Missing data reconstruction and anomaly detection in crop development using agronomic indicators derived from multispectral satellite images

Mohanad Albughdadi (1) , Denis Kouamé (1) , Guillaume Rieu (2) , Jean-Yves Tourneret (3, 4)

1 IRIT-TCI - Traitement et Compréhension d’Images
2 TerraNIS
3 IRIT-MINDS - CoMputational imagINg anD viSion
4 Toulouse INP - Institut National Polytechnique (Toulouse)

This paper studies a new three-step procedure for detecting anomalies in crop development using temporal indicators derived from multispectral satellite images. These anomalies may result from seeding problems, heterogeneity, deficiency and stress. The first step estimates different biophysical and statistical parameters associated with these parameters from the observed images. In a second step, missing data that arise from the existence of clouds or limited coverage in the satellite image are reconstructed. Finally, the mean shift algorithm is used as an unsupervised classifier to detect anomalies in these reconstructed data. The proposed procedure is evaluated using agronomic indicators estimated from SPOT 5 Take 5 satellite images from the Beauce area in France.

Mots clés: Mean shift; Anomaly detection; Agronomic indicators; Spot 5 satellite images; KNN reconstruction

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]; Traitement du signal et de l'image [eess.SP]

Mohanad Albughdadi, Denis Kouamé, Guillaume Rieu, Jean-Yves Tourneret. Missing data reconstruction and anomaly detection in crop development using agronomic indicators derived from multispectral satellite images. 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Jul 2017, Fort Worth, Texas, United States. pp.5081-5084. ⟨hal-02617253⟩