We have developed a map-based approach which enables us to efficiently extract object features from aerial images. We match an image with i ts corresponchng map in order to estimate the object states in the image. This approach is characterized by i t s active use of a figure contained in the map a s the object model for comparison. We determine the principal steps for the map-based approach fo...

Using Montarice in central Adriatic Italy as a case study, this paper focuses on the extraction of the spectral (i.e., plant colour) and geometrical (i.e., plant height) components of a crop canopy from archived aerial photographs, treating both parameters as proxies for archaeological prospection. After the creation of orthophotographs and a canopy height model using image-based modelling, new...

This paper presents a method for hypothesis verification in automatic road extraction based on the topology of road networks. The method includes the generation of topology of road networks, verification of hypothesized road segments and prediction of missing road segments. The topology of road networks is generated using small scale aerial images as they exhibit a global structure of road netw...

We propose a new method to simultaneously detect shadows and vegetation in remote sensing images. Several shadow and vegetation indices are merged with the Dempster-Shafer (DS) theory so as to increase the reliability and accuracy of the segmentation. The per-pixel DS fusion is incorporated in a Markovian context to obtain an optimal and regularized segmentation result. Evaluation on aerial ima...

In order to study the diversity of the leaf litter and aerial litter filamentous fungi, sample were collected from a semi-deciduous seasonal forest located in the Miguel Calmon, state of Bahia, Brazil. Leaf litter and aerial litter samples were collected. Samples were placed in moist chambers. Five conidial fungi were described for the first time in Brazil. Comments about their specimens and di...

An approach to simulating land-cover patterns based on historical land-use maps and forecasts based on models and planning documents is described and demonstrated. The approach uses stochastic spatial simulation to generate land-cover patterns on the basis of a land-use map and stated translation rules. The translation rules take the form of (1) a table that summarizes the proportions of each l...

This paper presents considerations and solutions, done by the National Survey and Cadastre (KMS), to overcome challenges in the transition from analogue to pure digital aerial image collection. Considerations and solutions are generalized but are actually linked to the case, when production is executed through partnerships established by a EU-tender.