Object-Based Land-Cover Mapping with High Resolution Aerial Photography at a County Scale in Midwestern USA

Abstract

There are growing demands for detailed and accurate land cover maps in land system research and planning. Macro-scale land cover maps normally cannot satisfy the studies that require detailed land cover maps at micro scales. In the meantime, applying conventional pixel-based classification methods in classifying high-resolution aerial imagery is ineffective to develop high accuracy land-cover maps, especially in spectrally heterogeneous and complicated urban areas. Here we present an object-based approach that identifies land-cover types from 1-meter resolution aerial orthophotography and a 5-foot DEM. Our study area is Tippecanoe County in the State of Indiana, USA, which covers about a 1300 km 2 land area. We used a countywide aerial photo mosaic and normalized digital elevation model as input datasets in this study. We utilized simple algorithms to minimize computation time while maintaining relatively high accuracy in land cover mapping at a county scale. The aerial photograph was pre-processed using principal component transformation to reduce its spectral dimensionality. Vegetation and non-vegetation were separated via masks determined by the Normalized Difference Vegetation Index. A combination of segmentation algorithms with lower calculation intensity was used to generate image objects that fulfill the characteristics selection requirements. A hierarchical image object network was formed based on the segmentation results and used to assist the image object delineation at different spatial scales. Finally, expert knowledge regarding spectral, contextual, and geometrical aspects was employed in OPEN ACCESSRemote Sens. 2014, 6 11373 image object identification. The resultant land cover map developed with this object-based image analysis has more information classes and higher accuracy than that derived with pixel-based classification methods.

Object Based Agricultural Land Cover Classification Map of Shadowed Areas From Aerial Image and Lidar Data Using Support Vector Machine

“…When the size of a growing region exceeds the threshold defined by the scale parameter, the merging process stops. Three criteria are defined in the Definiens software (formerly known as eCognition software) to constrain the pixel growing algorithm, namely: color, shape and scale, to control smoothness and compactness of image objects (Li and Shao, 2014). The subset of the study area showing segmentation for shadowed and non-shadowed classes as shown in Figure 2.…”

Mapping Complex Urban Land Cover from Spaceborne Imagery: The Influence of Spatial Resolution, Spectral Band Set and Classification Approach

“…A key factor for segmentation is how well segmented outputs correspond to real-world features. While the optimum shape and compactness settings remained consistent between input data sets (see Table 2 below), the scale setting had a significant impact on segmentation outcome [29]. Some recent A key factor for segmentation is how well segmented outputs correspond to real-world features.…”

“…In the past, considerable attention has focused on specific OBIA parameter settings, especially for the widely used eCognition [29], though this has created some difficulties for transferability since the OBIA process can be highly idiosyncratic to each particular study or image data set. As such, there is only limited benefit in reporting parameter settings, since these may not be directly transferable to another context.…”

Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks

“…The segments are then merged using the information from the classifier. Developing segmentation methods is an active research field [66], and some methods for merging regions include density-based spatial clustering of applications with noise (DBSCAN) [67] and mean brightness values [31]. These merging methods are based on only the input data, while our proposed merging method is based on the input data and the classified pixels.…”

“…Most datasets that use classification on a pixel-level only use a few hundred reference points [31,48,[50][51][52]. In order to validate the classifier using a much larger pool of validation points and for supervised learning and fine-tuning, each pixel in the full map is manually labeled.…”