Developing a Land Cover Classification of Salt Marshes Using Uas Time-Series Imagery and an Open Source Workflow

Abstract

Salt marsh ecology classification is difficult using traditional coarse resolution remote sensing techniques. Salt marshes exhibit a spatial pattern of vegetation zonation that are visually identifiable using imagery that has an improved 0.04 meter per pixel resolution. This project applies high resolution unmanned aerial system (UAS) imagery to aid in multi-temporal classification of our study area (Horseneck Beach) in Westport, Massachusetts, USA. We flew a DJI Phantom Pro 3 at low-and high-tide to capture effects the changing tide has on vegetation in an effort to predict effects of the rising sea level on saline plant species. We implement an open source software workflow using OpenDroneMap and the Semi-Automatic Classification Plugin for QGIS to create the necessary orthomosaics and to conduct vegetation classification required of this project. We compare land cover classifications using one-time-point RGB imagery to a multi-time-point (low tide, high tide) RGB image stack to investigate whether the multi-time point stack improves land cover classification accuracy. We find it does. More generally, this paper provides a model for others wishing to use low-cost UAS equipment carrying a simple low-cost RGB camera, and free and open source for geospatial (FOSS4G) tools, to develop multi-band image stacks to improve land cover classification accuracy. Further, we provide some reflections and technical notes on our experience. The approach we present here could be extended to include other image layers that UAS can provide when equipped with other sensors, such as multi-spectral (e.g., NIR, thermal), or by adding another band with photogrammetry-produced digital elevation data.

Seasonality and Characterization Mapping of Restored Tidal Marsh by NDVI Imageries Coupling UAVs and Multispectral Camera

“…The methodology needs multiple improvements to enhance vegetation characterization and classification, including: (1) Accounting for environmental conditions, such as water level and soil moisture, which are dominant issues in tidal systems that may affect the reflectance in the near-infrared and consequently affect the assessment of the vegetation state (NDVI); and (2) automatic classification or semi-automatic classification, calibration of the UAV images, which will be essential to avoid misclassification and reduce lens distortion, as indicated by Myers et al (2018) [66]. Therefore, further research is needed to define algorithms and rules for the UAVs images classification.…”

Species and habitat mapping in two dimensions and beyond. Structure-from-Motion Multi-View Stereo photogrammetry for the Conservation Community

“…Whether commercial or FOSS, SfM-MVS software offer an opportunity for the conservation community to engage in new and novel remote sensing techniques. They can be utilised to create highly detailed maps and 2.5/3D data at local scales, now include FOSS options that are being successfully deployed for scientific research (3,4,53–58,62,105) and can be incorporated into the existing FOSS remote sensing pipeline. With applications for Android smartphones such as the UAV Toolkit (67) or small, lightweight action cameras now available, combined with balloons, kites, drones, or even collecting data on the ground, there is an opportunity within the conservation sphere to start enabling remote sensing even at a grass-roots or community level, or in any situation where funding may be limited but this type of data desired.…”

“…MicMac is the more mature software of the two and was initially developed in 2003 by the French National Geographic Institute and French national school for geographic sciences (52) whereas ODM began as a concept presentation at the 2014 FOSS4G (Free and Open Source Software for Geospatial) conference in Seoul. Both have drawn attention from the scientific community, but with ODM being the newer option, the focus has primarily been on its development and initial quality testing (3,4,53,54). MicMac’s maturity has allowed for a deeper scrutiny (55,56), has been utilised as the primary SfM-MVS option in geomorphological studies (57) and has been shown to be comparable to both Pix4D and Agisoft Photoscan (Metashape) within a low sward grassland study (58).…”

“…Relatively new technologies, such as drones (1,2), advances in computational power (3,4), improvements in digital cameras (5), along with classic remote sensing platforms such as kite aerial photography (KAP) and balloons (6,7), have all combined to help create a new opportunity in remote sensing research utilising SfM-MVS photogrammetry. It is these convergent developments that now position SfM-MVS as a cost-effective and democratic tool for conservation research.…”