Advertisement

Intrinsically Motivated Active Perception for Multi-areas View Tasks

  • Dashun Pei
  • Linhua JiangEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11919)

Abstract

The target recognition of the human eye in real scenes is still far superior to any robot vision system. We believe that there are two major essential reasons. First, humans can observe the environment in which the object is located, get the probability of the object category. Second, human can use foveal to focus on the object and get more object detail features from the high resolution image containing the object and make it easier to identify. This paper proposes a novel method for searching and locating surrounding objects using a monocular Panning/Tilting/Zooming (PTZ) camera with free rotation and zoom functions.

Our system is an active environment-aware vision system based on Intrinsic Motivation and capable of autonomously exploring the surroundings of the camera. At the same time, by combining the visual information of foveal field of view and context field of view, the visual system observes more details and make more accurate prediction, and overcomes the limitation of low-resolution image in target recognition. Finally, our experiment proved that the visual perception system incorporating the curiosity mechanism is superior to the common perception method in terms of time overhead and learning ability.

Keywords

Intrinsic Motivation Active perception Computer vision Intrinsic adaptive curiosity Developmental robotics 

References

  1. 1.
    Ekvall, S., Kragic, D., Jensfelt, P.: Object detection and mapping for service robot tasks. Robotica 25(2), 175–187 (2007)CrossRefGoogle Scholar
  2. 2.
    Borji, A., Itti, L.: State-of-the-art in visual attention modeling. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 185–207 (2013)CrossRefGoogle Scholar
  3. 3.
    Itti, L., Koch, C.: Computational modelling of visual attention. Nat. Rev. Neurosci. 2(3), 194 (2001)CrossRefGoogle Scholar
  4. 4.
    Frintrop, S., Rome, E., Christensen, H.I.: Computational visual attention systems and their cognitive foundations: a survey. ACM Trans. Appl. Percept. (TAP) 7(1), 6 (2010)Google Scholar
  5. 5.
    Minut, S., Mahadevan, S.: A reinforcement learning model of selective visual attention. In: Proceedings of the Fifth International Conference on Autonomous Agents. ACM (2001)Google Scholar
  6. 6.
    Hueber, N., et al.: Bio-inspired approach for intelligent unattended ground sensors. In: Next-Generation Robotics II; and Machine Intelligence and Bio-inspired Computation: Theory and Applications IX, vol. 9494. International Society for Optics and Photonics (2015)Google Scholar
  7. 7.
    Young, M.: The Technical Writer’s Handbook: Writing with Style and Clarity. University Science Books (2002)Google Scholar
  8. 8.
    Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. arXiv preprint (2017)Google Scholar
  9. 9.
    Baldassarre, G., Mirolli, M. (eds.): Intrinsically Motivated Learning in Natural and Artificial Systems. Springer, Berlin (2013)Google Scholar
  10. 10.
    Oudeyer, P.-Y., Kaplan, F., Hafner, V.V.: Intrinsic motivation systems for autonomous mental development. IEEE Trans. Evol. Comput. 11(2), 265–286 (2007)CrossRefGoogle Scholar
  11. 11.
    Skinner, B.F.: An Experimental Analysis. The Behavior of Organisms. BF Skinner Foundation (1990)Google Scholar
  12. 12.
    Rosen, B.E., Goodwin, J.M., Vidal, J.J.: Machine operant conditioning. In: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, Piscataway (1988)Google Scholar
  13. 13.
    Tao, S., et al.: A study on autonomous learning mechanism of cognitive robot. In: 2015 27th Chinese Control and Decision Conference (CCDC). IEEE (2015)Google Scholar
  14. 14.
    Girshick, R., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)Google Scholar
  15. 15.
    Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (2015)Google Scholar
  16. 16.
    Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (2015)Google Scholar
  17. 17.
    Redmon, J., et al.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)Google Scholar
  18. 18.
    Cangelosi, A., Schlesinger, M.: Developmental Robotics: From Babies to Robots. The MIT Press (2015)Google Scholar
  19. 19.
    Brogden, J.W.: Principles of behavior. J. Consult. Psychol. 8(5), 330–330 (1944)CrossRefGoogle Scholar
  20. 20.
    Berlyne, D.E.: Curiosity and exploration. Science 153(3731), 25–33 (1966)CrossRefGoogle Scholar
  21. 21.
    Goodfellow, I.J., et al.: Generative adversarial nets. In: International Conference on Neural Information Processing Systems. MIT Press (2014)Google Scholar
  22. 22.
    Bajcsy, R., Aloimonos, Y., Tsotsos, J.K.: Revisiting active perception. Auton. Rob. 42(2), 177–196 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Engineering Research Center of Optical Instruments and Systems, Ministry of Education, Shanghai Key Lab of Modern Optical Systems, School of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghaiPeople’s Republic of China

Personalised recommendations