Use of hidden Markov models and phenology for multitemporal satellite image classification: applications to mountain vegetation classification

Abstract

Abstract-Ground cover classification based on a single satellite image can be challenging. The work reported here concerns the use of multitemporal satellite image data in order to alleviate this problem. We consider the problem of vegetation mapping and model the phenological evolution of the vegetation using a Hidden Markov Model (HMM). The different vegetation classes can be in one of a predefined set of states related to their phenological development. The characteristics of a given class are specified by the state transition probabilities as well as the probability of given satellite observations for that class and state. Classification of a specific pixel is thus reduced to selecting the class that has the highest probability of producing a given series of observations for that pixel. Compared to standard classification techniques such as maximum likelihood (ML) classification, the proposed scheme is flexible in that it derives its properties not only from image specific training data, but also from a model of the temporal behavior of the ground cover. It is shown to produce results that compare favorably to those obtained using ML classification on single satellite images, it also generalizes better than this approach.

A spatial–temporal approach to monitoring forest disease spread using multi-temporal high spatial resolution imagery

“…Specifically, changes can be related to land use history, fire inventory and vegetation phenology and we can use these ancillary information to establish temporal relation among different image series. For example, in Liu et al (2005), a fire perimeter layer is used to link the land cover transition before and after fires; in Aurdal et al (2005), a phenology model based on Markov chain is used to integrate multi-temporal TM imagery.…”

Crop Area Mapping Using 100-m Proba-V Time Series

“…We used a multi-temporal sequence of 100-m Proba-V images covering one to two growing seasons. The work in [8] reported an overall accuracy of 63% for vegetation mapping in southern Norway using 25-m resolution Landsat images. Another similar study reported an overall accuracy of 62.7% using the NDVI temporal profiles approach and 72.8% using a maximum likelihood classifier in the northeast of Germany with phenological information and spectral-temporal profiles from Landsat TM/ETM [16].…”

A Hidden Markov Models Approach for Crop Classification: Linking Crop Phenology to Time Series of Multi-Sensor Remote Sensing Data

“…Previous work has tested the application of HMMs in Landsat time series to classify mountain vegetation in Norway [26] and arable land in Brazil [27], in MODIS-NDVI time series covering cultivated areas of the United States [28] and NDVI data derived from the Advanced Very High Resolution Radiometer (AVHRR) over the West African savanna [24]. In all the aforementioned studies, the low and medium resolution images have been reported to be adequate for the classification of large-sized agricultural holdings.…”