|Generate QR code
Open Access
Subscription Access
Detection and Classification of Vehicles in Ultra-High Resolutions Images Using Neural Networks
https://doi.org/10.47612/0514-7506-2022-89-2-275-282
Abstract
The paper proposes a deep neural network architecture based on the integration of the convolutional neural network Faster R-CNN with the Feature Pyramid Network module. Based on this approach, an algorithm for detecting and classifying vehicles in images and a corresponding model have been developed. A cross-platform environment ML.NET was used to train the proposed model. The results of comparing the effectiveness of the proposed approach and convolutional neural networks YOLO v4 and Faster R-CNN are presented. The improvement of the accuracy of detection and localization of different types of vehicles in ultra-high resolutions images is shown. Examples of processing ultra-high resolutions remote sensing images and appropriate recommendations are given.
About the Authors
Ch. Chen
School of Information Science and Technology at Zhejiang Shuren University; International Science and Technology Cooperation Base of Zhejiang Province: Remote Sensing Image Processing and Application
China
China
Hangzhou
A. A. Мinald
Belarusian State University
Belarus
Belarus
Minsk
R. P. Bohush
Polotsk State University
Belarus
Belarus
Novopolotsk
G. Ma
EarthView Image Inc.
China
China
Huzhou
Y. Weichen
EarthView Image Inc.
China
China
Huzhou
S. V. Аblameyko
Belarusian State University;
United Institute for Informatics Problems, National Academy of Sciences of Belarus
Belarus
Belarus
Minsk
References
1. Yuntao Li, Zhihuan Wu, Lei Li, Daoning Yang, Hongfeng Pang. J. Appl. Remote Sens., 15, N 2 (2021) 026505, doi: 10.1117/1.JRS.15.026505
2. Q. Tan, J. Ling, J. Hu, X. Qin, J. Hu. IEEE Access, 8 (2020) 153394—153402, doi: 10.1109/ACCESS.2020.3017894
3. Y. Koga, H. Miyazaki, R. Shibasaki. Remote Sens., 12 (2020) 575, doi: 10.3390/rs12030575
4. L. Yongxi, T. Javidi. Proc. 53rd Annual Allerton Conf. Communication, Control, and Computing (2015) 1091—1098, doi: 10.1109/ALLERTON.2015.7447130
5. W. Shao, W. Yang, G. Liu, J. Liu. Proc. IEEE Int. Geoscience and Remote Sensing Symposium (2012) 4379—4382, doi: 10.1109/IGARSS.2012.6350403
6. D. Vorobjov, I. Zakharova, R. Bohush, S. Ablameyko. Advances in Neural Networks-ISNN2018.
7. Lecture Notes in Computer Science, 10878 (2018) 503—510, doi: 10.1007/978-3-319-92537-0
8. И. Н. Пугачев, Г. Я. Маркелов, В. С. Тормозов. Вестн. ТОГУ, 45, № 2 (2017) 13—20
9. Xungen Li, Feifei Men, Shuaishuai Lv, Xiao Jiang, Mian Pan, Qi Ma, Haibin Yu. ISPRS Int. J. GeoInformation, 10 (2021) 549, doi: 10.3390/ijgi10080549
10. A. Froidevaux, A. Julier, A. Lifschitz, M. Pham, R. Dambreville, S. Lefèvre, P. Lassalle, T. Huynh. IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, Sept. (2020) 256—259, ff10.1109/IGARSS39084.2020.9323827ff. ffhal-03213855
11. R. Girshick, J. Donahue, T. Darrell, J. Malik. IEEE Transact. Pattern Analysis and Machine Intelligence, 38 (2016) 142—158
12. R. Girshick. Proc. IEEE Int. Conf. Computer Vision. Santiago, Chile (2015) 1440—1448
13. S. Ren, K. He, R. Girshick, J. Sun. IEEE Transact. Pattern Analysis and Machine Intelligence, 39 (2015) 1137—1149
14. D. R. Lucio, R. Laroca, L. A. Zanlorensi, G. Moreira, D. Menotti. Region Detection Using Coarse Annotations, doi: 10.1109/SIBGRAPI.2019.00032, arXiv:1908.00069
15. T.-Yi Lin, P. Dollar, R. Girshick, K. He, B. Hariharan, S. Belongie. Feature Pyramid Networks for Object Detection arXiv:1612.03144v2 [cs.CV] 19 Apr 2017
16. https://github.com/jekhor/aerial-cars-dataset
17. M. Everingham, L. V. Gool, C. K. I. Williams, J. Winn, A. Zisserman. Int. J. Computer Vision, 88 (2010) 303—338, doi: 10.1007/s11263-009-0275-4
18. https://arxiv.org/pdf/2004.10934.pdf
Review
For citations:
Chen Ch., Мinald A.A., Bohush R.P., Ma G., Weichen Y., Аblameyko S.V. Detection and Classification of Vehicles in Ultra-High Resolutions Images Using Neural Networks. Zhurnal Prikladnoii Spektroskopii. 2022;89(2):275-282. (In Russ.) https://doi.org/10.47612/0514-7506-2022-89-2-275-282
Views: 416
Email this article 