Mangrove semantic segmentation on aerial images
Keywords:
Deep neural networks, Natural areas, Remote perception, Transfer learningAbstract
In the Yucatan Peninsula, there is a rich diversity of mangroves, notably including Rhizophora mangle, Avicennia germinans, and Laguncularia racemosa. These mangroves contribute to the recovery of degraded natural areas caused by human activities. Additionally, they serve as natural habitats for various animal and plant species. Studies have highlighted the significance of preserving and restoring these species through traditional methods. More recently, the integration of remote sensing and deep learning techniques has allowed for the automated detection and quantification of mangroves. In this study, we explore the application of deep neural network techniques to address computer vision challenges in the field of remote sensing. Specifically, we focus on the detection and quantification of mangroves in remote image sensing, employing transfer learning and fine-tuning with three distinct deep neural network architectures: SegNet-VGG16, U-Net, and Fully Convolutional Network (R-FCN), with the latter two based on the ResNet network. To evaluate the performance of each architecture, we applied key evaluation metrics, including Intersection over Union (IoU), Dice Coefficient, Precision, Sensitivity, and Accuracy. Our results indicate that SegNet-
VGG16 exhibited the highest levels of Precision (98.03%) and Accuracy (97.03%), while U-Net outperformed in terms of IoU
(96.97%), Dice Coefficient (92.20%), and Sensitivity (96.81%).
Downloads
References
A. Zald´ıvar-Jim´enez, J. A. Herrera-Silveira, R. P´erez-Ceballos, and C. Teutli-Hern´andez, “Evaluaci´on del uso de los humedales de manglar como biofiltro de efluentes de camaroneras en Yucat´an, M´exico,” Revista De Biologia Marina Y Oceanografia, vol. 47, pp. 395–405, 12 2012. doi: 10.4067/s0718-19572012000300003.
M. T. R. Z´u˜niga, J. A. Vel´azquez, C. Galindo-Leal, S. Cerdeira-Estrada, M. I. C. L´opez, J. D. Gallegos, R. J. Rosenberg, J. D. M. Mendoza, R. Ressl, C. T. Souza, A. U. Mart´ınez, L. Valderrama-Landeros, B. V. Balderas, A. D. V. Lule, and S. V. Salazar, Manglares de M´exico : Extensi´on, distribuci´on y monitoreo. 1 2013. doi: 10.5962/bhl.title.111178.
J. L. Portillo and E. Ezcurra, “Los manglares de M´exico: una revisi´on,” Madera Y Bosques, vol. 8, pp. 27–51, 9 2016. doi: 10.21829/myb.2002.801290.
S. Cinco-Castro and J. A. Herrera-Silveira, “Vulnerability of mangrove ecosystems to climate change effects: The case of the Yucatan Peninsula,” Ocean Coastal Management, vol. 192, p. 105196, 7 2020. doi: 10.1016/j.ocecoaman.2020.105196.
M. A. Zald´ıvar-Jim´enez, J. A. Herrera-Silveira, C. Teutli-Hern´andez, F. A. Comın, J. L. Andrade, C. C. Molina, and R. P´erez-Ceballos, “Conceptual framework for mangrove restoration in the Yucatan Peninsula,” Ecological restoration, North America, vol. 28, pp. 333–342, 8 2010. doi:10.3368/er.28.3.333.
M. Mohan, G. Richardson, G. Gopan, M. M. Aghai, S. Bajaj, G. P. Galgamuwa, M. Vastaranta, P. S. P. Arachchige, L. Amor´os, A. P. D. Cˆorte, S. De-Miguel, R. V. Leite, M. Kganyago, E. N. Broadbent, W. Doaemo, M. A. B. Shorab, and A. Card´ıl, “UAV-Supported Forest regeneration: Current trends, challenges and implications,” Remote Sensing, vol. 13, p. 2596, 7 2021. doi: 10.3390/rs13132596.
