Object-oriented and fuzzy logic classification methods for mapping reforested areas with exotic species in Rio Canoas State Park-Santa Catarina, Brazil

摘要

Reforestation with exotic plans may alter the natural flora due to uncontrolled expansion of the inserted species. This study evaluated the potential of the object-oriented classification method using fuzzy logic algorithm for the differentiation of forest areas in intermediate/advanced stage and areas reforested with exotic species around the Rio Canoas State Park in Santa Catarina State of Brazil, using high spatial resolution SPOT6 imagery. The study region has regional importance for the preservation of mixed ombrophilous forest remnants and is belonging to the Biosphere Reserve of the Atlantic Rainforest, and hence, it is important to monitor the advance of exotic species in the region. The methodology consisted of the creation of the hierarchical network and process tree with numerous descriptor tests in Trimble Ecognition software, principal component analysis, multi-resolution segmentation algorithm and fuzzy logic functions. It was concluded that the use of principal components associated with the red band by a simple ratio of digital levels is extremely effective for identifying the areas reforested with exotic species. Fuzzy logic pertinence functions are the key in discriminating natural forest areas and areas reforested with exotic species in the study region accurately. The object-oriented classification was validated by points collected in the field and presented an overall accuracy level of 0.83 and Kappa index of 0.78, concluding that it is an efficient methodology in the delimitation of exotic species reforestation areas around Rio Canoas State Park.