Human localization in video frames using a growing neural gas algorithm and fuzzy inference
O.S. Amosov, Y.S. Ivanov, S.V. Zhiganov

 

Komsomolsk-on-Amur State Technical University, Komsomolsk-on-Amur, Russia

Full text of article: Russian language.

 PDF

Abstract:
A problem of human body localization in video frames using growing neural gas and feature description based on the Histograms of Oriented Gradients is solved. The original neuro-fuzzy model of growing neural gas for reinforcement learning (GNG-FIS) is used as a basis of the algorithm. A modification of the GNG-FIS algorithm using a two-pass training with fuzzy remarking of classes and building of a heat map is also proposed.
As follows from the experiments, the index of the correct localizations of the developed classifier from 90.5% to 93.2%, depending on the conditions of the scene, that allows the use of the algorithm in real systems of situational video analytics.

Keywords:
human localization, growing neural gas, clustering, fuzzy inference.

Citation:
Amosov OS, Ivanov YS, Zhiganov SV. Human localiztion in video frames using a growing neural gas algorithm and fuzzy inference. Computer Optics 2017; 41(1): 46-58. DOI: 10.18287/2412-6179-2017-41-1-46-58.

References:

  1. Amosov OS, Ivanov YS. Modified algorithm of localization of license plates of vehicles based on the method of Viola-Jones [in Russian]. Informatics and Control Systems 2014; 39(1); 127-140.
  2. Melnikov II, Demidenko SV, Evseenko IA, Emelyanov IA. Motion detection based on pulsed neural networks [In Russian]. Information Technology 2013; 7: 57-60.
  3. Viola P, Jones M. Robust real-time face detection. International Journal of Computer Vision 2004; 57(2): 137-154. DOI: 10.1023/B:VISI.0000013087.49260.fb.
  4. Minaev EY, Nikonorov AV. Object detection and recognition in the driver assistace system based on the fractal analysis [in Russian]. Computer Optics 2012; 36(1): 124-130.
  5. Viola P, Jones MJ, Snow D. Detecting Pedestrians Using Patterns of Motion and Appearance. Int J Comput Vision 2005; 63(2): 153-161. DOI: 10.1007/s11263-005-6644-8.
  6. Enzweiler M, Dariu MG. Monocular Pedestrian Detection: Survey and Experiments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009; 31(12): 2179-2195. DOI: 10.1109/TPAMI.2008.260.
  7. Dalal N, Triggs B. Histograms of oriented gradients for human detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2005: 886-893. DOI: 10.1109/CVPR.2005.177.
  8. Cristianini N, Shawe-Taylor J. An introduction to support Vector Machines and other kernel-based learning methods. Cambridge: Cambridge University Press; 2000. ISBN: 978-0521780193.
  9. Lectures on the method of support vector machine [In Russian]. Source: <http://www.ccas.ru/voron/download/SVM.pdf>.
  10. Kazakov A, Bovyrin A. Fast algorithm for the detection of pedestrians on the video data [in Russian]. The 22nd International Conference on Computer Graphics and Vision 2012; 144-148.
  11. Cho H, Rybski PE, Bar-Hillel A and Zhang W. Real-time pedestrian detection with deformable part models. Intelligent Vehicles Symposium (IV), 2012 IEEE, Alcala de Henares 2012: 1035-1042. DOI: 10.1109/IVS.2012.6232264.
  12. Hua С, Makihara Y, Yagi Y. Pedestrian detection by using spatio temporal histogram of oriented gradients. IEICE Transactions on Information and Systems 2013; E96-D(6): P. 1376-1386. DOI: 10.1587/transinf.E96.D.1376.
  13. Vapnik VN. An overview of statistical learning theory. IEEE Transactions on Neural Networks 1999; 10(5): 988-999. DOI: 10.1109/72.788640.
  14. Vorontsov KV. Mathematical methods of training on precedents (machine learning theory) [In Russian]. Source: <http://www.machinelearning.ru/wiki/images/6/6d/Voron-ML-1.pdf>.
  15. Ciresan D, Meier U, Schmidhuber J. Multi-column deep neural networks for image classification. CVPR '12 2012: 3642-49. DOI: 10.1109/CVPR.2012.6248110.
  16. Ciresan D, Meier U, Masci J, Gambardella L, Schmidhuber J. Flexible, high performance convolutional neural networks for image classification. In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI '11) 2011; 2: 1237-1242. DOI: 10.5591/978-1-57735-516-8/IJCAI11-210.
