Land use image classification through optimum-path forest clustering

Land use classification has been paramount in the last years, since we can identify illegal land use and also to monitor deforesting areas. Although one can find several research works in the literature that address this problem, we propose here the land use recognition by means of Optimum-Path Forest Clustering (OPF), which has never been applied to this context up to date. Experiments among Optimum-Path Forest, Mean Shift and K-Means demonstrated the robustness of OPF for automatic land use classification of images obtained by CBERS-2B and Ikonos-2 satellites. © 2011 IEEE.

Encampment time : an anthropological analysis of the land occupations in Brazil

In this article the social trajectory of a land occupation participant, an encamped woman (Edesmaria) who is a member of an extended landless family, is closely examined in order to demonstrate the inner workings of what is called 'the world of land occupations' in Brazil. Through a native expression (encampment time), it is demonstrated that nowadays, for some individuals, involvement in land occupations and landless workers' movements represents not just an opportunity to claim a parcel of land, but, even more importantly, a chance for social mobility and recognition. In this sense, encampment time is a social code and, as such, it not only quantifies the amount of time spent in a given encampment, but it is also a marker of prestige and status as well as a principle that organises and orders social relations in the land occupation world.

Toward Satellite-Based Land Cover Classification Through Optimum-Path Forest

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)