Study of the dependence of accuracy in vehicles search on the size of the object using UAV images

Rostyslav Tsekhmystro, Oleksii Rubel, Vladimir Lukin

Abstract


Digital images are increasingly used to analyze different types of objects and their localization and classification. There are many areas for using this information; it is often employed for surveillance systems, automatic driving of vehicles, or exploration of new territories. At the same time, there are a fairly large number of neural networks that allow implementation of this functionality by training them using data sets of various types and classifications. Often, data sets created with the help of unmanned aerial vehicles are frequently used for research tasks. Such datasets allow the recognition of various types of objects without direct access to them, which allows safe exploration of different territories. The use of unmanned aerial vehicles is quite common nowadays, especially in the fields of photography and videography. Many photographers use unmanned aerial vehicles to take pictures of landscapes and use automatic tracking systems for movement. Automatic movement systems and object search systems are quite sensitive to the size of the object and the quality of the search algorithm. Because of the wide applicability of this task, as well as the small amount of initial data, the topic of our work is the study of the dependence of the accuracy of localization and classification of objects on their area in images obtained using unmanned aerial vehicles. The main subject of this study is the quality of neural networks that allow obtaining information about objects, as well as research by obtaining statistical data and a test set of data on the dependence of detection accuracy on the size of the object. The goal of this study was to obtain statistics on the accuracy of localization and classification depending on the size of the object and to determine the accuracy thresholds using the obtained statistics. The task of this study is to train common neural networks with an open architecture on a set of data obtained using unmanned aerial vehicles and to determine their characteristics, particularly the dependence of recognition accuracy on the size of the object. The expected result of the work is the threshold values of the size of the object, which are permissible for a sufficiently accurate classification and localization of objects, as well as the metrics of the quality of the work of the studied neural networks. Because of this work, conclusions are given that reflect the threshold values of object sizes, on which the recognition accuracy depends.

Keywords


object localization; YOLO v5; SSD; FasterRCNN; vehicle classification; unnamed aerial object

Full Text:

PDF

References


Bondžulić, B., Stojanović, N., Lukin, V., Stankevich, S. A., Bujaković, D., & Kryvenko, S. Target acquisition performance in the presence of JPEG image compression. Defence Technology, 2023. DOI: 10.1016/j.dt.2023.12.006.

Wang, L., Tang, J., & Liao, Q. A Study on Radar Target Detection Based on Deep Neural Networks. IEEE Sensors Letters, 2019, vol. 3, no. 3, article no. 7000504. DOI: 10.1109/LSENS.2019.2896072.

Yu, S. Sonar Image Target Detection Based on Deep Learning. Mathematical Problems in Engineering, 2022, vol. 2022, article no. 5294151. DOI: 10.1155/2022/5294151.

Zhao, M., Li, W., Li, L., Hu, J., Ma, P., & Tao, R. Single-Frame Infrared Small-Target Detection: A survey. IEEE Geoscience and Remote Sensing Magazine, 2022, vol. 10, no. 2, pp. 87-119. DOI: 10.1109/MGRS.2022.3145502.

Cox, T. H., Somers, I. & Fratello, D. J. Earth Observations and the Role of UAVs: A Capabilities Assessment. NASA, 2007. 346 p.

Boukoberine, M. N., Zhou, Z. & Benbouzid, M. A critical review on unmanned aerial vehicles power supply and energy management: Solutions, strategies, and prospects. Applied Energy, 2019, vol. 255, paper no. 113823. DOI: 10.1016/j.apenergy.2019.113823.

Xiuling, Z., Huijuan, W., Yu, S., Gang, C., Suhua, Z. & Quanbo, Y. Starting from the structure: A review of small object detection based on deep learning. Image and Vision Computing, 2024, vol. 146, paper no. 105054. DOI: 10.1016/j.imavis.2024.105054.

Tsekhmystro, R., Rubel, O. & Lukin, V. Investigation of the effect of object size on accuracy of human localisation in images acquired from unmanned aerial vehicles. Aerospace Technic and Technology, 2024, no. 2, pp. 83-90. DOI: 10.32620/aktt.2024.2.09.

Tang, G., Ni, J., Zhao, Y., Gu, Y. & Cao, W. A Survey of Object Detection for UAVs Based on Deep Learning. Remote Sensing, 2024, vol. 16, no. 1, article no. 149. DOI: 10.3390/rs16010149.

