DOI: https://doi.org/10.15587/1729-4061.2019.164789

Development of the modified methods to train a neural network to solve the task on recognition of road users

Ievgen Fedorchenko, Andrii Oliinyk, Alexander Stepanenko, Tetiana Zaiko, Serhii Shylo, Anton Svyrydenko

Abstract


We have developed modifications of a simple genetic algorithm for pattern recognition. In the proposed modification Alpha-Beta, at the stage of selection of individuals to the new population the individuals are ranked in terms of fitness, then the number of pairs is randomly determined ‒ a certain number of the fittest individuals, and the same number of the least adapted. The fittest individuals form the subset B, those least adapted ‒ the subset W. Both subsets are included in a set of pairs V. The number of individuals that can be selected to pairs is in the range of 20‒60 % of the total number of individuals. In the modification Alpha Beta fixed compared to the original version of a simple genetic algorithm we added a possibility of the emergence of two mutations, added a fixed point of intersection, as well as changed the selection of individuals for crossbreeding. This makes it possible to increase the indicator of accuracy in comparison with the basic version of a simple genetic algorithm. In the modification Fixed a fixed point of intersection was established. The cross-breeding involves half the genes ‒ those genes that are responsible for the number of neurons in layers, values for other genes are always passed to the descendants from one of the individuals. In addition, at the stage of mutation there are randomly occurring mutations using a Monte-Carlo method.

The developed methods were implemented in software to solve the task on recognizing motorists (cars, bicycles, pedestrians, motorcycles, trucks). We also compared indicators for using modifications of a simple genetic algorithm and determined the best approach to solving the task on recognizing road traffic participants. It was found that the developed modification Alpha-Beta showed better results compared to other modifications when solving the task on recognizing road traffic participants. When applying the developed modifications, the following indicators for the accuracy of Alpha-Beta were obtained ‒ 96.90 %, Alpha‒Beta fixed ‒ 95.89 %, fixed ‒ 85.48 %. In addition, applying the developed modifications reduces the time for the neuromodel’s parameters selection, specifically using the Alpha-Beta modification employs only 73.9 % of the time required by the basic method, applying the Fixed modification ‒ 91.1 % of the time required by the basic genetic method

Keywords


pattern recognition; genetic algorithm; evolutionary algorithm; neural networks; Python; OpenCV; Keras

References


Dorosinskiy, L. G. (2011). Raspoznavanie izobrazheniy, neyronnye seti i geneticheskie algoritmy. Advances in current natural sciences, 10, 87–88.

Ekspert robototekhniki: «Nikogda ne ispol'zuyte avtopilot Tesla ryadom s velosipedistami!». Available at: https://itc.ua/news/ekspert-robototehniki-nikogda-ne-ispolzuyte-avtopilot-tesla-ryadom-s-velosipedistami/

Mazda I-Activsense. Available at: http://mazda.ua/ru/showroom/cx-5/i-activsense/

Waymo. Available at: https://waymo.com/

Zhang, Y., Ling, Q. (2017) Bicycle Detection Based On Multi-feature and Multi-frame Fusion in Low-Resolution Traffic Videos. arXiv. Available at: https://arxiv.org/pdf/1706.03309.pdf

Dalal, N., Triggs, B. (2005). Histograms of Oriented Gradients for Human Detection. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). doi: https://doi.org/10.1109/cvpr.2005.177

Dopico, J. R. R., Dorado, J., Pazos, A. (Eds.) (2009). Encyclopedia of artificial intelligence. IGI Global. doi: https://doi.org/10.4018/978-1-59904-849-9

Ben-Hur, A., Horn, D., Siegelmann, H. T., Vapnik, V. (2001). Support vector clustering. Journal of Machine Learning Research, 2, 125–137.

Viola, P., Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001. doi: https://doi.org/10.1109/cvpr.2001.990517

Viola, P., Jones, M. J. (2004). Robust Real-Time Face Detection. International Journal of Computer Vision, 57 (2), 137–154. doi: https://doi.org/10.1023/b:visi.0000013087.49260.fb

Peppa, M. V., Bell, D., Komar, T., Xiao, W. (2018). Urban traffic flow analysis based on deep learning car detection from CCTV image series. ISPRS – International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-4, 499–506. doi: https://doi.org/10.5194/isprs-archives-xlii-4-499-2018

Ren, S., He, K., Girshick, R., Sun, J. (2017). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39 (6), 1137–1149. doi: https://doi.org/10.1109/tpami.2016.2577031

Liu, W., Anguelov, D., Erhan D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A. C. (2016). SSD: Single Shot MultiBox Detector. Computer Vision – ECCV 2016, 21–37. doi: https://doi.org/10.1007/978-3-319-46448-0_2

Xuze, Z., Shengsuo, N., Teng, H. (2018). A CNN Vehicle Recognition Algorithm based on Reinforcement Learning Error and Error-prone Samples. IOP Conference Series: Earth and Environmental Science, 153, 032052. doi: https://doi.org/10.1088/1755-1315/153/3/032052

Krizhevsky, A., Sutskever, I., Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. In NIPS, 1097–1105.

