What makes segmentation good? A case study in boreal forest habitat mapping
Räsänen, A., Rusanen, A., Kuitunen, M., & Lensu, A. (2013). What makes segmentation good? A case study in boreal forest habitat mapping. International Journal of Remote Sensing, 34(23), 8603-8627. https://doi.org/10.1080/01431161.2013.845318
Published inInternational Journal of Remote Sensing
© Taylor & Francis. This is an Author's final draft version of an article whose final and definitive form has been published by Taylor & Francis.
Segmentation goodness evaluation is a set of approaches meant for deciding which segmentation is good. In this study, we tested different supervised segmentation evaluation measures and visual interpretation in the case of boreal forest habitat mapping in Southern Finland. The data used were WorldView-2 satellite imagery, a lidar digital elevation model (DEM), and a canopy height model (CHM) in 2 m resolution. The segmentation methods tested were the fractal net evolution approach (FNEA) and IDRISI watershed segmentation. Overall, 252 different segmentation methods, layers, and parameter combinations were tested. We also used eight different habitat delineations as reference polygons against which 252 different segmentations were tested. The ranking order of segmentations depended on the chosen supervised evaluation measure; hence, no single segmentation could be ranked as the best. In visual interpretation among the several different segmentations that we found rather good, we selected only one as the best. In the literature, it has been noted that better segmentation leads to higher classification accuracy. We tested this argument by classifying 12 of our segmentations with the random forest classifier. It was found out that there is no straightforward answer to the argument, since the definition of good segmentation is inconsistent. The highest classification accuracy (0.72) was obtained with segmentation that was regarded as one of the best in visual interpretation. However, almost similarly high classification accuracies were obtained with other segmentations. We conclude that one has to decide what one wants from segmentation and use segmentation evaluation measures with care. ...
PublisherTaylor & Francis
Publication in research information system
MetadataShow full item record
Showing items with similar title or keywords.
Developing and comparing methods for mapping habitat types and conservation values using remote sensing data and GIS methods Räsänen, Aleksi (University of Jyväskylä, 2014)
Editorial for the special issue "Frontiers in spectral imaging and 3D technologies for geospatial solutions" Honkavaara, Eija; Karantzalos, Konstantinos; Liang, Xinlian; Nocerino, Erica; Pölönen, Ilkka; Rönnholm, Petri (MDPI, 2019)This Special Issue hosts papers on the integrated use of spectral imaging and 3D technologies in remote sensing, including novel sensors, evolving machine learning technologies for data analysis, and the utilization of ...
Airborne-laser-scanning-derived auxiliary information discriminating between broadleaf and conifer trees improves the accuracy of models for predicting timber volume in mixed and heterogeneously structured forests Bont, Leo Gallus; Hill, Andreas; Waser, Lars T.; Bürgi, Anton; Ginzler, Christian; Blattert, Clemens (Elsevier, 2020)Managing forests for ecosystem services and biodiversity requires accurate and spatially explicit forest inventory data. A major objective of forest management inventories is to estimate the standing timber volume for ...
Raita-Hakola, Anna-Maria; Pölönen, Ilkka (Copernicus Publications, 2022)The idea is to create a self-learning Minimal Learning Machine (MLM) model that is computationally efficient, easy to implement and performs with high accuracy. The study has two hypotheses. Experiment A examines the ...
Mazziotta, Adriano; Triviño, María; Tikkanen, Olli-Pekka; Kouki, Jari; Strandman, Harri; Mönkkönen, Mikko (Springer Netherlands, 2016)Species climate change vulnerability, their predisposition to be adversely affected, has been assessed for a limited portion of biodiversity. Our knowledge of climate change impacts is often based only on exposure, the ...