OBJECT BASED POSTPROCESSING METHOD FOR CROP CLASSIFICATION MAPS ACCORDING TO EACH CLASS SPECIFICITY

Микола Сергіович Лавренюк

Abstract


Obtaining reliable and accurate crop classification and land cover map based on satellite data, in particular high resolution data, is one of the most important tasks in remote sensing. Such maps provide basic information for many other applied problems and are vital in remote sensing studies. Despite of which machine learning methods were utilized for maps obtaining: traditional (Random Forest, Support Vector Machine, Multi-layer perceptron, logistic regression) or state-of-the-art approaches (autoencoder, convolutional neural network, recurrent neural network) there is some noise (single pixels or groups and clusters of pixels that wrong classify) on such maps. There are traditional methods for noise reduction, however these methods do not take into account image semantics. Therefore, they are not effective for filtration land cover and crop classification maps based on satellite images. The most complicated task in the filtering such maps is to preserve boundaries between different agricultural fields and to remove quite big clusters of incorrect classified pixels (objects) and at the same time save small farmer fields that are right classified. Thus, in this paper we proposed new method for postprocessing crop classification map based on algorithm that takes into account each class specificity and as a result utilizes different thresholds for different classes. We proposed investigate each object in classification map independently and decision should be: “is this whole object a noise or not?”. We consider each class independent and use connected component labeling technique for discriminating objects from classification map. Further different types of conditions based on sharpness and compactness where proposed for the investigated object. Accuracy and efficiency of this method with the proposed filtration method have been tested on the independent set and using the visual comparison with the results of utilizing common filters. Also, McNemar statistical test has been conducted to prove the statistically significant gain of utilizing proposed filtration methodology compare to common voting filter

Keywords


crop classification; postprocessing; filtration; connected component labeling; Sobel algorithm

References


Huang, Xin, et al. New postprocessing methods for remote sensing image classification: A systematic study. IEEE Transactions on Geoscience and Remote Sensing, vol. 52, iss. 11, 2014, pp. 7140-7159.

Kolotii, A., et al. Comparison of biophysical and satellite predictors for wheat yield forecasting in Ukraine. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 40, iss.7, 2015, pp. 39-44.

Gallego, Francisco Javier, et al. Efficiency assessment of using satellite data for crop area estimation in Ukraine. International Journal of Applied Earth Observation and Geoinformation, vol. 29, 2014, pp. 22-30.

Kogan, Felix, et al. Winter wheat yield forecasting in Ukraine based on Earth observation, meteorological data and biophysical models. International Journal of Applied Earth Observation and Geoinformation, vol. 23, 2013, pp. 192-203.

Kussul, Nataliia, et al. Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data. IEEE Geoscience and Remote Sensing Letters, vol. 14, iss. 5, 2017, pp. 778-782.

Shelestov, Andrii, et al. Exploring Google Earth Engine Platform for Big Data Processing: Classification of Multi-Temporal Satellite Imagery for Crop Mapping. Frontiers in Earth Science, vol. 5, 2017, pp. 17.

Kussul, Nataliia, et al. Parcel-based crop classification in ukraine using landsat-8 data and sentinel-1A data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 9, iss. 6, 2016, pp. 2500-2508.

Waldner, François, et al. Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity. International Journal of Remote Sensing, vol. 37, iss. 14, 2016, pp. 3196-3231.

Lavrenyuk, Mykola. Metod ob"yektnoyi fil'tratsiyi kart klasyfikatsiyi zemnoho pokryvu na osnovi morfolohichnykh oznak [Method of object filtering maps of the classification of the earth's surface on the basis of morphological features]. Induktyvne modelyuvannya skladnykh system, 2017, no. 9 (unpublished).

Löw, Fabian, Christopher Conrad, and Ulrich Michel. Decision fusion and non-parametric classifiers for land use mapping using multi-temporal RapidEye data. ISPRS Journal of Photogrammetry and Remote Sensing, vol. 108, 2015, pp. 191-204.

Kussul, N., Shelestov, A., Basarab, R., Skakun, S., Kussul, O., Lavreniuk, M. Geospatial Intelligence and Data Fusion Techniques for Sustainable Development Problems. In ICTERI, 2015, pp. 196–203.

