Deep Learning-Based Semantic Segmentation Models for Crane Detection in Post-Earthquake UAV Imagery
Downloads
The rapid identification of heavy machinery in post-disaster environments can significantly support recovery and reconstruction operations. This study presents a comparative evaluation of deep learning based semantic segmentation models for crane segmentation in UAV imagery acquired after the February 6, 2023 earthquakes in Kahramanmaraş, Türkiye. Five semantic segmentation architectures, namely SegFormer, DeepLabV3+, SegNet, FCN and U-Net, were trained and evaluated under identical experimental conditions. The results showed that DeepLabV3+ achieved the best overall quantitative performance with an IoU of 66.1%, mIoU of 81.0%, and Dice score of 78.9%. The findings demonstrate that modern segmentation architectures provide effective solutions for crane segmentation in complex post-earthquake UAV imagery and have significant potential for supporting disaster recovery and situational awareness applications.
Giordan, D., Adams, M. S., Aicardi, I., Alicandro, M., Allasia, P., Baldo, M., ... & Troilo, F. (2020). The use of unmanned aerial vehicles (UAVs) for engineering geology applications. Bulletin of Engineering Geology and the Environment, 79, 3437-3481.
Tang, G., Ni, J., Zhao, Y., Gu, Y., & Cao, W. (2023). A survey of object detection for UAVs based on deep learning. Remote Sensing, 16(1), 149.
Wang, L., Wu, J., Yang, Y., Tang, R., & Ya, R. (2024). Deep learning models for hazard-damaged building detection using remote sensing datasets: A comprehensive review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 15301-15318.
Ivanov, M. L., & Georgiev, M. P. (2025). Innovations, applications, and future perspectives in geospatial information visualization for disaster response: insights from the 2023 Kahramanmaras Earthquake urban search and rescue operations. Natural Hazards, 121(19), 22787-22816.
Calantropio, A., Chiabrando, F., Codastefano, M., & Bourke, E. (2021). Deep learning for automatic building damage assessment: application in post-disaster scenarios using UAV data. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 1, 113-120.
Takhtkeshha, N., Mohammadzadeh, A., & Salehi, B. (2022). A rapid self-supervised deep-learning-based method for post-earthquake damage detection using UAV data (case study: Sarpol-e Zahab, Iran). Remote Sensing, 15(1), 123.
Jozi, S. D. (2024). UAV-based Post-disaster Damage Assessment of Buildings Using Image Processing.
Albeaino, G., Gheisari, M., & Franz, B. W. (2019). A systematic review of unmanned aerial vehicle application areas and technologies in the AEC domain. Journal of information technology in construction, 24.
He, L., Zhou, Y., Liu, L., & Ma, J. (2024). Research and application of YOLOv11-based object segmentation in intelligent recognition at construction sites. Buildings, 14(12), 3777.
Gu, J., Xie, Z., Zhang, J., & He, X. (2024). Advances in rapid damage identification methods for post-disaster regional buildings based on remote sensing images: A survey. Buildings, 14(4), 898.
Al Shafian, S., & Hu, D. (2024). Integrating machine learning and remote sensing in disaster management: A decadal review of post-disaster building damage assessment. Buildings, 14(8), 2344.
Xiao, Y., Yang, T. Y., Pan, X., Xie, F., & Chen, Z. (2023). A reinforcement learning based construction material supply strategy using robotic crane and computer vision for building reconstruction after an earthquake. arXiv preprint arXiv:2308.16280.
Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021). SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems, 34, 12077-12090.
Chen, L. C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV) (pp. 801-818).
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence, 39(12), 2481-2495.
Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3431-3440)
Ronneberger, O., Fischer, P., & Brox, T. (2015, October). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention (pp. 234-241). Cham: Springer international publishing.
