Search results for "Object based"
showing 2 items of 2 documents
Post-processing of Pixel and Object-Based Land Cover Classifications of Very High Spatial Resolution Images
2020
The state of the art is plenty of classification methods. Pixel-based methods include the most traditional ones. Although these achieved high accuracy when classifying remote sensing images, some limits emerged with the advent of very high-resolution images that enhanced the spectral heterogeneity within a class. Therefore, in the last decade, new classification methods capable of overcoming these limits have undergone considerable development. Within this research, we compared the performances of an Object-based and a Pixel-Based classification method, the Random Forests (RF) and the Object-Based Image Analysis (OBIA), respectively. Their ability to quantify the extension and the perimeter…
Object-based image analysis technique for gully mapping using topographic data at very high resolution (VHR)
2018
An accurate mapping of gullies is important since they are still major contributors of sediment to streams. Mapping gullies can be difficult because of the presence of dense canopy, which precludes the identification through aerial photogrammetry and other traditional remote sensing methods. Moreover, the wide spatial extent of some gullies makes their identification and characterization through field surveys a very large and expensive proposition. One cheaper and more expeditious way to detect gullies can be achieved in terms of morphological characteristics by the Digital Elevation Models (DEMs). The recent widespread availability of very high resolution (VHR) imagery, such as LIDAR data,…