Object-based classification of grasslands from high resolution satellite image time series using Gaussian mean map kernels

Maïlys Lopes 1 Mathieu Fauvel 1 Stephane Girard 2 David Sheeren 1
2 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : This paper deals with the classification of grasslands using high resolution satellite image time series. Grasslands considered in this work are semi-natural elements in fragmented landscapes, i.e., they are heterogeneous and small elements. The first contribution of this study is to account for grassland heterogeneity while working at the object scale by modeling its pixels distributions by a Gaussian distribution. To measure the similarity between two grasslands, a new kernel is proposed as a second contribution: the a-Gaussian mean kernel. It allows to weight the influence of the covariance matrix when comparing two Gaussian distributions. This kernel is introduced in Support Vector Machine for the supervised classification of grasslands from south-west France. A dense intra-annual multispectral time series of Formosat-2 satellite is used for the classification of grasslands management practices, while an inter-annual NDVI time series of Formosat-2 is used for permanent and temporary grasslands discrimination. Results are compared to other existing pixel- and object-based approaches in terms of classification accuracy and processing time. The proposed method shows to be a good compromise between processing speed and classification accuracy. It can adapt to the classification constraints and it encompasses several similarity measures known in the literature. It is appropriate for the classification of small and heterogeneous objects such as grasslands.
Complete list of metadatas

Cited literature [76 references]  Display  Hide  Download

https://hal.inria.fr/hal-01424929
Contributor : Stephane Girard <>
Submitted on : Tuesday, June 13, 2017 - 4:28:15 PM
Last modification on : Friday, June 14, 2019 - 6:31:15 PM
Long-term archiving on : Tuesday, December 12, 2017 - 2:45:29 PM

File

paper_agmk_rem_sens_ver2.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Maïlys Lopes, Mathieu Fauvel, Stephane Girard, David Sheeren. Object-based classification of grasslands from high resolution satellite image time series using Gaussian mean map kernels. Remote Sensing, MDPI, 2017, 9 (7), pp.Article 688. ⟨10.3390/rs9070688⟩. ⟨hal-01424929v3⟩

Share

Metrics

Record views

766

Files downloads

675