Autors: Popov, V. L., Shakev, N. G., Ahmed, S. A., Topalov, A. V.
Title: Recognition of Dynamic Targets using a Deep Convolutional Neural Network
Keywords: Deep Learning; Convolutional Neural Network; Image Recognition; Mobile Robots, Autonomous Robotic Systems

Abstract: Recognition and tracking of dynamic objects play an important role in the development of service robots behaviors allowing them to co-exist with humans and other autonomous machines in shared environments. They can simplify the design of autonomous navigation and obstacle avoidance algorithms as well as the ability to operate within multi-agent formations. In this investigation an approach is proposed to use a deep convolutional neural network for recognition and tracking of pre-specified dynamic objects on a sequence of images. It is regarded as a substantial part on the way of achieving our goal to design a dynamic target following behavior for a service robot, based on data received from its onboard camera. During the experiments the implemented deep learning neural network is able to recognize and localize on a sequence of images a moving mobile robot iRobot Create. The developed algorithm localizes the recognized object and begins considering it as a potential dynamic target.

References

  1. Angelov, P. and Sperduti, A., 2016, Challenges in Deep Learning, ESANN 2016 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges (Belgium), 27-29 April 2016, <Bruges (Belgium)>, i6doc.com publication
  2. Oh K., Jung K., 2004, GPU implementation of neural networks., Pattern Recognition, Volume 37 (6), pp. 1311-1314
  3. Rolfes T., 2004, Neural networks on programmable graphics hardware, Game Programming Gems, Volume 4, pp. 373–378
  4. Krizhevsky, A., Sutskever, I. and Hinton G. E., 2012, . Imagenet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, Volume 25, pp. 1106–1114

Issue

ANNA'18 Advances in Neural Networks and Applications, 2018, Bulgaria,

Copyright VDE VERLAG

Цитирания (Citation/s):
1. Varela N., Zoe C.-G., Ternera-Muñoz Yesith R., Esmeral-Romero Ernesto F., Zelaya N.A.L., Method for classifying images in databases through deep convolutional networks (2020), Procedia Computer Science, 175, pp. 135 - 140, DOI: 10.1016/j.procs.2020.07.022 - 2020 - в издания, индексирани в Scopus или Web of Science
2. Mohammed I.M., Al-Dabagh M.Z.N., Rashid S.J., Isa N.A.M., Path discovering in maze area using mobile robot (2022) Telkomnika (Telecommunication Computing Electronics and Control), 20 (2), pp. 416 - 425, DOI: 10.12928/TELKOMNIKA.v20i2.19408 - 2022 - в издания, индексирани в Scopus или Web of Science

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus