Metodologias de visão computacional para contagem de plantas por meio de imagens de satélite
Resumo
Nesta pesquisa são propostas duas metodologias de visão computacional para a contagem de árvores a partir de imagens de satélite. As metodologias consistem de um processamento comum à ambas dado por conversão das imagens para níveis de cinza, binarização, tratamento morfológico e aplicação da transformada da distância. Numa segunda etapa do processo comparamos segmentação por inundação (watershed) com detecção de picos por filtragem máxima local. Na terceira fase é feita a rotulação dos objetos identificados. A metodologia foi avaliada em imagens de satélite obtidas via API Google Maps de dois tipos de árvores: jabuticabeiras e coqueiros. Melhores resultados foram obtidos para filtragem máxima local, com 92.03% de precisão para a contagem de plantas de jabuticabeiras e 92.88% para coqueiros.
Palavras-chave:
Visão computacional, segmentação por inundação (watershed, árvores, conversão de imagens)
Referências
Daliakopoulos, I. N., Grillakis, E. G., Koutroulis, A. G., and Tsanis, I. K. (2009). Tree crown detection on multispectral vhr satellite imagery. Photogrammetric Engineering Remote Sensing, 75(10):1201–1211.
Disperati, A. A., dos Santos, J. R., de Oliveira Filho, P. C., and Neeff, T. (2007). Aplicação da técnica filtragem de locais máximas em fotografia aérea digital para a contagem de copas em reflorestamento de pinus elliottii. SciELO Brasil, 76:45–55.
Fabbri, R., Costa, L. D. F., Torelli, J. C., and Bruno, O. M. (2008). 2d euclidean distance transform algorithms: A comparative survey. ACM Comput. Surv., 40(1):2:1–2:44.
Franco, S., Tarantino, E., Figorito, B., Stefania, G., and D’Onghia, A. (2013). A tree counting algorithm for precision agriculture tasks. International Journal of Digital Earth, 6:94–102.
Gebreslasie, M., Ahmed, F., van Aardt, J., and Blakeway, F. (2011). Individual tree detection based on variable and fixed window size local maxima filtering applied to ikonos imagery for even-aged eucalyptus plantation forests. International Journal of Remote Sensing, 32:4141–4154.
Gonzalez, R. C. and Woods, R. E. (2006). Digital Image Processing (3rd Edition).Prentice-Hall, Inc., Upper Saddle River, NJ, USA.
González-Jiménez, J., Galindo, C., Arevalo, V., and Ambrosio, G. (2007). Applying image analysis and probabilistic techniques for counting olive trees in high-resolution satellite images. volume 4678, pages 920–931.
Katoh, M. and Gougeon, F. (2012). Improving the precision of tree counting by combi- ning tree detection with crown delineation and classification on homogeneity guided smoothed high resolution (50 cm) multispectral airborne digital data. Remote Sensing, 4(5):1411–1424.
Kestur, R., Angural, A., Bashir, B., Omkar, S. N., Anand, G., and Meenavathi, M. B. (2018). Tree crown detection, delineation and counting in uav remote sensed images: A neural network based spectral–spatial method. Journal of the Indian Society of Remote Sensing, 46(6):991–1004.
Koch, B., Heyder, U., and Weinacker, H. (2006). Detection of individual tree crowns in airborne lidar data. Photogrammetric Engineering and Remote Sensing, 72:357–363.
Li, W., Fu, H., Yu, L., and Cracknell, A. (2017). Deep learning based oil palm tree detection and counting for high-resolution remote sensing images. Remote Sensing, 9(1):1–22.
Maillard, P. and Gomes, M. (2016). Detection and counting of orchard trees from vhr ima- ges using a geometrical-optical model and marked template matching. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, III-7:75–82.
Puttemans, S., Van Beeck, K., and Goedemé, T. (2018). Comparing boosted cascades to deep learning architectures for fast and robust coconut tree detection in aerial images.
Recio, J., Hermosilla, T., Ruiz, L., and Palomar, J. (2013). Automated extraction of tree and plot-based parameters in citrus orchards from aerial images. Computers and Electronics in Agriculture, 90:24–34.
Srestasathiern, P. and Rakwatin, P. (2014a). Oil palm tree detection with high resolution multi-spectral satellite imagery. Remote Sensing, 6:9749–9774.
Srestasathiern, P. and Rakwatin, P. (2014b). Oil palm tree detection with high resolution multi-spectral satellite imagery. volume 6, pages 9749–9774.
Strimbu, V. and Strimbu, B. (2015). A graph-based segmentation algorithm for tree crown extraction using airborne lidar data. ISPRS Journal of Photogrammetry and Remote Sensing, 104:30–43.
Vibha, L., Shenoy, P. D., Venugopal, K. R., and Patnaik, L. M. (2009). Robust technique for segmentation and counting of trees from remotely sensed data. In 2009 IEEE International Advance Computing Conference, pages 1437–1442.
