Improving the effectiveness of training the on-board object detection system for a compact unmanned aerial vehicle

Authors

DOI:

https://doi.org/10.15587/1729-4061.2018.139923

Keywords:

growing neural gas, objects detector, information criterion, simulated annealing algorithm

Abstract

The model of object detector and the criterion of leaning effectiveness of the model were proposed. The model contains 7 first modules of the convolutional Squeezenet network, two convolutional multiscale layers and the information­extreme classifier. The multiplicative convolution of the particular criteria that takes into account the effectiveness of detection of objects in the image and accuracy of the classification analysis was considered as the criterion of learning effectiveness of the model. In this case, additional use of the orthogonal matching pursuit algorithm in calculating high­level features makes it possible to increase the accuracy of the model by 4 %. The training algorithm of object detector under conditions of a small size of labeled training datasets and limited computing resources available on board of a compact unmanned aerial vehicle was developed. The essence of the algorithm is to adapt the high­level layers of the model to the domain application area, based on the algorithms of growing sparse coding neural gas and simulated annealing. Unsupervised learning of high­level layers makes it possible to use effectively the unlabeled datasets from the domain area and determine the required number of neurons. It is shown that in the absence of fine tuning of convolutional layers, 69 % detection of objects in the images of the test dataset Inria Aerial Image was ensured. In this case, after fine tuning based on the simulated annealing algorithm, 95 % detection of the objects in test images is ensured.

It was shown that the use of unsupervised pretraining makes it possible to increase the generalizing ability of decision rules and to accelerate the iteration process of finding the global maximum during supervised learning on the dataset of limited size. In this case, the overfitting effect is eliminated by optimal selection of the value of hyperparameter, characterizing the measure of coverage of the input data of by network neurons.

Supporting Agency

  • Робота виконана на базі лабораторії інтелектуальних систем кафедри комп’ютерних наук Сумського державного університету при фінансовій підтримці МОН України в рамках держбюджетної науково-дослідної роботи ДР № 0117U003934

Author Biographies

Vyacheslav Moskalenko, Sumy State University Rimskoho-Korsakova str., 2, Sumy, Ukraine, 40007

PhD, Associate Professor

Department of Computer Science

Anatoliy Dovbysh, Sumy State University Rimskoho-Korsakova str., 2, Sumy, Ukraine, 40007

Doctor of technical sciences, Professor, Head of Department

Department of Computer Science

Igor Naumenko, Research Center for Missile Troops and Artillery Gerasima Kondratyeva str., 165, Sumy, Ukraine, 40021

PhD, Senior Researcher, Colonel

Alyona Moskalenko, Sumy State University Rimskoho-Korsakova str., 2, Sumy, Ukraine, 40007

PhD, Assistant

Department of Computer Science

Artem Korobov, Sumy State University Rimskoho-Korsakova str., 2, Sumy, Ukraine, 40007

