Using SPOT 5 fusion-ready imagery to detect Chinese tamarisk (saltcedar) with mathematical morphological method

Evaluating the Potential of Multi-Seasonal CBERS-04 Imagery for Mapping the Quasi-Circular Vegetation Patches in the Yellow River Delta Using Random Forest

“…Accuracy assessment of the classification results was presented in a confusion matrix and measured according to the producer's (PA) and user's accuracy (UA), overall accuracy (OA), and the Kappa coefficient. Next a successive identification was performed, where a majority analysis with a 3 × 3 kernel size was first used to match the salt and pepper noise pixels within a large single class with a large single class, followed by a change in the classification to vector analysis in order to separate the QVPs from the non-QVP vegetation based on the thresholds of area (less than 3000 m 2 ) and perimeter/area (less than 0.54), as determined by previous results [16,28,73]. The precision rate (Ad), recall rate (Ar), and F measure (F) were then used to analyze the final detection accuracy of the QVPs; these factors have often been used for performance measures in pattern recognition, information retrieval, machine learning and binary classification [73,99].…”

Comparison of CBERS-04, GF-1, and GF-2 Satellite Panchromatic Images for Mapping Quasi-Circular Vegetation Patches in the Yellow River Delta, China

“…Timely, reliable information on vegetation patches is necessary to quantify the effects of complex, interacting ecological processes and to formulate an understanding of ecosystem dynamics. Although traditional ground-based methods have revealed vegetation patch landscapes, the disadvantages of such methods include the limited spatial extent covered and the associated time and cost required [ 22 , 23 ]. Moreover, even intensive and long-term field observations cannot by themselves provide full coverage of dynamic variations in vegetation spatial patterns and the timing of changes in related driving forces [ 24 ].…”

“…Laliberte et al [ 31 ] used an object-oriented image analysis (OB) to map shrub encroachment from 1937 to 2003 in southern New Mexico using aerial photographs acquired between 1937 and 1996 and the QB satellite images acquired in 2003. Multi-temporal Landsat TM, SPOT 5, ALOS, ZY-3, and QB images have been used to monitor quasi-circular vegetation patch (QVP) recovery in abandoned land in the Yellow River Delta (YRD) [ 13 , 23 , 32 , 33 , 34 , 35 ]. It was a practical method to detect the location and dynamics of the QVPs through the analysis of the absorption position and depth using the tasseled cap transformation brightness from 15 m fusion-ready Landsat 7 ETM+ at-satellite reflectance [ 34 ].…”

“…It was a practical method to detect the location and dynamics of the QVPs through the analysis of the absorption position and depth using the tasseled cap transformation brightness from 15 m fusion-ready Landsat 7 ETM+ at-satellite reflectance [ 34 ]. The QVPs could be effectively detected using the edge detector and the geometric differences between the QVPs and background based on SPOT 5 (2.5 m resolution fusion imagery), ALOS (2.5 m resolution fusion imagery) and ZY-3 (5.8 m resolution multispectral imagery) images, and the detection accuracy was 93.4%, 89.3% and 64.1%, respectively [ 23 , 32 , 33 ]. The object-based approach was a useful tool for mapping the QVPs with the QB high spatial resolution multispectral image, and the precision rate was 65.6% [ 35 ].…”

“…Consequently, it is important to compare the different types of satellite images that are available for vegetation patch studies, especially images from high-resolution (fine–spatial resolution) satellite sensors. Although the previous research had demonstrated that the images with a pixel size of 2 m were suitable for mapping vegetation patch patterns [ 18 , 23 , 33 ], if the same vegetation patch can be detected at a coarser spatial resolution, future studies on vegetation patch patterns may avoid the cost-, time-, and labor-intensiveness associated with high–spatial resolution remote sensing images, unless detailed analytical data are needed.…”