Effect of Textural Features for Landcover Classification of Uav Multispectral Imagery of a Salt Marsh Restoration Site

Abstract

Abstract. Salt marshes are intertidal ecosystems valuable for services including coastal protection and carbon sequestration. Restoration of salt marshes is popular in this era of climate change and sea-level rise, especially in areas where marshes have been historically altered, including in the Bay of Fundy. Salt marsh restoration involves landcover change through time as a community of halophytic vegetation develops in the study area. Restoration sites are difficult to survey using traditional on-foot methods, and developing remote sensing methods to survey them would increase efficiency of monitoring. The purpose of our study was to assess the capability of UAV multispectral imagery to map landcovers in a salt marsh restoration site in the Musquash Estuary, New Brunswick, Canada. We used the Random Forests (RF) supervised classifier and validated our maps using field data. We also evaluated the importance of textural features by running two classifications, with and without textural features. The classification omitting textural features had lower classification and validation accuracies (96.29 % and 91.23 %, respectively) than the classification and validation accuracies obtained by including textural features (99.56 % and 96.84 %, respectively). Additional work is required to test our method in different locations and seasons.

Comparing Pixel- and Object-Based Approaches for Classifying Multispectral Drone Imagery of a Salt Marsh Restoration and Reference Site

“…Despite adequate average JM distance values, many pairs had low values (<1.90), indicating that they were not well separated. While low JM distances must be considered, our classifications were completed using additional input features of vegetation indices and textures that have improved classification accuracies in the past [36,76] but were not included in the JM distance calculations. In addition, many of our classes represented areas that changed from month to month, and it was expected that these classes would have low separability values when analyzed one month at a time.…”

“…Overall OOB accuracies were >99% when using multi-temporal image sets for both PB and OB methods (Tables 7 and 8). It is common for RF classifiers to achieve very high out-of-bag accuracy when working with many input variables [33,36,40], and many studies that use RF choose to not present OOB accuracy assessments. We have presented these values because they display how effective the RF classifiers were at assigning training area pixels to the correct classes, and it is valuable to understand how high these values can be when using hundreds of input variables, as we did (we used 414).…”

“…For our study, we used RF-supervised classification approaches. Random Forest, which has been used to achieve high classification accuracies for mapping salt marshes and other coastal wetlands [33,34,36,40,50,54], is considered easily accessible (including within the free software R v4.2.3) and requires relatively few pre-defined parameters. In addition, the structure of the RF classifier is more easily understood than those of deep learning classifiers, including Artificial Neural Networks, which use hidden layers.…”

“…Aerial imagery acquired using sensors fixed to planes [26][27][28] and satellites, including Sentinel [29], Landsat [30][31][32][33], Worldview [33], and others [34], has been successfully used for mapping coastal wetlands. Very-high-spatial-resolution aerial imagery can be acquired using sensors fixed to drones, which have recently (compared to planes and satellites) become popular tools for environmental monitoring and have also been used to map coastal wetland vegetation and its changes [35][36][37][38][39][40][41]. Prior to the development of very-highspatial-resolution drone and satellite imagery, which are especially valuable for assessing differences in heterogeneous wetland communities with species composition differing at the scale of centimeters [42], a prevalent challenge in mapping wetlands (including salt marshes) was that the spatial resolution of images was too low to assess fine-scale ecological dynamics [43].…”

“…When inspecting studies in other wetland environments that use very-high-spatial-resolution multispectral images but do not directly compare classification approaches, there is a preference for using OB methods [27,40,44,53] over PB methods [37]. Within a PB or OB framework (i.e., using either pixels or objects as the base unit of image analysis), many commonly used classification algorithms can be applied for mapping coastal wetland vegetation, such as machine learning algorithms, including Maximum Likelihood [32], Support Vector Machine [40], and Random Forest (RF) [33,34,36,40,50,54]; deep learning algorithms, including Artificial Neural Networks [38,44,52]; K-Nearest Neighbours [27]; etc. In general, many studies have investigated the suitability of the available classification algorithms for coastal wetlands and obtained varying results.…”