Improving the model of object detection on aerial photographs and video in unmanned aerial systems

Authors

DOI:

https://doi.org/10.15587/1729-4061.2022.252876

Keywords:

neural network, object detection, VisDrone 2021, Microsoft COCO, YOLOv5x, unmanned aerial system

Abstract

This paper considers a model of object detection on aerial photographs and video using a neural network in unmanned aerial systems. The development of artificial intelligence and computer vision systems for unmanned systems (drones, robots) requires the improvement of models for detecting and recognizing objects in images and video streams. The results of video and aerial photography in unmanned aircraft systems are processed by the operator manually but there are objective difficulties associated with the operator’s processing of a large number of videos and aerial photographs, so it is advisable to automate this process. Analysis of neural network models has revealed that the YOLOv5x model (USA) is most suitable, as a basic model, for performing the task of object detection on aerial photographs and video. The Microsoft COCO suite (USA) is used to train this model. This set contains more than 200,000 images across 80 categories. To improve the YOLOv5x model, the neural network was trained with a set of VisDrone 2021 images (China) with the choice of such optimal training parameters as the optimization algorithm SGD; the initial learning rate (step) of 0.0005; the number of epochs of 25. As a result, a new model of object detection on aerial photographs and videos with the proposed name VisDroneYOLOv5x was obtained. The effectiveness of the improved model was studied using aerial photographs and videos from the VisDrone 2021 set. To assess the effectiveness of the model, the following indicators were chosen as the main indicators: accuracy, sensitivity, the estimation of average accuracy. Using a convolutional neural network has made it possible to automate the process of object detection on aerial photographs and video in unmanned aerial systems.

Author Biographies

Vadym Slyusar, Central Scientific Research Institute of Armament and Military Equipment of the Armed Forces of Ukraine

Doctor of Technical Sciences, Professor

Research Institute Group

Mykhailo Protsenko, Central Scientific Research Institute of Armament and Military Equipment of the Armed Forces of Ukraine

PhD, Senior Researcher

Office of Special Forces

Anton Chernukha, National University of Civil Defence of Ukraine

PhD, Associate Professor

Department of Service and Training

Vasyl Melkin, Central Scientific Research Institute of Armament and Military Equipment of the Armed Forces of Ukraine

PhD

Organizational and Scientific Division

Oleh Biloborodov, Central Scientific Research Institute of Armament and Military Equipment of the Armed Forces of Ukraine

Doctor of Technical Sciences

Research Unit

Mykola Samoilenko, Mykolayiv National Agrarian University

Doctor of Agricultural Sciences, Professor

Department of Viticulture and Horticulture

Olena Kravchenko, Mykolayiv National Agrarian University

PhD, Associate Professor

Department of Genetics, Animal Feeding and Biotechnology

Halyna Kalynychenko, Mykolayiv National Agrarian University

PhD, Associate Professor

Department of Livestock Production Technology

Anton Rohovyi, National Technical University "Kharkiv Polytechnic Institute"

PhD

Department of Strategic Management

Mykhaylo Soloshchuk, National Technical University "Kharkiv Polytechnic Institute"