Leibe, B., Seemann, E., Schiele, B. (2005). Pedestrian Detection in Crowded Scenes. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). doi: https://doi.org/10.1109/cvpr.2005.272

Du, X., El-Khamy, M., Morariu, V. I., Lee, J., Davis, L. (2018). Fused Deep Neural Networks for Efficient Pedestrian Detection. arXiv. Available at: https://arxiv.org/pdf/1805.08688.pdf

He, M., Luo, H., Chang, Z., Hui, B. (2017). Pedestrian Detection with Semantic Regions of Interest. Sensors, 17 (11), 2699. doi: https://doi.org/10.3390/s17112699

Adu-Gyamf, Y. O. (2017). Automated Vehicle Recognition with Deep Convolutional Neural Networks. Iowa State University Digital Repository, 12. Available at: https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=1182&context=ccee_pubs

Lipton, A. J., Fujiyoshi, H., Patil, R. S. (1998). Moving target classification and tracking from real-time video. Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201). doi: https://doi.org/10.1109/acv.1998.732851

Cohen, I., Medioni, G. (1999). Detecting and tracking moving objects for video surveillance. Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149). doi: https://doi.org/10.1109/cvpr.1999.784651

Luo, P., Tian, Y., Wang, X., Tang, X. (2014). Switchable Deep Network for Pedestrian Detection. 2014 IEEE Conference on Computer Vision and Pattern Recognition. doi: https://doi.org/10.1109/cvpr.2014.120

Tombari, F., Salti, S., Di Stefano, L. (2013). Performance Evaluation of 3D Keypoint Detectors. International Journal of Computer Vision, 102 (1-3), 198–220. doi: https://doi.org/10.1007/s11263-012-0545-4

Fan, J., Xu, W., Wu, Y., Gong, Y. (2010). Human Tracking Using Convolutional Neural Networks. IEEE Transactions on Neural Networks, 21 (10), 1610–1623. doi: https://doi.org/10.1109/tnn.2010.2066286

Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., LeCun, Y. (2009). What is the best multi-stage architecture for object recognition? 2009 IEEE 12th International Conference on Computer Vision. doi: https://doi.org/10.1109/iccv.2009.5459469

Oliinyk, A., Subbotin, S., Lovkin, V., Leoshchenko, S., Zaiko, T. (2018). Development of the indicator set of the features informativeness estimation for recognition and diagnostic model synthesis. 2018 14th International Conference on Advanced Trends in Radioelecrtronics, Telecommunications and Computer Engineering (TCSET). doi: https://doi.org/10.1109/tcset.2018.8336342

Oliinyk, A. A., Subbotin, S. A. (2016). A stochastic approach for association rule extraction. Pattern Recognition and Image Analysis, 26 (2), 419–426. doi: https://doi.org/10.1134/s1054661816020139

Oliinyk, A. O., Zayko, T. A., Subbotin, S. O. (2014). Synthesis of Neuro-Fuzzy Networks on the Basis of Association Rules. Cybernetics and Systems Analysis, 50 (3), 348–357. doi: https://doi.org/10.1007/s10559-014-9623-7

Stepanenko, A., Oliinyk, A., Deineha, L., Zaiko, T. (2018). Development of the method for decomposition of superpositions of unknown pulsed signals using the second­order adaptive spectral analysis. Eastern-European Journal of Enterprise Technologies, 2 (9 (92)), 48–54. doi: https://doi.org/10.15587/1729-4061.2018.126578

Alsayaydeh, J. A. J., Shkarupylo, V., Bin Hamid, M. S., Skrupsky, S., Oliinyk, A. (2018). Stratified model of the internet of things infrastructure. Journal of Engineering and Applied Sciences, 13 (20), 8634–8638.