Kussul, N., Lavreniuk, N., Shelestov, A., Yailymov, B., Butko, I. Land Cover Changes Analysis Based on Deep Machine Learning Technique. Jour. of Automation and Information Sciences, 2016, vol. 48, no. 5, pp. 42–54.

Kussul, N., Shelestov, A., Lavreniuk, M., Butko, I., Skakun, S. Deep learning approach for large scale land cover mapping based on remote sensing data fusion. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2016, pp. 198-201.

Kussul, N., Lavreniuk, M., Shelestov, A., Yailymov, B. Along the season crop classification in Ukraine based on time series of optical and SAR images using ensemble of neural network classifiers. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2016, pp. 7145-7148.

LUCAS 2009, Land Use / Cover Area Frame Survey. Available at: http://ec.europa.eu/eurostat/documents/205002/208938/LUCAS2009_C1-Instructions_Revised20130925.pdf/ (аccessed 12.06.2017).

Lavreniuk, Mykola, et al. Large-scale classification of land cover using retrospective satellite data. Cybernetics and Systems Analysis, vol. 52, iss. 1, 2016, pp. 127-138.

Lavreniuk, M. S. Metod detektuvannya mezh na karti klasyfikatsiyi na osnovi modyfikovanoho alhorytmu Sobelya [Borders detection method based on a modified sobel algorithm for crop classification maps]. Radioelektronni i komp'uterni sistemi - Radioelectronic and computer systems, 2017, no. 4 (84), pp. 17–27.

Kesheng, Wu., Ekow, Otoo., Shoshani, Arie. Optimizing connected component labeling algorithms. Lawrence Berkeley National Laboratory. Available at: https://escholarship.org/uc/item/7jg5d1zn (аccessed 12.08.2017).

Chrystal, George. On the problem to construct the minimum circle enclosing n given points in the plane. Proceedings of the Edinburgh Mathematical Society, 1885, vol. 3, pp. 30-33.

Rocha, Lourena, Luiz Velho, and Paulo Cezar Pinto Carvalho. "Image moments-based structuring and tracking of objects. Computer Graphics and Image Processing, 2002. Proceedings. XV Brazilian Symposium on. IEEE. Available at: http://

ieeexplore.ieee.org/document/1167130/ (аccessed 15.07.2017). DOI: 10.1109/SIBGRA.2002.1167130

Stojmenovic, Milos., Nayak, Amiya. Direct ellipse fitting and measuring based on shape boundaries. Advances in Image and Video Technology, 2007, pp. 221-235.

Vermeer, Martin. "Statistical uncertainty and error propagation. Available at: https://users.aalto.fi/

~mvermeer/uncertainty.pdf (аccessed 22.05.2017).

Ramer, Urs. An iterative procedure for the polygonal approximation of plane curves. Computer graphics and image processing, 1972, vol. 1, iss. 3, pp. 244-256.

Douglas, David H., Peucker, Thomas K. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica: The International Journal for Geographic Information and Geovisualization, 1973, vol. 10, iss. 2, pp. 112-122.

Beucher, Serge, and Christian Lantuéjoul. "Use of watersheds in contour detection. Workshop on image processing. Available at: http://cmm.ensmp.fr/~beucher/publi/watershed.pdf (аccessed 11.04.2017).

Congalton, Russell G. A review of assessing the accuracy of classifications of remotely sensed data. Remote sensing of environment, 1991, vol. 37, iss. 1, pp. 35-46.

Foody, Giles M. Classification accuracy comparison: hypothesis tests and the use of confidence intervals in evaluations of difference, equivalence and non-inferiority. Remote Sensing of Environment, 2009, vol. 113, iss. 8, pp. 1658-1663.

Foody, Giles M. Thematic map comparison. Photogrammetric Engineering & Remote Sensing, 2004, vol. 70, iss. 5, pp. 627-633.

Skakun, Sergii, et al. Efficiency assessment of multitemporal C-band Radarsat-2 intensity and Landsat-8 surface reflectance satellite imagery for crop classification in Ukraine. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, vol. 9, iss. 8, pp. 3712-3719.

Kussul, Nataliia, et al. Regional scale crop mapping using multi-temporal satellite imagery. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2015, vol. 40, iss. 7, pp. 45–52. DOI:10.5194/isprsarchives-XL-7-W3-45-2015.




DOI: https://doi.org/10.32620/aktt.2018.1.10