  17. Karungaru SG, Fukumi M, Akamatsu N. Face recognition in colour images using neural networks and genetic algorithms. International Journal of Computational Intelligence and Applications 2005; 5(1); 55-67; DOI: 10.1142/S1469026805001477.
  18. Soldatova OP, Garshin AA. Convolutional neural network applied to handwritten digits recognition [In Russian]. Computer Optics 2010; 34(2): 252-259.
  19. Verma A, Hebbalaguppe R, Vig L, Kumar S, Hassan E. Pedestrian detection via mixture of CNN experts and thresholded aggregated channel features. ICCVW '15 2015: 555-563. DOI: 10.1109/ICCVW.2015.78.
  20. Ouyang W, Wang X. Joint deep learning for pedestrian detection. ICCV '13 2013: 2056-2063. DOI: 10.1109/ICCV.2013.257.
  21. Haykin S. Neural Networks: A Comprehensive Foundation. Upper Saddle River, NJ, USA: Prentice Hall PTR; 1998. ISBN: 0132733501.
  22. Kohonen T. Self-organizing maps. Berlin, Heidelberg: Springer-Verlag; 2001. ISBN: 978-3-540-67921-9.
  23. Wasserman PD. Neural computing: theory and practice. New York, NY, USA: Van Nostrand Reinhold Co.; 1989. ISBN:0-442-20743-3.
  24. Martinetz TM, Berkovich SG, Schulten KJ. "Neural-gas" network for vector quantization and its application to time series prediction. IEEE Transactions on Neural Networks 1993; 4(4): 558-569. DOI: 10.1109/72.238311.
  25. Fawcett T. An introduction to ROC analysis. Pattern Recognition Letters – Special issue: ROC analysis in pattern recognition 2006; 27(8): 861-874. DOI: 10.1016/j.patrec.2005.10.010.
  26. Goto Y, Yamauchi Y, Fujiyoshi H. CS-HOG: Color similarity-based HOG. FCV 2013: 266-271. DOI: 10.1109/FCV.2013.6485502.
  27. Agoston MK. Computer graphics and geometric modeling: Implementation and algorithms. London: Springer; 2005. ISBN: 978-1-85233-818-3. DOI: 10.1007/b138805.
  28. Pizer SM, Amburn EP, Austin JD, et al. Adaptive histogram equalization and its variations. Computer Vision, Graphics, and Image Processing 1987; 39(3); 355-368. DOI: 10.1016/S0734-189X(87)80186-X.
  29. The image processing library OpenCV. Source:<http://docs.opencv.org/>.
  30. Beyer O, Cimiano P. Online semi-supervised growing neural gas. International Journal of Neural Systems 2012; 22(5): 425-435. DOI: 10.1142/S0129065712500232.
  31. Qin AK, Suganthan PK. Robust growing neural gas algorithm with application in cluster analysis. Neural Networks 2004; 17(8): 1135-1148. DOI: 10.1016/j.neunet.2004.06.013.
  32. Beyer O, Cimiano P. Online labelling strategies for growing neural gas. IDEAL 2011: 76-83. DOI: 10.1007/978-3-642-23878-9_10.
  33. Muravev AS, Belousov AA. Modified algorithm of growing neural gas applied to the problem of classification [In Russian]. Siberia Science Bulletin 2014; 4(14); 105-111.
  34. Ayvazyan SA, Buchstaber VM, Enyukov IS, Meshalkin LD. Applied Statistics: Classification and reduction of dimension [In Russian]. Moscow: "Finansy i Statistica" Publisher; 1989.
  35. INRIA Person Dataset. Source: <http://pascal.inrialpes.fr/data/human/>.
  36. Caltech Pedestrian Detection Benchmark. Source: <http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/ >.
  37. Amosov OS, Malashevskaya EA, Baena SG. High-speed neurofuzzy algorithms for filtering the mobile object trajectory parameters. 23rd Saint Petersburg International Conference on Integrated Navigation Systems, ICINS 2016: 389-392.
  38. Park YM, Moon UC, Lee KY. A self-organizing fuzzy logic controller for dynamic systems using a fuzzy auto-regressive moving average model. IEEE Transactions on Fuzzy Systems 1995; 3(1): 75-82. DOI: 10.1109/91.366563.
  39. Jang J.-SR. ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man and Cybernetics 1993; 23(3): 665-685. DOI: 10.1109/21.256541.
  40. Dollar P, Wojek C, Schiele B, Perona P. Pedestrian detection: An evaluation of the state of the art. IEEE PAMI 2012; 34(4): 743-761. DOI: 10.1109/TPAMI.2011.155.
© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: journal@computeroptics.ru; Phones: +7 (846) 332-56-22, Fax: +7 (846) 332-56-20