Shkarupylo, V., Skrupsky, S., Oliinyk, A., Kolpakova, T. (2017). Development of stratified approach to software defined networks simulation. Eastern-European Journal of Enterprise Technologies, 5 (9 (89)), 67–73. doi: https://doi.org/10.15587/1729-4061.2017.110142

Kolpakova, T., Oliinyk, A., Lovkin, V. (2017). Improved method of group decision making in expert systems based on competitive agents selection. 2017 IEEE First Ukraine Conference on Electrical and Computer Engineering (UKRCON). doi: https://doi.org/10.1109/ukrcon.2017.8100388

Oliinyk, A., Fedorchenko, I., Stepanenko, A., Rud, M., Goncharenko, D. (2018). Evolutionary Method for Solving the Traveling Salesman Problem. 2018 International Scientific-Practical Conference Problems of Infocommunications. Science and Technology (PIC S&T). doi: https://doi.org/10.1109/infocommst.2018.8632033


GOST Style Citations


Dorosinskiy L. G. Raspoznavanie izobrazheniy, neyronnye seti i geneticheskie algoritmy // Advances in current natural sciences. 2011. Issue 10. P. 87–88.

Ekspert robototekhniki: «Nikogda ne ispol'zuyte avtopilot Tesla ryadom s velosipedistami!». URL: https://itc.ua/news/ekspert-robototehniki-nikogda-ne-ispolzuyte-avtopilot-tesla-ryadom-s-velosipedistami/

Mazda I-Activsense. URL: http://mazda.ua/ru/showroom/cx-5/i-activsense/

Waymo. URL: https://waymo.com/

Zhang Y., Ling Q. Bicycle Detection Based On Multi-feature and Multi-frame Fusion in Low-Resolution Traffic Videos // arXiv. 2017. URL: https://arxiv.org/pdf/1706.03309.pdf

Dalal N., Triggs B. Histograms of Oriented Gradients for Human Detection // 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). 2005. doi: https://doi.org/10.1109/cvpr.2005.177 

Encyclopedia of artificial intelligence / J. R. R. Dopico, J. Dorado, A. Pazos (Eds.). IGI Global, 2009. doi: https://doi.org/10.4018/978-1-59904-849-9 

Support vector clustering / Ben-Hur A., Horn D., Siegelmann H. T., Vapnik V. // Journal of Machine Learning Research. 2001. Vol. 2. P. 125–137.

Viola P., Jones M. Rapid object detection using a boosted cascade of simple features // Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001. 2001. doi: https://doi.org/10.1109/cvpr.2001.990517 

Viola P., Jones M. J. Robust Real-Time Face Detection // International Journal of Computer Vision. 2004. Vol. 57, Issue 2. P. 137–154. doi: https://doi.org/10.1023/b:visi.0000013087.49260.fb 

Urban traffic flow analysis based on deep learning car detection from CCTV image series / Peppa M. V., Bell D., Komar T., Xiao W. // ISPRS – International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2018. Vol. XLII-4. P. 499–506. doi: https://doi.org/10.5194/isprs-archives-xlii-4-499-2018 

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks / Ren S., He K., Girshick R., Sun J. // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017. Vol. 39, Issue 6. P. 1137–1149. doi: https://doi.org/10.1109/tpami.2016.2577031 

SSD: Single Shot MultiBox Detector / Liu W., Anguelov D., Erhan D., Szegedy C., Reed S., Fu C.-Y., Berg A. C. // Computer Vision – ECCV 2016. 2016. P. 21–37. doi: https://doi.org/10.1007/978-3-319-46448-0_2 

Xuze Z., Shengsuo N., Teng H. A CNN Vehicle Recognition Algorithm based on Reinforcement Learning Error and Error-prone Samples // IOP Conference Series: Earth and Environmental Science. 2018. Vol. 153. P. 032052. doi: https://doi.org/10.1088/1755-1315/153/3/032052 

Krizhevsky A., Sutskever I., Hinton G. E. ImageNet Classification with Deep Convolutional Neural Networks // In NIPS. 2012. P. 1097–1105.

