Location: Location not imported yet.Title: Object-based classification of hyperspatial digital mapping camera (DMC) imagery for potential integration into the National Resource Inventory (NRI) of grazing lands) Author
Submitted to: American Society for Photogrammetry and Remote Sensing Proceedings
Publication Type: Abstract only
Publication Acceptance Date: 12/11/2009
Publication Date: 4/30/2010
Citation: Laliberte, A.S., Browning, D.M., Herrick, J.E., Gronemeyer, P. 2010. Object-based classification of hyperspatial digital mapping camera (DMC) imagery for potential integration into the National Resource Inventory (NRI) of grazing lands [abstract]. American Society for Photogrammetry and Remote Sensing (ASPRS) Annual Conference, April 26-30,2010, San Diego, CA. Interpretive Summary:
Technical Abstract: Land management agencies such as the Bureau of Land Management (BLM) and the Natural Resources Conservation Service (NRCS) are required to monitor and assess vegetation conditions across millions of acres of rangelands and grazing lands. Field-based assessments are very costly and inefficient over large areas; remote sensing offers the potential to increase the number of monitoring locations, automate the image classification process, and reduce monitoring costs. Hyperspatial digital aerial photography has great potential to complement or replace ground measurements of vegetation cover. We investigated object-based image analysis (OBIA) techniques for classifying vegetation in southwestern U.S. arid rangelands with 4 cm resolution digital aerial photography. We obtained high r-square values for image- and ground-based measures of percent cover (r-square values: 0.82-0.92). OBIA enabled us to automate the classification process by applying a process tree developed on one image iteratively to subsequent images of the same vegetation community. The ability to classify multiple images efficiently offers the potential to increase the precision of national level inventories by increasing sample locations and to reduce costs by requiring fewer personnel to obtain ground measurements. This approach has demonstrated potential for quantifying fine-scale land cover attributes with very high resolution digital imagery, and exhibits promise for nationwide application for monitoring grazing lands.