robot. IEEE Trans Robot 30:1260–1269CrossRefGoogle Scholar
  6. 6.
    Wu K, Ranasinghe R, Dissanayake G (2015)Active recognition and pose estimation of household objects in clutter. In: ICRA, pp 4230–4237Google Scholar
  7. 7.
    Potthast C, Breitenmoser A, Sha F, Sukhatme GS (2016) Active multi-view object recognition: a unifying view on online feature selection and view planning. Robot Auton Syst 84:31–47CrossRefGoogle Scholar
  8. 8.
    Imperolia M, Pretto A (2016) Active detection and localization of textureless objects in cluttered environments. In: CVIU, pp 1–18Google Scholar
  9. 9.
    Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518:529–533CrossRefGoogle Scholar
  10. 10.
    Malmir M, Sikka K, Forster D, Movellan J, Cottrell G (2015) Deep q-learning for active recognition of germs: baseline performance on a standardized dataset for active learning. In: BMVC, pp 161–171Google Scholar
  11. 11.
    Caicedo JC, Lazebnik S (2015) Active object localization with deep reinforcement learning. In: ICCV, pp 1–8Google Scholar
  12. 12.
    Huang G-B, Zhu Q-Y, Siew C-K (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501CrossRefGoogle Scholar
  13. 13.
    Huang G-B, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern 42:513–529CrossRefGoogle Scholar
  14. 14.
    Cao J, Lin Z (2015) Extreme learning machines on high dimensional and large data applications: a survey. Math Probl Eng 2015:1–13. doi: 10.1155/2015/103796
  15. 15.
    Cao J, Lin Z, Huang G-B, Liu N (2012) Voting based extreme learning machine. Inf Sci 185(1):66–77MathSciNetCrossRefGoogle Scholar
  16. 16.
    Lu H, Du B, Liu J, Xia H, Yeap WK (2016) A kernel extreme learning machine algorithm based on improved particle swam optimization. Memet Comput 1–8Google Scholar
  17. 17.
    Li X, Mao W, Jiang W, Yao Y (2016) Extreme learning machine via free sparse transfer representation optimization. Memet Comput 8(2):85–95CrossRefGoogle Scholar
  18. 18.
    Zhang H, Zhang S, Yin Y Kernel online sequential elm algorithm with sliding window subject to time-varying environments. Memet Comput 1–10Google Scholar
  19. 19.
    Zhang N, Ding S (2016) Unsupervised and semi-supervised extreme learning machine with wavelet kernel for high dimensional data. Memet Comput 1–11Google Scholar
  20. 20.
    Cao J, Zhao Y, Lai X, Ong MEH, Yin C, Koh ZX, Liu N (2015) Landmark recognition with sparse representation classification and extreme learning machine. J Frankl Inst 352(10):4528–4545MathSciNetCrossRefGoogle Scholar
  21. 21.
    Kan EM, Lim MH, Ong YS, Tan AH, Yeo SP (2013) Extreme learning machine terrain-based navigation for unmanned aerial vehicles. Neural Comput Appl 22(3–4):469–477CrossRefGoogle Scholar
  22. 22.
    Xiao C, Dong Z, Xu Y, Meng K, Zhou X, Zhang X (2016) Rational and self-adaptive evolutionary extreme learning machine for electricity price forecast. Memet Comput 8(3):223–233CrossRefGoogle Scholar
  23. 23.
    Cao J, Wang W, Wang J, Wang R (2016) Excavation equipment recognition based on novel acoustic statistical features. IEEE Trans Cybern. doi: 10.1109/TCYB.2016.2609999
  24. 24.
    Das SP, Padhy S (2016) Unsupervised extreme learning machine and support vector regression hybrid model for predicting energy commodity futures index. Memet Comput 1–14Google Scholar
  25. 25.
    Pan J, Wang X, Cheng Y, Cao G (2012) Reinforcement learning based on extreme learning machine. In: International conference on intelligent computing. Springer, New York, pp 80–86Google Scholar
  26. 26.
    Lopez-Guede JM, Fernandez-Gauna B, Grana M (2013) State-action value function modeled by elm in reinforcement learning for hose control problems. Int J Uncertain Fuzziness Knowl Based Syst 21(supp02):99–116MathSciNetCrossRefGoogle Scholar
  27. 27.
    Lopez-Guede JM, Fernandez-Gauna B, Ramos-Hernanz JA (2015) A L-MCRS dynamics approximation by ELM for reinforcement learning. Neurocomputing 150:116–123CrossRefGoogle Scholar
  28. 28.
    Hwangbo J, Gehring C, Bellicoso D, Fankhauser P, Siegwart R, Hutter M (2015) Direct state-to-action mapping for high dof robots using ELM. In: IROSGoogle Scholar
  29. 29.
    Malmir M, Sikka K, Forster D, Movellan JR, Cottrell G (2015) Deep Q-learning for active recognition of GERMS: baseline performance on a standardized dataset for active learning. In: BMVC, pp 161–171Google Scholar
  30. 30.
    Sutton RS, Barto AG (1998) Introduction to reinforcement learning, vol 135. MIT Press, CambridgezbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  1. 1.Department of Computer Science and Technology, Tsinghua University, State Key Lab. of Intelligent Technology and SystemsTNLISTBeijingPeople’s Republic of China
  2. 2.Department of Electronic InformationTaiyuan University of TechnologyShanxiChina

Personalised recommendations