Crop Cover Fraction Estimation Based On Digital Images from 2014-2016: A Case Study of Kadirli in Osmaniye Province

Abstract

Crop cover fraction is commonly used to define ecosystem change and vegetation quality. In 2014, 2015 and 2016, color images were taken in approximately 90 sample fields at intervals of one to two weeks. Images were gathered in April, May, June and July. These 4 months means the growth period from planting until the harvesting. In this way, plant phenology was studied closely. Two approaches were used to estimate crop cover fraction in two crop types in this study. In first method, the images were transformed from the RGB color space to the HSI color space. Object-based classification was used to separate the images as the green vegetation and the non-green part. In the second method, The Green Crop Tracker software is used. The Green Crop Tracker is an applicable alternative to ground-based methods. In this approach, both the loss of time and the loss of labor is less than object-based classification. Results from the green Crop Tracker software and object based classification were compared during the growing seasons in 2014, 2015 and 2016 high correlation was obtained between these two methods (for 2014 R²=0.89, for 2015 R²=0.87, for 2016 R²=0.90).   

Keywords

• Crop Cover Fraction
• RGB to HSI
• Digital Camera
• Object-Based Classification

2014-2016 Dijital Görüntülerinden Bitki Örtü Kesitinin Tahmini: Osmaniye İli Kadirli Örneği

Öz

Bitki örtü kesiti, genellikle ekosistem değişikliği ve bitki örtüsü kalitesini tanımlamak için kullanılır. 2014, 2015 ve 2016 yıllarında bir ila iki hafta aralıklarla sahada yaklaşık 90 renkli görüntü alınmıştır. Görüntüler Nisan, Mayıs, Haziran ve Temmuz aylarında elde edilmiştir. Bu 4 ay, ekimden hasada kadar olan büyüme dönemini içermektedir. Bu şekilde bitki fenolojisi yakından incelenmiştir. Bu çalışmada iki ürün türünde bitki örtü kesitini tahmin etmek için iki yaklaşım kullanılmıştır. İlk yöntemde, görüntüler RGB renk uzayından HSI renk uzayına dönüştürülmüştür. Nesne tabanlı sınıflandırma, görüntüleri yeşil bitki örtüsü ve yeşil olmayan kısım olarak ayırmak için kullanılmıştır. İkinci yöntemde Green Crop Tracker yazılımı kullanılmıştır. Green Crop Tracker, arazi tabanlı yöntemlere uygulanabilir bir alternatiftir. Bu yaklaşımda hem zaman kaybı hem de iş gücü kaybı, nesne tabanlı sınıflandırmaya göre daha azdır. Green Crop Tracker yazılımından ve nesne tabanlı sınıflandırmadan elde edilen sonuçlar, 2014, 2015 ve 2016 yıllarındaki büyüme sezonlarında karşılaştırılmış, bu iki yöntem arasında yüksek korelasyon elde edilmiştir (2014 için R² = 0.89, 2015 için R² = 0.87, 2016 için R² = 0.90). 

Anahtar Kelimeler

• Bitki örtüsü kesiti
• RGB’den HSI’ya
• Sayısal kemera
• Nesne tabalı sınıflandırma

References

1. Definiens, ecognition Developer. (2016).User Guide.
2. Ewing, R. P. & Horton, R. (1999). Quantitative color image analysis of agronomic images, Agronomy Journal, 91 (1), 148-153.
3. Fiala, A.C.S., Garman, S.L., Gray, A.N. (2006). Comparison of five canopy cover estimation techniques in the western Oregon Cascades. Forest Ecology and Management, 232, 188–197.
4. Gitelson, A. A., Kaufman, Y. J., Stark, R. & Rundquist, D. (2002). Novel algorithms for remote estimation of vegetation fraction, Remote Sensing of Environment, 80 (1), 76-87.
5. Godinez-Alvarez, H., Herrick, J. E., Mattocks, M., Toledo, D. ve Van Zee, J. (2009). Comparison of three vegetation monitoring methods: Their relative utility for ecological assessment and monitoring, Ecological Indicators, 9 (5), 1001-1008.
6. Gutman, G., Ignalov, A. (1998). The derivation of the green vegetation fraction from NOAA/AVHRR data for use in numerical weather prediction models. Int. J. Remote Sens. 19 (8), 1533–1543.
7. Hemming, J. & Rath, T. (2001). Computer-vision-based weed identification under field conditions using controlled lighting, Journal of Agricultural Engineering Research, 78, 233-243.
8. Hirano, Y., Yasuoka, Y., Ichinose, T. (2004). Urban climate simulation by incorporating satellite—derived vegetation cover distribution into a mesoscale meteorological model. Theor. Appl. Climatol. 2004, 175–184.

9. Jensen, J.R. (2005). Introductory Digital Image Processing: a Remote Sensing Perspective (third ed), Prentice Hall, Upper Saddle River, NJ, pp. 164–167.
10. Jiang, Z., Huete, A.R., Chen, J., Chen, Y., Li, J., Yan, G., Zhang, X. (2006). Analysis of NDVI and scaled difference vegetation index retrievals of vegetation fraction, Remote Sens. Environ., 101, 366-378.
11. Jiapaer, G., Chen, X., Bao A. (2011). A comparison of methods for estimating fractional vegetation cover in arid regions, Agricultural and Forest Meteorology, 151(12), 1698-1710.
12. Karakus, P., Karabork, H., Kaya, S., (2017), A Comparison Of The Classification Accuracies In Determining The Land Cover Of Kadirli Region Of Turkey By Using The Pixel Based And Object Based Classification Algorithms, International Journal of Engineering and Geosciences, 2(2), 52-60.
13. Karcher, D.E., & M.D. Richardson. (2003). Quantifying turfgrass color using digital image analysis. Crop Science, 43(3), 943–951.
14. Laliberte, A.S., Rango, A., Herrick, J.E., Fredrickson, E.L., Burkett, L. (2007). An object-based image analysis approach for determining fractional cover of senescent and green vegetation with digital plot photography. Journal of Arid Environment, 69, 1–14.
15. Lee, K.-J, Lee, B.-W. (2011). Estimating canopy cover from color digital camera image of rice field, J. Crop Sci. Biotechnol.,14, 151–155.
16. Liu, J. G. & Pattey, E. (2010). Retrieval of Leaf Area Index from Top-Of-Canopy Digital Photography over Agricultural Crops, Agricultural and Forest Meteorology, 150, 1485-1490.
17. Liu, J., Pattey, E., & Admiral, S. (2013). Assessment of in situ crop LAI measurement using unidirectional view digital photography. Agricultural and Forest Meteorology, 169, 25-34.
18. Meyer, G. E., Hindman, T. W., Laksmi, K. (1999). Machine Vision Detection Parameters for Plant Species Identification, SPIE, Boston, MA, USA, 327-335.
19. Moons, T. (1997). 3D Reconstruction and Modelling of Topographic Objects. ISPRS Workshop, Stuttgart, Germany.
20. Mu, X., Hu, M., Song, W., Ruan, G., Ge, Y., Wang, J.,Huang, S. & Yan G.(2015) Evaluation of Sampling Methods for Validation of Remotely Sensed Fractional Vegetation Cover, Remote Sensing, 7, 16164–16182.
21. Pan, G., Li, F., Sun, G. (2007). Digital camera based measurement of crop cover for wheat yield prediction. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Barcelona, Spain, 797–800.
22. Perez, A.J., Lopez, F., Benlloch, J.V., Christensen, S. (2000). Colour and shape analysis techniques for weed detection in cereal fields, Computers and Electronics in Agriculture, 25 (3), 197-212.
23. Purevdorj, T., Tateishi, R., Ishiyama, T. & Honda, Y. (1998). Relationships between percent vegetation cover and vegetation indices. International Journal of Remote Sensing, 19 (18), 3519-3535.
24. Ryherd, S, Woodcock C. (1996).Combining spectral and texture data in the segmentation of remotely sensed images. Photogrammetric Engineering and Remote Sensing, 62, 181-194.
25. Sakamoto, T., Gitelson, A.A., Nguy-Robertson, A.L., Arkebauer, T.J., Wardlow, B.D., Suyker, A.E., Verma, S.B., Shibayama, M. (2012). An alternative method using digital cameras for continuous monitoring of crop status. Agric. For. Meteorol. 154–155, 113–126.
26. Smith, J. (1987a). Close range photogrammetry for analyzing distressed trees. Photogrammetria, 42(1), 47-56.
27. Smith, J. (1987b). Economic printing of color orthophotos. Report KRL-01234. Kennedy Research Laboratories. Arlington, VA, USA.
28. Smith, J. (1989). Space Data from Earth Sciences. (pp. 321-332). Amsterdam: Elsevier.
29. Smith, J. (2000). Remote sensing to predict volcano outbursts. The International Archives of the Photogrammetry. Remote Sensing and Spatial Information Sciences. Kyoto, Japan, Vol. XXVII, 456-469.
30. Song W., Mu X., Ruan G., Gao Z., Li L., Yan G., (2017), Estimating fractional vegetation cover and the vegetation index of bare soil and highly dense vegetation with a physically based method, International Journal of Applied Earth Observation and Geoinformation, Volume 58, June 2017, 168-176.
31. URL-1: https://www.sony.com.tr/electronics/support/compact-cameras-dsc-s-series/dsc-s930 [access date: 18.01.2017]
32. Zhang D., Mansaray L. R., Jin H., Sun H., Kuang Zh., Huang Jing-feng, (2018), A universal estimation model of fractional vegetation cover for different crops based on time series digital photographs, Computers and Electronics in Agriculture, 151,93-103.