A. S. Ayub, A. Anggoro, A. H. Lukman, A. Ariasari, A. N. N. Suci, N. T. Agustini, F. Nugroho, A. M. Muslih, C. C. Hanami, and R. Zulhendri, “Mapping The Potential of Mangrove Planting in The Rehabilitation of Coastal Ecosystems Using Drone Technology,” Journal of Sylva Indonesiana, vol. 6, pp. 164–177, 8 2023. doi: 10.32734/jsi.v6i02.10515.
D. Yin and L. Wang, “Individual mangrove tree measurement using UAV-based LIDAR data: Possibilities and challenges,” Remote Sensing of Environment, vol. 223, pp. 34–49, 3 2019. doi:10.1016/j.rse.2018.12.034.
A. C. C. Viodor, C. J. G. Aliac, and L. T. Santos-Feliscuzo, “Mangrove species identification using deep neural network,” in 2022 6th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), pp. 1–6, 2022. doi: 10.1109/ICITISEE57756.2022.10057793.
L. Ma, Y. Liu, X. Zhang, Y. Ye, G. Yin, and B. A. Johnson, “Deep learning in remote sensing applications: A meta-analysis and review,” Isprs Journal of Photogrammetry and Remote Sensing, vol. 152, pp. 166–177, 6 2019. doi: 10.1016/j.isprsjprs. 2019.04.015.
Y. Yu, C. Wang, Q. Fu, R. Kou, F. Huang, B. Yang, T. Yang, and M. Gao, “Techniques and Challenges of Image Segmentation:
A review,” Electronics, vol. 12, p. 1199, 3 2023. doi: 10.3390/electronics12051199.
U. Sehar and M. L. Naseem, “How deep learning is empowering semantic segmentation,” Multimedia Tools and Applications,
vol. 81, pp. 30519–30544, 4 2022. doi: 10.1007/s11042-022-12821-3.
Y. Guo, H. Shi, A. Kumar, K. Grauman, T. Rosing, and R. Feris, “SpotTune: Transfer Learning Through Adaptive Fine-Tuning,” In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 6 2019. doi: 10.1109/cvpr.2019.00494.
S. Malek, Y. Bazi, N. Alajlan, H. Alhichri, and F. Melgani, “Efficient framework for palm tree detection in UAV images,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 7, pp. 4692–4703, 12 2014. doi: 10.1109/jstars.2014.2331425.
N. A. B`ınh, L. T. Hauser, P. V. Hoa, G. T. P. Thao, N. N. An, H. S. Nhut, T. A. Phuong, and J. Verrelst, “Quantifying mangrove leaf area index from Sentinel-2 imagery using hybrid models and active learning,” International Journal of Remote Sensing, vol. 43, pp. 5636–5657, 3 2022. doi: 10.1080/01431161.2021.2024912.
S. G. Sodjinou, V. Mohammadi, A. T. S. Mahama, and P. Gouton, “A deep semantic segmentation-based algorithm to segment crops and weeds in agronomic color images,” Information Processing in Agriculture, vol. 9, pp. 355–364, 9 2022. doi: 10.1016/j.inpa.2021.08.003.
S. Kolhar and J. Jagtap, “Convolutional neural network based encoder-decoder architectures for semantic segmentation of plants,” Ecological Informatics, vol. 64, p. 101373, 9 2021. doi:10.1016/j.ecoinf.2021.101373.
W. Li, C. He, J. Fang, J. Zheng, H. Fu, and L. Yu, “Semantic Segmentation-Based building footprint extraction using very High-Resolution satellite images and Multi-Source GIS data,” Remote Sensing, vol. 11, p. 403, 2 2019. doi: 10.3390/rs11040403.
E. Shelhamer, J. Long, and T. Darrell, “Fully convolutional networks for semantic segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, pp. 640–651, 4 2017. doi: 10.1109/tpami.2016.2572683.
R. Saleem, J. H. Shah, M. Sharif, and G. J. Ansari, “Mango leaf disease identification using fully resolution convolutional network,” Computers, materials continua, vol. 69, pp. 3581–3601, 1 2021. doi: 10.32604/cmc.2021.017700.
