Advertisement

Object Detection in Aerial Photos Using Neural Networks

  • Egor S. Ivanov
  • Aleksandr V. Smirnov
  • Igor P. Tishchenko
  • Andrei N. VinogradovEmail author
Chapter
  • 18 Downloads
Part of the Studies in Computational Intelligence book series (SCI, volume 869)

Abstract

The paper describes the method of objects detection on aerial photographs using neural networks. The aim of this paper is to present an object detection algorithm by neural networks using sliding window. Main idea and main benefit of this concept is that image processing by sliding window with different sizes and that user can set possibility threshold for neural network classifying. This approach can be used with any neural network types because the goal of neural network in the method is to classify current part of image. For our experiments we took convolutional neural network and aerial photos. Also in this paper described the extension of this method. It’s an algorithm that allows post processing of data obtained as a result of the operation of neural networks. The problem of searching for aircraft in images is considered as an example. Some results of aircraft detection are presented in this paper. Image processing took place in distributed data processing system that also described in this paper.

Keywords

Remote sensing of the earth Recognition Image analysis Neural networks 

Notes

Acknowledgements

 This work was carried out with the financial support of the state represented by the Ministry of Education and Science of the Russian Federation (unique identifier of the project RFMEFI60419X0236)

References

  1. Cheng G, Han J (2016) A survey on object detection in optical remote sensing images. ISPRS J Photogramm Remote Sens 117:11–28CrossRefGoogle Scholar
  2. Chen Q, Sun Q, Heng PA, Xia D (2008) A double-threshold image binarization method based on edge detector. Pattern Recognit 41:1254–1267. https://www.researchgate.net/publication/220604236_A_double-threshold_image_binarization_method_based_on_edge_detector
  3. Cheng G, Zhou P, Han J (2016) Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images. IEEE Trans Geosci Remote Sens 54(12):7405–7415Google Scholar
  4. Dorogii YY (2012) Arkhitektura obobshchennykh svertochnykh neironnykh setei (The architecture of generalized convolutional neural networks), Vestnik NTUU KPII, 2012, No. 57, 6 p. Available at: http://www.itvisnyk.kpi.ua/wp-content/uploads/2012/08/54_36.pdf
  5. Face detection using haar cascades, OpenCV. Open source computer vision documentation. http://docs.opencv.org/trunk/d7/d8b/tutorial_py_face_detection.html
  6. Girshick RB, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE conference on computer vision and pattern recognition, CVPR 2014. https://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Girshick_Rich_Feature_Hierarchies_2014_CVPR_paper.pdf
  7. Hinton GE et al (2012a) Improving neural networks by preventing co-adaptation of feature detectors. arXiv:1207.0580v1, 3 July 2012
  8. Hinton GE, Srivastava N et al (2012b) Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580. https://pdfs.semanticscholar.org/2116/b2eaaece4af9c28c32af2728f3d49b792cf9.pdf
  9. Ivanov ES, Tishchenko IP, Vinogradov AN (2019) Multispectral image segmentation using neural network. Sovremennye problem DZZ iz kosmosa 16(1):25–34. http://d33.infospace.ru/d33_conf/sb2019t1/25-34.pdf
  10. Kondratyev A, Tishchenko I (2016) Concept of distributed processing system of images flow in terms of π-calculus. In: 2016 18th conference of open innovations association and seminar on information security and protection of information technology (FRUCT-ISPIT), pp 328–334Google Scholar
  11. Kriesel D (2007) A brief introduction to neural networks. ZETA2-EN. http://www.dkriesel.com/_media/science/neuronalenetze-enzeta2-2col-dkrieselcom.pdf
  12. Pitknen J (2001) Individual tree detection in digital aerial images by combining locally adaptive binarization and local maxima methods. Can J For Res 31(5):832–844Google Scholar
  13. Ren S et al (2017) Object detection networks on convolutional feature maps. IEEE Trans Pattern Anal Mach Intell 39(7):1476–1481. https://arxiv.org/pdf/1504.06066
  14. Romanov AA (2018) Svertochnye neironnye seti (Convolutional neural networks), Nauchnye issledovaniya: klyuchevye problemy III tysyacheletiya, 2018, pp 5–9. Available at: https://scientificresearch.ru/images/PDF/2018/21/svertochnye.pdf
  15. Rosebrock A (2015) Histogram of oriented gradients and object detection [Web log post]. Retrieved 31 Aug 2015. http://www.pyimagesearch.com/2014/11/10/histogram-oriented-gradients-object-detection/
  16. Sarangi N, Sekhar C (2015) Tensor deep stacking networks and kernel deep convex networks. In: 4th International conference on pattern recognition: applications and methods, IC RAM, 2015, pp 267–281. https://link.springer.com/chapter/10.1007/978-3-319-27677-=9_17
  17. Ševo I, Avramovic A (2016) Convolutional neural network based automatic object detection on aerial images. IEEE Geosci Remote Sens Lett 13(5):740–744CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Egor S. Ivanov
    • 1
  • Aleksandr V. Smirnov
    • 1
  • Igor P. Tishchenko
    • 1
  • Andrei N. Vinogradov
    • 2
    Email author
  1. 1.Ailamazyan Program Systems Institute of RAS (PSI RAS)Pereslavl DistrictRussia
  2. 2.Department of Information TechnologiesPeoples’ Friendship University of Russia (RUDN University)MoscowRussia

Personalised recommendations