A NEURAL NETWORK APPROACH TO SEMANTIC SEGMENTATION OF VEHICLES IN VERY HIGH RESOLUTION IMAGES
DOI:
https://doi.org/10.15588/1607-3274-2025-3-8Keywords:
semantic segmentation, vehicles, deep neural networks, ResNet-101, DeepLab, multi-scale analysis, very high resolution imagesAbstract
Context. The semantic segmentation of vehicles in very high resolution aerial images is essential in developing intelligent transportation systems. It allows for the automation of real-time traffic management and the detection of congestion and emergencies.
Objective. This work aims to develop and evaluate the effectiveness of a neural network approach to semantic segmentation in very high resolution aerial images, which provides high detail and correct reproduction of object boundaries.
Method. The DeepLab architecture with ResNet-101 as a backbone is used for gradient preservation and multiscale feature analysis. We trained on DOTA data and retrained on specialized sets with classes: vehicles, green areas, buildings, and roads. A loss function based on the Dice coefficient was applied to reduce the imbalance of classes. It effectively solves the class imbalance problem and improves the accuracy of segmenting objects of different sizes. Using ResNet-101 instead of Xception in the backbone network allows us to maintain the gradient as the network depth increases.
Results. Experimental studies have confirmed the effectiveness of the proposed approach, which achieves a segmentation accuracy of more than 90%, outperforming existing analogs. The use of multiscale feature analysis allows for preserving the texture features of objects, reducing false classifications. A comparative study with U-Net, SegNet, FCN8s, and other methods confirms the higher performance of the proposed approach in terms of mIoU (82.3%) and Pixel Accuracy (95.1%).
Conclusions. The experiments confirm the effectiveness of the proposed method of semantic segmentation of vehicles in ultrahigh spatial resolution images. Using DeepLab v3+ResNet-101 significantly improves the quality of vehicle segmentation in an urbanized environment. Excellent metric performance makes it promising for infrastructure monitoring and traffic planning tasks. Further research will focus on adapting the model to new datasets
References
Yongtao Yu., Tiannan Gu., Haiyan G., Dilong Li, Shenghua J. Vehicle detection from high resolution remote sensing imagery using convolutional capsule networks, IEEE Geosci. Remote Sens. Lett., 2019, Vol. 16, No. 12, pp. 1894– 1898. DOI:10.1109/LGRS.2019.2912582.
Byun S., Shin I.-K., Moon J., Kang J., Choi S.-I. Road traffic monitoring from UAV images using deep learning networks, Remote Sens, 2021, No. 13, P. 4027. DOI: 10.3390/rs13204027.
Khrissi L., El Akkad N., Satori H., Satori K. Clustering method and sine cosine algorithm for image segmentation, Evol. Intell., 2022, No. 15, pp. 669–682. DOI:10.1007/s12065-020-00544-z.
Osco L., Junior J., Ramos A., de Castro Jorge L., Fatholahi S., de Andrade Silva J., Matsubara E., Pistori H., Gonçalves W., Li J. A review on deep learning in UAV remote sensing, International Journal of Applied Earth Observation and Geoinformation, 2021. DOI:102:102456.
Kemker R., Salvaggio C., Kanan C. Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learning, ISPRS Journal of Photogrammetry and Remote Sensing, 2018, Vol. 145. DOI:10.1016/j.isprsjprs.2018.04.014.
Hong D., Danfeng H., Gao L., Yokoya N., Jing Y., Chanussot J., Du Q., Zhang B. More diverse means better: multimodal deep learning meets remote-sensing imagery classification, IEEE Transactions on Geoscience and Remote Sensing, 2020, Vol. 59 (5), pp. 4340–4354.
DOI: 10.1109/TGRS.2020.3016820.
Binge C., Chen X., Lu Y. Semantic segmentation of remote sensing images using transfer learning and deep convolutional neural network with dense connection, IEEE Access2020, No. 8, pp. 116744–116755. DOI:10.1109/Access.6287639.
Singh C., Mishra V., Jain K., Shukla A. FRCNN-based reinforcement learning for real-time vehicle detection, tracking and geolocation from UAS, Drones, 2022, No. 6, P. 406. DOI: 10.3390/drones6120406.
Saqib M., Khan S., Sharma N., Blumenstein M. A study on detecting drones using deep convolutional neural networks, In Proceedings of the 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2017, pp. 1–5. DOI: 10.1109/AVSS.2017.8078541.
Kong X., Zhang Y., Tu S., Xu C., Yang W. Vehicle detection in high-resolution aerial images with parallel RPN and density-assigner, Remote Sens, 2023, No. 15, P. 1659. DOI: 10.3390/rs15061659.
Hordiiuk D., Oliinyk I., Hnatushenko V., Maksymov K. Semantic segmentation for ships detection from satellite imagery, 2019 IEEE 39th International Conference on Electronics and Nanotechnology (ELNANO), 2019. DOI:10.1109/elnano.2019.8783822.
Borovyk D., Fedoniuk R., Oliinyk A., Subbotin S., Kolpakova T. Detection of vehicles in aerial photographs using convolutional neural network, Smartindustry, 2024. https://ceur-ws.org/Vol-3699/paper12.pdf
Bochkovskiy A., Wang C., Liao H. YOLOv4: optimal speed and accuracy of object detection, arXiv 2020, arXiv:2004.10934, 2020. DOI: 10.48550/ARXIV.2004.10934.
Radionov Y., Kashtan V., Hnatushenko V., Kazymyrenko O. Aircraft detection with deep neural networks and contour-based methods, Radio Electronics, Computer Science, Control, 2024, №4(71), pp. 121–129. DOI:10.15588/1607- 3274-2024-4-12.
Zhang Y., Guo Z., Wu J., Tian Y., Tang H., Guo X. Realtime vehicle detection based on improved YOLO v5, Sustainability, 2022, No. 14(19), P. 12274. DOI:10.3390/su141912274.
DOTA [Electronic resource]. Access mode: https://captainwhu.github.io/DOTA/index.html
Kashtan V., Hnatushenko V., Shedlovska Y. Processing technology of multispectral remote sensing images, 2017 IEEE International Young Scientists Forum on Applied
Physics and Engineering (YSF), 2017. DOI:10.1109/ysf.2017.8126647.
He K., Zhang X., Ren S., Sun J. Deep residual learning for image recognition, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit, 2016, pp. 770–778. DOI: 10.48550/arXiv.1512.03385.
Chengzhi Y., Hongjun G. A Method of Image Semantic Segmentation Based on PSPNet, Mathematical Problems in Engineering, 2022, pp. 1–9. DOI:10.1155/2022/8958154.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 V. Yu. Kashtan, V. V. Hnatushenko , I. M. Udovyk, O. V. Kazymyrenko , Y. D. Radionov
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Creative Commons Licensing Notifications in the Copyright Notices
The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.
The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.
The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.
Authors who publish with this journal agree to the following terms:
-
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
-
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
-
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