Leibe B., Seemann E., Schiele B. Pedestrian Detection in Crowded Scenes // 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). 2005. doi: https://doi.org/10.1109/cvpr.2005.272 

Fused Deep Neural Networks for Efficient Pedestrian Detection / Du X., El-Khamy M., Morariu V. I., Lee J., Davis L. // arXiv. 2018. URL: https://arxiv.org/pdf/1805.08688.pdf

Pedestrian Detection with Semantic Regions of Interest / He M., Luo H., Chang Z., Hui B. // Sensors. 2017. Vol. 17, Issue 11. P. 2699. doi: https://doi.org/10.3390/s17112699 

Adu-Gyamf Y. O. Automated Vehicle Recognition with Deep Convolutional Neural Networks // Iowa State University Digital Repository. 2017. 12 p. URL: https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=1182&context=ccee_pubs

Lipton A. J., Fujiyoshi H., Patil R. S. Moving target classification and tracking from real-time video // Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201). 1998. doi: https://doi.org/10.1109/acv.1998.732851 

Cohen I., Medioni G. Detecting and tracking moving objects for video surveillance // Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149). 1999. doi: https://doi.org/10.1109/cvpr.1999.784651 

Switchable Deep Network for Pedestrian Detection / Luo P., Tian Y., Wang X., Tang X. // 2014 IEEE Conference on Computer Vision and Pattern Recognition. 2014. doi: https://doi.org/10.1109/cvpr.2014.120 

Tombari F., Salti S., Di Stefano L. Performance Evaluation of 3D Keypoint Detectors // International Journal of Computer Vision. 2013. Vol. 102, Issue 1-3. P. 198–220. doi: https://doi.org/10.1007/s11263-012-0545-4 

Human Tracking Using Convolutional Neural Networks / Fan J., Xu W., Wu Y., Gong Y. // IEEE Transactions on Neural Networks. 2010. Vol. 21, Issue 10. P. 1610–1623. doi: https://doi.org/10.1109/tnn.2010.2066286 

What is the best multi-stage architecture for object recognition? / Jarrett K., Kavukcuoglu K., Ranzato M. A., LeCun Y. // 2009 IEEE 12th International Conference on Computer Vision. 2009. doi: https://doi.org/10.1109/iccv.2009.5459469 

Development of the indicator set of the features informativeness estimation for recognition and diagnostic model synthesis / Oliinyk A., Subbotin S., Lovkin V., Leoshchenko S., Zaiko T. // 2018 14th International Conference on Advanced Trends in Radioelecrtronics, Telecommunications and Computer Engineering (TCSET). 2018. doi: https://doi.org/10.1109/tcset.2018.8336342 

Oliinyk A. A., Subbotin S. A. A stochastic approach for association rule extraction // Pattern Recognition and Image Analysis. 2016. Vol. 26, Issue 2. P. 419–426. doi: https://doi.org/10.1134/s1054661816020139 

Oliinyk A. O., Zayko T. A., Subbotin S. O. Synthesis of Neuro-Fuzzy Networks on the Basis of Association Rules // Cybernetics and Systems Analysis. 2014. Vol. 50, Issue 3. P. 348–357. doi: https://doi.org/10.1007/s10559-014-9623-7 

Development of the method for decomposition of superpositions of unknown pulsed signals using the second­order adaptive spectral analysis / Stepanenko A., Oliinyk A., Deineha L., Zaiko T. // Eastern-European Journal of Enterprise Technologies. 2018. Vol. 2, Issue 9 (92). P. 48–54. doi: https://doi.org/10.15587/1729-4061.2018.126578 

Stratified model of the internet of things infrastructure / Alsayaydeh J. A. J., Shkarupylo V., Bin Hamid M. S., Skrupsky S., Oliinyk A. // Journal of Engineering and Applied Sciences. 2018. Vol. 13, Issue 20. P. 8634–8638.

Development of stratified approach to software defined networks simulation / Shkarupylo V., Skrupsky S., Oliinyk A., Kolpakova T. // Eastern-European Journal of Enterprise Technologies. 2017. Vol. 5, Issue 9 (89). P. 67–73. doi: https://doi.org/10.15587/1729-4061.2017.110142 

Kolpakova T., Oliinyk A., Lovkin V. Improved method of group decision making in expert systems based on competitive agents selection // 2017 IEEE First Ukraine Conference on Electrical and Computer Engineering (UKRCON). 2017. doi: https://doi.org/10.1109/ukrcon.2017.8100388 

Evolutionary Method for Solving the Traveling Salesman Problem / Oliinyk A., Fedorchenko I., Stepanenko A., Rud M., Goncharenko D. // 2018 International Scientific-Practical Conference Problems of Infocommunications. Science and Technology (PIC S&T). 2018. doi: https://doi.org/10.1109/infocommst.2018.8632033 







Copyright (c) 2019 Ievgen Fedorchenko, Andrii Oliinyk, Alexander Stepanenko, Tetiana Zaiko, Serhii Shylo, Anton Svyrydenko

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

ISSN (print) 1729-3774, ISSN (on-line) 1729-4061