Novelty Detection Classifiers in Weed Mapping: Silybum marianum Detection on UAV Multispectral Images

Sensors - Tập 17 Số 9 - Trang 2007
Thomas Alexandridis1, Afroditi Alexandra Tamouridou2,1, Xanthoula Eirini Pantazi2, Anastasia L. Lagopodi3, J. Kashefi4, Georgios Ovakoglou1, Vassilios Polychronos5, Dimitrios Moshou2
1Laboratory of Remote Sensing and GIS, Faculty of Agriculture, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece
2Agricultural Engineering Laboratory, Faculty of Agriculture, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece
3Plant Pathology Laboratory, Faculty of Agriculture, Aristotle University of Thessaloniki, Thessaloniki 54124, Greece
4USDA-ARS-European Biological Control Laboratory, Tsimiski 43, 7th floor, Thessaloniki 54623, Greece
5Geosense S.A., Filikis Etairias 15-17, Pylaia, Thessaloniki 55535, Greece

Tóm tắt

In the present study, the detection and mapping of Silybum marianum (L.) Gaertn. weed using novelty detection classifiers is reported. A multispectral camera (green-red-NIR) on board a fixed wing unmanned aerial vehicle (UAV) was employed for obtaining high-resolution images. Four novelty detection classifiers were used to identify S. marianum between other vegetation in a field. The classifiers were One Class Support Vector Machine (OC-SVM), One Class Self-Organizing Maps (OC-SOM), Autoencoders and One Class Principal Component Analysis (OC-PCA). As input features to the novelty detection classifiers, the three spectral bands and texture were used. The S. marianum identification accuracy using OC-SVM reached an overall accuracy of 96%. The results show the feasibility of effective S. marianum mapping by means of novelty detection classifiers acting on multispectral UAV imagery.

Từ khóa


Tài liệu tham khảo

Thorp, 2004, A review on remote sensing of weeds in agriculture, Precis. Agric., 5, 477, 10.1007/s11119-004-5321-1

Zhang, 2012, Robust hyperspectral vision-based classification for multi-season weed mapping, ISPRS J. Photogramm. Remote Sens., 69, 65, 10.1016/j.isprsjprs.2012.02.006

Baerveldt, 2002, An agricultural mobile robot with vision-based perception for mechanical weed control, Auton. Robots, 13, 21, 10.1023/A:1015679903293

Waske, 2010, Sensitivity of support vector machines to random feature selection in classification of hyperspectral data, IEEE Trans. Geosci. Remote Sens., 48, 2880, 10.1109/TGRS.2010.2041784

Ahmed, 2012, Classification of crops and weeds from digital images: A support vector machine approach, Crop Prot., 40, 98, 10.1016/j.cropro.2012.04.024

Vapnik, V. (1998). Statistical Learning Theory, John Wiley & Sons, Inc.

Sluiter, R. (2005). Mediterranean Land Cover Change: Modelling and Monitoring Natural Vegetation Using Gis and Remote Sensing, Utrecht University.

Im, 2005, A change detection model based on neighborhood correlation image analysis and decision tree classification, Remote Sens. Environ., 99, 326, 10.1016/j.rse.2005.09.008

Dihkan, 2013, Remote sensing of tea plantations using an svm classifier and pattern-based accuracy assessment technique, Int. J. Remote Sens., 34, 8549, 10.1080/01431161.2013.845317

Crupi, 2004, Neural-network-based system for novel fault detection in rotating machinery, Modal Anal., 10, 1137

Tax, D.M.J. (2001). One-Class Classification. [Ph.D. Thesis, Delft University of Technology].

Parsons, W.T., and Cuthbertson, E. (2001). Noxious Weeds of Australia, CSIRO Publishing.

Tucker, J.M., Cordy, D.R., Berry, L.J., Harvey, W.A., and Fuller, T.C. (1961). Nitrate Poisoning in Livestock, University of California.

Khan, 2011, Screening the allelopathic potential of various weeds, Pak. J. Weed Sci. Res., 11, 73

Tamouridou, 2017, Evaluation of uav imagery for mapping silybum marianum weed patches, Int. J. Remote Sens., 38, 2246, 10.1080/01431161.2016.1252475

Pantazi, 2017, Evaluation of hierarchical self-organising maps for weed mapping using uas multispectral imagery, Comput. Electron. Agric., 139, 224, 10.1016/j.compag.2017.05.026

Peña, J.M., Torres-Sánchez, J., de Castro, A.I., Kelly, M., and López-Granados, F. (2013). Weed mapping in early-season maize fields using object-based analysis of unmanned aerial vehicle (UAV) images. PLoS ONE, 8.

Rojas, I., Joya, G., and Catala, A. (2015, January 6). An experimental comparison for the identification of weeds in sunflower crops via unmanned aerial vehicles and object-based analysis. Proceedings of the 13th International Work-Conference on Artificial Neural Networks (IWANN), Palma de Mallorca, Spain.

Torres-Sánchez, J., López-Granados, F., De Castro, A.I., and Peña-Barragán, J.M. (2013). Configuration and specifications of an unmanned aerial vehicle (UAV) for early site specific weed management. PLoS ONE, 8.

Tax, 2004, Support vector data description, Mach. Learn., 54, 45, 10.1023/B:MACH.0000008084.60811.49

Scholkopf, B., and Smola, A.J. (2002). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, MIT Press.

Saunders, R., and Gero, J.S. (2001, January 19–21). A curious design agent: A computational model of novelty-seeking behaviour in design. Proceedings of the Sixth Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2001), Sydney, Australia.

Japkowicz, N., Myers, C., and Gluck, M. (1995). A Novelty Detection Approach to Classification, International Joint Conference on Artificial Intelligence (IJCAI 95).

Hertz, J.A., Krogh, A.S., and Palmer, R.G. (1991). Introduction to the Theory of Neural Computation, Addison-Wesley Longman Publishing Co., Inc.

Baldi, 1989, Neural networks and principal component analysis: Learning from examples without local minima, Neural Netw., 2, 53, 10.1016/0893-6080(89)90014-2

Bourlard, 1988, Auto-association by multilayer perceptrons and singular value decomposition, Biol. Cybern., 59, 291, 10.1007/BF00332918

Bishop, C.M. (1995). Neural Networks for Pattern Recognition, Oxford University Press.

Congalton, 1991, A review of assessing the accuracy of classifications of remotely sensed data, Remote Sens. Environ., 37, 35, 10.1016/0034-4257(91)90048-B

Metternicht, G. (2007). Geospatial Technologies and the Management of Noxious Weeds in Agricultural and Rangelands Areas of Australia, University of South Australia.

Thông tin
Thông tin xuất bản

Sensors

Tập 17 Số 9

2007

Thông tin tác giả