Postgraduate student

Department of Computer Science

References

  1. Patricia, N., Caputo, B. (2014). Learning to Learn, from Transfer Learning to Domain Adaptation: A Unifying Perspective. 2014 IEEE Conference on Computer Vision and Pattern Recognition. doi: https://doi.org/10.1109/cvpr.2014.187
  2. Nguyen, A., Yosinski, J., Clune, J. (2015). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi: https://doi.org/10.1109/cvpr.2015.7298640
  3. Ayumi, V., Rere, L. M. R., Fanany, M. I., Arymurthy, A. M. (2016). Optimization of convolutional neural network using microcanonical annealing algorithm. 2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS). doi: https://doi.org/10.1109/icacsis.2016.7872787
  4. Antipov, G., Berrani, S.-A., Ruchaud, N., Dugelay, J.-L. (2015). Learned vs. Hand-Crafted Features for Pedestrian Gender Recognition. Proceedings of the 23rd ACM International Conference on Multimedia – MM ’15. doi: https://doi.org/10.1145/2733373.2806332
  5. Carrio, A., Sampedro, C., Rodriguez-Ramos, A., Campoy, P. (2017). A Review of Deep Learning Methods and Applications for Unmanned Aerial Vehicles. Journal of Sensors, 2017, 1–13. doi: https://doi.org/10.1155/2017/3296874
  6. Xu, X., Ding, Y., Hu, S. X., Niemier, M., Cong, J., Hu, Y., Shi, Y. (2018). Scaling for edge inference of deep neural networks. Nature Electronics, 1 (4), 216–222. doi: https://doi.org/10.1038/s41928-018-0059-3
  7. Loquercio, A., Maqueda, A. I., del-Blanco, C. R., Scaramuzza, D. (2018). DroNet: Learning to Fly by Driving. IEEE Robotics and Automation Letters, 3 (2), 1088–1095.doi: https://doi.org/10.1109/lra.2018.2795643
  8. Mathew, A., Mathew, J., Govind, M., Mooppan, A. (2017). An Improved Transfer learning Approach for Intrusion Detection. Procedia Computer Science, 115, 251–257. doi: https://doi.org/10.1016/j.procs.2017.09.132
  9. Qassim, H., Verma, A., Feinzimer, D. (2018). Compressed residual-VGG16 CNN model for big data places image recognition. 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC). doi: https://doi.org/10.1109/ccwc.2018.8301729
  10. Nakahara, H., Yonekawa, H., Sato, S. (2017). An object detector based on multiscale sliding window search using a fully pipelined binarized CNN on an FPGA. 2017 International Conference on Field Programmable Technology (ICFPT). doi: https://doi.org/10.1109/fpt.2017.8280135
  11. Moskalenko, V., Moskalenko, A., Pimonenko, S., Korobov, A. (2017). Development of the method of features learning and training decision rules for the prediction of violation of service level agreement in a cloud-based environment. Eastern-European Journal of Enterprise Technologies, 5 (2 (89)), 26–33. doi: https://doi.org/10.15587/1729-4061.2017.110073
  12. Feng, Q., Chen, C. L. P., Chen, L. (2016). Compressed auto-encoder building block for deep learning network. 2016 3rd International Conference on Informative and Cybernetics for Computational Social Systems (ICCSS). doi: https://doi.org/10.1109/iccss.2016.7586437
  13. Chen, X., Xiang, S., Liu, C.-L., Pan, C.-H. (2014). Aircraft Detection by Deep Convolutional Neural Networks. IPSJ Transactions on Computer Vision and Applications, 7, 10–17. doi: https://doi.org/10.2197/ipsjtcva.7.10
  14. Labusch, K., Barth, E., Martinetz, T. (2009). Sparse Coding Neural Gas: Learning of overcomplete data representations. Neurocomputing, 72 (7-9), 1547–1555. doi: https://doi.org/10.1016/j.neucom.2008.11.027
  15. Mrazova, I., Kukacka, M. (2013). Image Classification with Growing Neural Networks. International Journal of Computer Theory and Engineering, 422–427. doi: https://doi.org/10.7763/ijcte.2013.v5.722
  16. Palomo, E. J., Lopez-Rubio, E. (2016). The Growing Hierarchical Neural Gas Self-Organizing Neural Network. IEEE Transactions on Neural Networks and Learning Systems, 1–10. doi: https://doi.org/10.1109/tnnls.2016.2570124
  17. Rere, L. M. R., Fanany, M. I., Arymurthy, A. M. (2016). Metaheuristic Algorithms for Convolution Neural Network. Computational Intelligence and Neuroscience, 2016, 1–13. doi: https://doi.org/10.1155/2016/1537325
  18. Maggiori, E., Tarabalka, Y., Charpiat, G., Alliez, P. (2017). High-Resolution Aerial Image Labeling With Convolutional Neural Networks. IEEE Transactions on Geoscience and Remote Sensing, 55 (12), 7092–7103. doi: https://doi.org/10.1109/tgrs.2017.2740362

Downloads

Published

2018-07-31

How to Cite

Moskalenko, V., Dovbysh, A., Naumenko, I., Moskalenko, A., & Korobov, A. (2018). Improving the effectiveness of training the on-board object detection system for a compact unmanned aerial vehicle. Eastern-European Journal of Enterprise Technologies, 4(9 (94), 19–26. https://doi.org/10.15587/1729-4061.2018.139923

Issue

Vol. 4 No. 9 (94) (2018): Information and controlling system

Section

Information and controlling system

License

Copyright (c) 2018 Vyacheslav Moskalenko, Anatoliy Dovbysh, Igor Naumenko, Alyona Moskalenko, Artem Korobov

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

The consolidation and conditions for the transfer of copyright (identification of authorship) is carried out in the License Agreement. In particular, the authors reserve the right to the authorship of their manuscript and transfer the first publication of this work to the journal under the terms of the Creative Commons CC BY license. At the same time, they have the right to conclude on their own additional agreements concerning the non-exclusive distribution of the work in the form in which it was published by this journal, but provided that the link to the first publication of the article in this journal is preserved.

A license agreement is a document in which the author warrants that he/she owns all copyright for the work (manuscript, article, etc.).
The authors, signing the License Agreement with TECHNOLOGY CENTER PC, have all rights to the further use of their work, provided that they link to our edition in which the work was published.
According to the terms of the License Agreement, the Publisher TECHNOLOGY CENTER PC does not take away your copyrights and receives permission from the authors to use and dissemination of the publication through the world's scientific resources (own electronic resources, scientometric databases, repositories, libraries, etc.).
In the absence of a signed License Agreement or in the absence of this agreement of identifiers allowing to identify the identity of the author, the editors have no right to work with the manuscript.
It is important to remember that there is another type of agreement between authors and publishers – when copyright is transferred from the authors to the publisher. In this case, the authors lose ownership of their work and may not use it in any way.