Estimation of timber volume at the sample plot level by means of image segmentation and Landsat TM imagery

By H. Mäkelä, Anssi Pekkarinen. 2001

115 citations recorded by the source corpus.

Subfields: Ecology, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/8b838e0d543e305f9e451c8b01e7d12b576273fb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecology

In Environmental Engineering

Citations in the corpus

Using k-nn and discriminant analyses to classify rain forest types in a Landsat TM image over northern Costa Rica (2008, methodology): “We applied the modified implementation of “Segmentation with directed trees” (Narendra & Goldberg, 1980; Pekkarinen, 2002), which has shown good results for delineating forest stands and in extracting spectral features for forest inventory applications (Mäkelä & Pekkarinen, 2001; Pekkarinen, 2002).”
Modelling butterfly distribution based on remote sensing data (2002, result): “Introduction of object orientated segmentation methods could lead to more reliable classification results, particularly in small structured landscapes like ours (see, e.g. Kilpeläinen & Tokola, 1999; Stuckens et al., 2000; Mäkelä & Pekkarinen, 2001).”
Estimating areal means and variances of forest attributes using the k-Nearest Neighbors technique and satellite imagery (2007, methodology): “For estimating volume at stand and regional scales, Mäkelä and Pekkarinen (2001) examined different pixel window and image segment approaches to Landsat TM feature extraction and later (Mäkelä & Pekkarinen, 2004) used Landsat TMand stand-level inventory data to predict species specific stand volume.”
Forest change detection by statistical object-based method (2006, methodology): “The segmentation is also less sensitive to misregistration errors than traditional pixel-based analysis methods (Mäkelä & Pekkarinen, 2001) and reduces the change detection processing time given that there are much fewer objects than pixels.”
Estimation of managed loblolly pine stand age and density with Landsat ETM+ data (2006, background): “Pixels along the stand boundaries were excluded to minimize edge-effects (Makela and Pekkarinen, 2001), which could introduce errors in subsequent analyses.”
Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis (2018, background): “…Roy, 2014), better and faster forest change analysis from SPOT images (Desclée et al., 2006), robustness against shadowing and registration errors (Desclée et al., 2006; Mäkelä and Pekkarinen, 2001), and reduced salt-and-pepper e ﬀ ect apparent in per-pixel classi-ﬁ cations (Matton et al., 2015).”