DIGITALNA ARHIVA ŠUMARSKOG LISTA
prilagođeno pretraživanje po punom tekstu
| ŠUMARSKI LIST 3-4/2009 str. 40 <-- 40 --> PDF |
D. Klobučar, R. Pernar: UMJETNE NEURONSKE MREŽE U PROCJENI SASTOJINSKIH OBRASTA...Šumarski list br. 3–4, CXXXIII (2009), 145-155 http://www.isafa.it/scientifica/model. International Journal of Remote Sensing, retineurali.htm18: 981–989. Skidmore, A.K., B. J. Turner,W.Brinkhof,W.Wulder,M., K. Niemann, D. Goodenough, Knowles,1997: Performance of a neural ne-2000: Local maximum filtering for the extractwork: mapping forests using GIS and remotelytion of tree locations and basal area from high sensed data. Photogrammetric Engineering andspatial resolution imagery. Remote Sensing of Remote Sensing, 63: 501–514.En vironment 73, pp. 103–114. St-Onge,B., F.Cavayas,1997: AutomatedforestXiangcheng,M., YingbinZou, Wei Wei, Kestructure mapping from high resolution imagerypingMa,2005:Testing the generalization of arbased on directional semivariogram estimates.tificial neural networks with cross-validation and Remote Sensing of Environment 61, pp. 82–95.independent-validation in modelling rice tillering dynamics. Ecological Modelling 181, 493–508. Verbeke, L.P.C., F.M. BVanCoillie, R. R.DeWulf, 2006: Object-based forest stand densityOsnova gospodarenja G. J. “Jamaričko brdo”, važnost estimation from very high resolution optical1. 1. 2002. - 31. 12. 2011. imagery using wavelet-based texture measures. Pravilnik o uređivanju šuma. NN 111/06. In: 1st International Conference on Object-based ImageAnalysis (OBIA2006). Wang,Y., D. Dong,1997: Retrieving forest stand parameters from SAR backscatter data using a neural network trained by a canopy backscatter SUMMARY: In the field of remote sensing the results of research undertaken with the purpose of determining quantitative and qualitative stand parameters showed the usefulness of artificial neural networks (Ardö et al. 1997, Skidmore et al. 1997, Wang & Dong 1997, Moisen & Frescino 2002, Ingram et al. 2005, Joshi et al. 2006, Kuplich 2006, Verbeke et al. 2006, Klobučar et al. 2008) as an alternative approach to classical statistical methods. This paper explores the possibility of estimating and distributing stand density using methods of artificial neural networks. These methods involve particular textural features of first and second order histograms on a digital ortophoto compiled from black and white aerial photographs at an approximate scale of 1:20,000. The paper is also aimed at collecting data with an acceptable accuracy, which will reduce material investments. Research encompassed the area of the MU “Jamaričko Brdo”, Lipovljani forest administration. Cyclic surveying was conducted in 2000. In order to determine textural features of first and second order histograms, a sample was cut out from a digital ortophoto for 80 stand scenes (compartments/subcompartments) in management classes of pedunculate oak, sessile oak and common beech of the fourth (the most common), fifth and sixth age class. A multi-layer perceptron was used to solve the problem of stand density estimation. A multi-layer perceptron is a neural network without feedback connections, where supervised learning is carried out with the error back propagation algorithm. An early stopping method was applied to improve generalization. The early stopping method is a statistical cross-validation method in which the available data are divided into three sets: training, validation and testing set. Of the overall dataset, 50 % (or 40 compartments/subcompartments) relates to the training set, whereas the two remaining datasets were divided equally: 25 % (20 compartments/subcompartments) relate to the validation set and 25 % (20 compartments/ subcompartments) to the testing set. |