Yamani, A., Alyami, A., Luqman, H., Ghanem, B. & Giancola, S. Active Learning for Single-Stage Object Detection in UAV Images. 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 1849-1858. DOI: 10.1109/WACV57701.2024.00187.

Agrawal, P., Girshick, R. & Malik, J. Analyzing the Performance of Multilayer Neural Networks for Object Recognition. Computer Vision – ECCV 2014, 2014, vol. 8695, pp. 329–344. DOI: 10.1007/978-3-319-10584-0_22.

Ren, J. & Wang, Y. Overview of Object Detection Algorithms Using Convolutional Neural Networks. Journal of Computer and Communications, no. 10, pp. 115–132. DOI: 10.4236/jcc.2022.101006.

Khan, S. A., Lee, H. J. & Lim, H. Enhancing Object Detection in Self-Driving Cars Using a Hybrid Approach. Electronics, 2023, vol. 12, no. 13, article no. 2768. DOI: 10.3390/electronics12132768.

Padilla, R., Netto, S. L. & da Silva, E. A. B. A Survey on Performance Metrics for Object-Detection Algorithms. 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), 2020, pp. 237-242. DOI: 10.1109/IWSSIP48289.2020.9145130.

Tsekhmystro, R., Rubel, O. & Lukin, V. Study of methods for searching and localizing objects in images from aircraft using convolutional neural networks. Radioelectronic and Computer Systems, 2024, vol. 109, no. 1, pp. 87-98. DOI: 10.32620/reks.2024.1.08.

Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S. Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 658-666. DOI: 10.48550/arXiv.1902.09630.

Ting, K. M. Precision and Recall. Encyclopedia of Machine Learning, 2010. 781 p. DOI: 10.1007/978-0-387-30164-8_652.

Lian, J., Yuhang, Y., Linhui, L., Zhenghao, W. & Yafu, Z. Small Object Detection in Traffic Scenes Based on Attention Feature Fusion. Sensors, 2021, no. 9, article no. 3031. DOI: 10.3390/s21093031.

Rahman, S., Rony, J. H., Uddin, J. & Samad, M. A. Real-Time Obstacle Detection with YOLOv8 in a WSN Using UAV Aerial Photography. Journal of Imaging, 2023, vol. 9, no. 10, article no. 216. DOI: 10.3390/jimaging9100216.

Girshick, R. Fast R-CNN. 2015 IEEE International Conference on Computer Vision (ICCV), 2015, pp. 1440-1448. DOI: 10.1109/ICCV.2015.169.

Zhu, P., Wen, L., Du, D., Bian, X., Fan, H., Hu, Q., & Ling, H. Detection and Tracking Meet Drones Challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, vol. 44, no. 11, pp. 7380-7399. DOI: 10.1109/TPAMI.2021.3119563.

Du, D., Qi, Y., Yu, H., Yang, Y., Duan, K., Li, G., Zhang, W., Huang, Q., & Tian, Q. The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking. European Conference on Computer Vision (ECCV), 2018, vol. 128, pp. 1141-1159. DOI: 10.1007/s11263-019-01266-1.

Wallach, D. & Goffinet, B. Mean squared error of prediction as a criterion for evaluating and comparing system models. Ecological Modelling, 1989, vol. 44, pp. 299-306. DOI: 10.1016/0304-3800(89)90035-5.

Ruby, U., Theerthagiri, P., Jacob, J. & Vamsidhar, Y. Binary cross entropy with deep learning technique for Image classification. International Journal of Advanced Trends in Computer Science and Engineering, 2020, vol. 9, no. 4, pp. 5393-5397. DOI: 10.30534/ijatcse/2020/175942020.

Mao, A., Mohri, M. & Zhong, Y. Cross-Entropy Loss Functions: Theoretical Analysis and Applications. Proceedings of the 40th International Conference on Machine Learning, 2023, vol. 202, pp. 23803-23828. DOI: 10.48550/arXiv.2304.07288.

Robinson, H. & Monro, S. A Stochastic Approximation Method. The Annals of Mathematical Statistics, 1951, vol. 22, no. 3, pp. 400-407. DOI: 10.1214/aoms/1177729586.

Li, X., Wang, W., Wu, L., Chen, S., Hu, X., Li, J., Tang, J. and Yang, J. Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS '20), 2020, article no. 1763. DOI: 10.48550/arXiv.2006.04388.




DOI: https://doi.org/10.32620/aktt.2024.3.08