J. Fuentes-Pacheco, J. Torres-Olivares, E. Rom´an-Rangel, S. Cervantes, P. Ju´arez-L´opez, J. H. Valadez, and J. M. Rend´on-Mancha, “Fig Plant Segmentation from Aerial Images Using a Deep Convolutional Encoder-Decoder Network,” Remote Sensing, vol. 11, p. 1157, 5 2019. doi: 10.3390/rs11101157.
T. Anand, S. Sinha, M. Mandal, V. Chamola, and F. R. Yu, “AGRISEGNET: Deep Aerial Semantic Segmentation Framework for IoT-Assisted Precision Agriculture,” IEEE Sensors Journal, vol. 21, pp. 17581–17590, 8 2021. doi: 10.1109/jsen.2021.3071290.
T. Masuda, “Leaf Area Estimation by Semantic Segmentation of Point Cloud of Tomato Plants,” Proceedings of the IEEE/CVF International Conference on Computer Vision, 10 2021. doi: 10.1109/iccvw54120.2021.00159.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” In Proceedings of the IEEE conference on computer vision and pattern recognition, 6 2016. doi: 10.1109/cvpr.2016.90.
J. A. Herrera-Silveira, “Overview and characterization of the hydrology and primary producer communities of selected coastal lagoons of Yucat´an, M´exico,” Aquatic Ecosystem Health Management, vol. 1, pp. 353–372, 12 1998. doi: 10.1016/s1463-4988(98)00014-1.
A. M. Gill and P. B. Tomlinson, “Studies on the growth of red mangrove (Rhizophora mangle l.) 3. Phenology of the shoot,” Biotropica, vol. 3, p. 109, 12 1971. doi: 10.2307/2989815.
V. Badrinarayanan and R. Cipolla, “SEGNet: a deep convolutional Encoder-Decoder architecture for image segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, pp. 2481–2495, 12 2017. doi: 10.1109/tpami.2016.2644615.
O. Ronneberger, P. Fischer, and T. Brox, “U-NET: Convolutional Networks for Biomedical Image Segmentation,” arXiv (Cornell University), 5 2015. doi: 10.48550/arxiv.1505.04597.
G. J. Brostow, J. Shotton, J. Fauqueur, and R. Cipolla, Segmentation and recognition using structure from motion point clouds. 1 2008. doi: 10.1007/978-3-540-88682-2{_5.
A. Abdalla, H. Cen, L. Wan, R. B. Rashid, H. Weng, W. Zhou, and Y. He, “Fine-tuning convolutional neural network with transfer learning for semantic segmentation of ground-level oilseed rape images in a field with high weed pressure,” Computers and Electronics in Agriculture, vol. 167, p. 105091, 12 2019. doi:10.1016/j.compag.2019.105091.
V. T. Thi, A. Xuan, H. Nguyen, F. Dahdouh-Guebas, and N. Koedam, “Application of remote sensing and GIS for detection of long-term mangrove shoreline changes in Mui Ca Mau, Vietnam,” Biogeosciences, vol. 11, pp. 3781–3795, 7 2014. doi: 10.5194/bg-11-3781-2014.
D. M. Belete and M. D. Huchaiah, “Grid search in hyperparameter optimization of machine learning models for prediction of HIV/AIDS test results,” International Journal of Computers and Applications, vol. 44, pp. 875–886, 9 2021. doi:10.1080/1206212x.2021.1974663.
Y. S. Yi, Z. Zhang, W. Zhang, C. Zhang, W. Li, and T. Zhao, “Semantic Segmentation of Urban Buildings from VHR Remote Sensing Imagery Using a Deep Convolutional Neural Network,” Remote Sensing, vol. 11, p. 1774, 7 2019. doi: 10.3390/rs11151774.
![](https://latamt.ieeer9.org/public/journals/1/submission_8557_12116_coverImage_en_US.png)