PhD

Department of Computer Science and Intellectual Property

References

  1. Kuznetsova, Y., Somochkin, M. (2021). The concept of creating an intellectual core of an integrated information and analytical system for action in emergencies of man-made nature. Innovative Technologies and Scientific Solutions for Industries, 4 (18), 40–49. doi: https://doi.org/10.30837/itssi.2021.18.040
  2. Peng, F., Zheng, L., Cui, X., Wang, Z. (2021). Traffic flow statistics algorithm based on YOLOv3. 2021 International Conference on Communications, Information System and Computer Engineering (CISCE). doi: https://doi.org/10.1109/cisce52179.2021.9445932
  3. Bin Zuraimi, M. A., Kamaru Zaman, F. H. (2021). Vehicle Detection and Tracking using YOLO and DeepSORT. 2021 IEEE 11th IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE). doi: https://doi.org/10.1109/iscaie51753.2021.9431784
  4. Fedosov, V. P., Ibadov, S. R., Ibadov, R. R., Kucheryavenko, S. V. (2021). Method For Detecting Violation at a Pedestrian Crossing Using a Convolutional Neuaral Network. 2021 Radiation and Scattering of Electromagnetic Waves (RSEMW). doi: https://doi.org/10.1109/rsemw52378.2021.9494089
  5. Sindhu, V. S. (2021). Vehicle Identification from Traffic Video Surveillance Using YOLOv4. 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS). doi: https://doi.org/10.1109/iciccs51141.2021.9432144
  6. Kim, J., Koh, J., Lee, B., Yang, S., Choi J. (2021). Video Object Detection Using Object's Motion Context and Spatio-Temporal Feature Aggregation. 2020 25th International Conference on Pattern Recognition (ICPR). doi: https://doi.org/10.1109/icpr48806.2021.9412715
  7. Ahmed, A. A., Echi, M. (2021). Hawk-Eye: An AI-Powered Threat Detector for Intelligent Surveillance Cameras. IEEE Access, 9, 63283–63293. doi: https://doi.org/10.1109/access.2021.3074319
  8. Zhao, Z.-Q., Zheng, P., Xu, S.-T., Wu, X. (2019). Object Detection With Deep Learning: A Review. IEEE Transactions on Neural Networks and Learning Systems, 30 (11), 3212–3232. doi: https://doi.org/10.1109/tnnls.2018.2876865
  9. Redmon, J., Divvala, S., Girshick, R., Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi: https://doi.org/10.1109/cvpr.2016.91
  10. Slyusar, V., Protsenko, M., Chernukha, A., Gornostal, S., Rudakov, S., Shevchenko, S. et. al. (2021). Construction of an advanced method for recognizing monitored objects by a convolutional neural network using a discrete wavelet transform. Eastern-European Journal of Enterprise Technologies, 4 (9 (112)), 65–77. doi: https://doi.org/10.15587/1729-4061.2021.238601
  11. Redmon, J., Farhadi, A. (2017). YOLO9000: Better, Faster, Stronger. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi: https://doi.org/10.1109/cvpr.2017.690
  12. Knysh, B., Kulyk, Y. (2021). Improving a model of object recognition in images based on a convolutional neural network. Eastern-European Journal of Enterprise Technologies, 3 (9 (111)), 40–50. doi: https://doi.org/10.15587/1729-4061.2021.233786
  13. Huang, Z., Wang, J., Fu, X., Yu, T., Guo, Y., Wang, R. (2020). DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection. Information Sciences, 522, 241–258. doi: https://doi.org/10.1016/j.ins.2020.02.067
  14. Bochkovskiy, A., Wang, C.-Y., Liao, M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.org. Available at: https://arxiv.org/pdf/2004.10934.pdf
  15. Xu, R., Lin, H., Lu, K., Cao, L., Liu, Y. (2021). A Forest Fire Detection System Based on Ensemble Learning. Forests, 12 (2), 217. doi: https://doi.org/10.3390/f12020217
  16. Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., Zisserman, A. (2014). The Pascal Visual Object Classes Challenge: A Retrospective. International Journal of Computer Vision, 111 (1), 98–136. doi: https://doi.org/10.1007/s11263-014-0733-5 5
  17. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D. et. al. (2014). Microsoft COCO: Common Objects in Context. Lecture Notes in Computer Science, 740–755. doi: https://doi.org/10.1007/978-3-319-10602-1_48
  18. Zhu, P., Wen, L., Bian, X., Ling, H., Hu, Q. (2018). Vision meets drones: A challenge. arXiv.org. Available at: https://arxiv.org/pdf/1804.07437.pdf
  19. Ultralytics Yolov5 and Vision AI. Available at: https://github.com/ultralytics/yolov5
  20. Slyusar, V., Protsenko, M., Chernukha, A., Kovalov, P., Borodych, P., Shevchenko, S. et. al. (2021). Improvement of the model of object recognition in aero photographs using deep convolutional neural networks. Eastern-European Journal of Enterprise Technologies, 5 (2 (113)), 6–21. doi: https://doi.org/10.15587/1729-4061.2021.243094
  21. Slyusar, V., Protsenko, M., Chernukha, A., Melkin, V., Petrova, O., Kravtsov, M. et. al. (2021). Improving a neural network model for semantic segmentation of images of monitored objects in aerial photographs. Eastern-European Journal of Enterprise Technologies, 6 (2 (114)), 86–95. doi: https://doi.org/10.15587/1729-4061.2021.248390

Downloads

Published

2022-02-28

How to Cite

Slyusar, V., Protsenko, M., Chernukha, A., Melkin, V., Biloborodov, O., Samoilenko, M., Kravchenko, O., Kalynychenko, H., Rohovyi, A., & Soloshchuk, M. (2022). Improving the model of object detection on aerial photographs and video in unmanned aerial systems. Eastern-European Journal of Enterprise Technologies, 1(9(115), 24–34. https://doi.org/10.15587/1729-4061.2022.252876

Issue

Section

Information and controlling system