Detección de cambio en superficie costera mediante la segmentación de imágenes aéreas utilizando redes neuronales convolucionales
Resumen
La conservación de ecosistemas en zonas costeras debe contemplarse dentro de un marco sustentable con las actividades antropogénicas. Es relevante cuantificar el impacto que generan agentes externos, por lo que el objetivo de este trabajo es implementar un método para el monitoreo de la degradación en superficie de playa y vegetación litoral adyacente. Fueron recabadas capturas de imágenes aéreas de zonas costeras protegidas, obtenidas periódicamente mediante un vehículo drone. Se integró un dataset que contempla todas las fases estacionales y distingue 5 clases para su monitoreo: Mangle, vegetación rastrera, arena, mar y cerro-planicie. Para la segmentación semántica se implementaron y compararon distintas arquitecturas de redes neuronales convolucionales (CNN) empleando aprendizaje transferido. Los resultados han sido robustos en la clasificación, alcanzando una precisión global del 93.9% y entre 89.9-95.8% en las clases individuales. En la métrica Intersección sobre Unión, IoU, el rango fue entre 86.6-92.7%. En la detección de cambio son utilizadas series temporales para el monitoreo de clases. Este método ha sido aplicado al caso de estudio de la playa Ensenada Grande en el Parque Nacional Archipiélago Espíritu Santo.
Descargas
Citas
A.Géron. (2019). Hands-on machine learning with Scikit-Learn, Keras and TensorFlow: concepts, tools, and techniques to build intelligent systems. O’Reilly Media, pp. 450-478. https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/
Aggarwal, C. C. (2018). Neural Networks and Deep Learning. Neural Networks and Deep Learning. https://doi.org/10.1007/978-3-319-94463-0
Bayr, U., & Puschmann, O. (2019). Automatic detection of woody vegetation in repeat landscape photographs using a convolutional neural network. Ecological Informatics, 50, 220–233. https://doi.org/10.1016/j.ecoinf.2019.01.012
Casella, E., Rovere, A., Pedroncini, A., Stark, C. P., Casella, M., Ferrari, M., & Firpo, M. (2016). Drones as tools for monitoring beach topography changes in the Ligurian Sea (NW Mediterranean). Geo-Marine Letters, 36(2), 151–163. https://doi.org/10.1007/S00367-016-0435-9
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. https://github.com/tensorflow/models/tree/master/
Computer Vision Toolbox - MATLAB & Simulink. (2020.). Retrieved May 9, 2022, from https://la.mathworks.com/products/computer-vision.html
Ellenson, A. N., Simmons, J. A., Wilson, G. W., Hesser, T. J., & Splinter, K. D. (2020). Beach State Recognition Using Argus Imagery and Convolutional Neural Networks. Remote Sensing 2020, Vol. 12, Page 3953, 12(23), 3953. https://doi.org/10.3390/RS12233953
Gonzalo-Martin, C., Garcia-Pedrero, A., Lillo-Saavedra, M., & Menasalvas, E. (2016). Deep learning for superpixel-based classification of remote sensing images. https://doi.org/10.3990/2.401
Google, C. (2014). Xception: Deep Learning with Depthwise Separable Convolutions. Computer Vision and Pattern Recognition, 1251–1258.
Guo, R., Liu, J., Li, N., Liu, S., Chen, F., Cheng, B., Duan, J., Li, X., & Ma, C. (2018). Pixel-Wise Classification Method for High Resolution Remote Sensing Imagery Using Deep Neural Networks. ISPRS International Journal of Geo-Information 2018, Vol. 7, Page 110, 7(3), 110. https://doi.org/10.3390/IJGI7030110
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition. http://image-net.org/challenges/LSVRC/2015/
Jenčo, M., Fulajtár, E., Bobál’ová, H., Matečný, I., Saksa, M., Kožuch, M., Gallay, M., Kaňuk, J., Píš, V., & Oršulová, V. (2020). Mapping soil degradation on arable land with aerial photography and erosion models, case study from Danube Lowland, Slovakia. Remote Sensing, 12(24), 1–17. https://doi.org/10.3390/RS12244047
Pandey, P. C., Rani, M., Srivastava, P. K., Sharma, L. K., & Singh Nathawat, M. (2013). Land degradation severity assessment with sand encroachment in an ecologically fragile arid environment: a geospatial perspective. https://doi.org/10.5339/connect.2013.43
Rubio, V. G., Antonio, J., Ferrán, R., Manuel Menéndez García, J., Sánchez Almodóvar, N., María, J., Mayordomo, L., & Álvarez, F. (2019). Automatic Change Detection System over Unmanned Aerial Vehicle Video Sequences Based on Convolutional Neural Networks. https://doi.org/10.3390/s19204484
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks.
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2016). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning.
The Mathworks, Inc. (2020). MATLAB (No. R2020b). la.mathworks.com/.
Valentini, N., & Balouin, Y. (2020). Assessment of a Smartphone-Based Camera System for Coastal Image Segmentation and Sargassum monitoring. Journal of Marine Science and Engineering 2020, Vol. 8, Page 23, 8(1), 23. https://doi.org/10.3390/JMSE8010023
Wagner, F. H., Sanchez, A., Tarabalka, Y., Lotte, R. G., Ferreira, M. P., Aidar, M. P. M., Gloor, E., Phillips, O. L., & Aragão, L. E. O. C. (2019). Using the U‐net convolutional network to map forest types and disturbance in the Atlantic rainforest with very high resolution images. Remote Sensing in Ecology and Conservation, 5(4), 360–375. https://doi.org/10.1002/rse2.111
Yoo, C. I., & Oh, T. S. (2016). Beach volume change using UAV photogrammetry Songjung beach, Korea. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, 41, 1201–1205. https://doi.org/10.5194/ISPRSARCHIVES-XLI-B8-1201-2016
Younis, M. C., & Keedwell, E. (2019). Semantic segmentation on small datasets of satellite images using convolutional neural networks. Journal of Applied Remote Sensing,