Abstract
Espeletia is one of the most representative endemic species of moorland ecosystems, and is currently being affected by biotic stress. Meanwhile, the analysis of images obtained by means of unmanned aerial vehicle imagery has proved its usefulness in environmental monitoring activities. The present work is aimed at establishing whether image-texture analysis applied to unmanned aerial vehicle imagery from Moorlands of Chingaza (Colombia) allows the identification of biotic stress in Espeletia. To this end, this study makes use of occurrence analysis, gray-level co-occurrence matrix, and Fourier transform. Identification of healthy/unhealthy Espeletia is conducted using maximum likelihood tests and support vector machines. The results are assessed based on overall accuracy, the kappa coefficient and bhattacharyya distance. By combining spectral and image-texture information, it is shown that classification accuracy increases, reaching kappa coefficient values of 0,9824 and overall accuracy values of 99,51%.
Publisher
Universidad Militar Nueva Granada
Reference33 articles.
1. FAO, ¿por qué invertir en el desarrollo sostenible de las montañas?, Roma, 2014.
2. O. V. Ríos and P. Pedraza, El Parque Nacional Natural Chingaza. UNal de Colombia, 2004.
3. A. Sanchez, A. Rey-Sánchez, J.M. Posada, W. K. Smith. Interplay of seasonal sunlight, air and leaf temperature in two alpine páramo species, Colombian Andes. Agricultural and Forest Meteorology, 253–254, (2018), 38–47. https://doi.org/10.1016/j.agrformet.2018.01.033.
4. M. Cabrera and W. Ramírez, Restauración Ecológica de los páramos de Colombia: Transformación y herramientas para su conservación. Min Ambiente, Instituto von Humboldt, 2014.
5. N. Susiˇc, U. Zibrat, S. Sirca, P. Strajnar, J Razinger, M. Knapiˇc, A. Vonˇcina, G. Urek, BG. Stare, Discrimination between abiotic and biotic drought stress in tomatoes using hyperspectral imaging, Sensors and Actuators: B. Chemical (2018), https://doi.org/10.1016/j.snb.2018.06.121
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献