Wulder, M., Niemann, K., and Goodenough, D. G. (2000). Local maximum filtering for the extraction of tree locations and basal area from high spatial resolution imagery. Remote Sensing of Environment, 73(1):103 – 114.
Wulder, M., White, J., Niemann, K., and Nelson, T. (2004). Comparison of airborne and satellite high spatial resolution data for the identification of individual trees with local maxima filtering. International Journal of Remote Sensing, 25:2225–2232.
Disperati, A. A., dos Santos, J. R., de Oliveira Filho, P. C., and Neeff, T. (2007). Aplicação da técnica filtragem de locais máximas em fotografia aérea digital para a contagem de copas em reflorestamento de pinus elliottii. SciELO Brasil, 76:45–55.
Fabbri, R., Costa, L. D. F., Torelli, J. C., and Bruno, O. M. (2008). 2d euclidean distance transform algorithms: A comparative survey. ACM Comput. Surv., 40(1):2:1–2:44.
Franco, S., Tarantino, E., Figorito, B., Stefania, G., and D’Onghia, A. (2013). A tree counting algorithm for precision agriculture tasks. International Journal of Digital Earth, 6:94–102.
Gebreslasie, M., Ahmed, F., van Aardt, J., and Blakeway, F. (2011). Individual tree detection based on variable and fixed window size local maxima filtering applied to ikonos imagery for even-aged eucalyptus plantation forests. International Journal of Remote Sensing, 32:4141–4154.
Gonzalez, R. C. and Woods, R. E. (2006). Digital Image Processing (3rd Edition).Prentice-Hall, Inc., Upper Saddle River, NJ, USA.
González-Jiménez, J., Galindo, C., Arevalo, V., and Ambrosio, G. (2007). Applying image analysis and probabilistic techniques for counting olive trees in high-resolution satellite images. volume 4678, pages 920–931.
Katoh, M. and Gougeon, F. (2012). Improving the precision of tree counting by combi- ning tree detection with crown delineation and classification on homogeneity guided smoothed high resolution (50 cm) multispectral airborne digital data. Remote Sensing, 4(5):1411–1424.
Kestur, R., Angural, A., Bashir, B., Omkar, S. N., Anand, G., and Meenavathi, M. B. (2018). Tree crown detection, delineation and counting in uav remote sensed images: A neural network based spectral–spatial method. Journal of the Indian Society of Remote Sensing, 46(6):991–1004.
Koch, B., Heyder, U., and Weinacker, H. (2006). Detection of individual tree crowns in airborne lidar data. Photogrammetric Engineering and Remote Sensing, 72:357–363.
Li, W., Fu, H., Yu, L., and Cracknell, A. (2017). Deep learning based oil palm tree detection and counting for high-resolution remote sensing images. Remote Sensing, 9(1):1–22.
Maillard, P. and Gomes, M. (2016). Detection and counting of orchard trees from vhr ima- ges using a geometrical-optical model and marked template matching. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, III-7:75–82.
Puttemans, S., Van Beeck, K., and Goedemé, T. (2018). Comparing boosted cascades to deep learning architectures for fast and robust coconut tree detection in aerial images.
Recio, J., Hermosilla, T., Ruiz, L., and Palomar, J. (2013). Automated extraction of tree and plot-based parameters in citrus orchards from aerial images. Computers and Electronics in Agriculture, 90:24–34.
Srestasathiern, P. and Rakwatin, P. (2014a). Oil palm tree detection with high resolution multi-spectral satellite imagery. Remote Sensing, 6:9749–9774.
Srestasathiern, P. and Rakwatin, P. (2014b). Oil palm tree detection with high resolution multi-spectral satellite imagery. volume 6, pages 9749–9774.
Strimbu, V. and Strimbu, B. (2015). A graph-based segmentation algorithm for tree crown extraction using airborne lidar data. ISPRS Journal of Photogrammetry and Remote Sensing, 104:30–43.
Vibha, L., Shenoy, P. D., Venugopal, K. R., and Patnaik, L. M. (2009). Robust technique for segmentation and counting of trees from remotely sensed data. In 2009 IEEE International Advance Computing Conference, pages 1437–1442.
Wulder, M., Niemann, K., and Goodenough, D. G. (2000). Local maximum filtering for the extraction of tree locations and basal area from high spatial resolution imagery. Remote Sensing of Environment, 73(1):103 – 114.
Wulder, M., White, J., Niemann, K., and Nelson, T. (2004). Comparison of airborne and satellite high spatial resolution data for the identification of individual trees with local maxima filtering. International Journal of Remote Sensing, 25:2225–2232.
Publicado
22/11/2019
Como Citar
DA SILVA, Patrícia Duarte; DOS SANTOS FILHO, Tércio Alberto; DA SILVA, Sérgio Francisco .
Metodologias de visão computacional para contagem de plantas por meio de imagens de satélite. In: ESCOLA REGIONAL DE INFORMÁTICA DE GOIÁS (ERI-GO), 7. , 2019, Goiânia.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 143-154.
