Hierarchical object-based classification of ultra-high-resolution digital mapping camera (DMC) imagery for rangeland mapping and assessment

Abstract

Ultra-high-resolution digital aerial imagery has great potential to complement or replace ground measurements of vegetation cover for rangeland monitoring and assessment. This research investigated object-based image analysis (OBIA) techniques for classifying vegetation in southwestern USA arid rangelands with 4 cm resolution digital aerial imagery. We obtained high r-square values for the regressions relating ground- to image-based measures of percent cover (r-square values: 0.82–0.92). OBIA enabled us to automate the classification process and demonstrated potential for quantifying fine-scale land cover attributes with ultra-high-resolution imagery. This approach exhibits promise for nationwide application for monitoring grazing lands.

Keywords:

• aerial photography
• object-based image analysis
• very high resolution
• rangelands
• vegetation classification

Acknowledgements

This research was funded by the USDA Natural Resources Conservation Service in support of the Conservation Effects Assessment Project, and by the USDA Agricultural Research Service and the National Science Foundation Long-Term Ecological Research Program, Jornada Basin V: Landscape Linkages in Arid and Semiarid Ecosystems. The authors would like to thank Debra Peters and John Anderson for access to the LTER NPP sites, and Hector Godinez-Alvarez, Michelle Mattocks, David Toledo and Justin Van Zee for providing assistance with field data collection. Additional thanks go to the three anonymous reviewers.