Skip to main content
ARS Home » Plains Area » Las Cruces, New Mexico » Range Management Research » Research » Publications at this Location » Publication #225738

Title: Texture and scale in object-based analysis of subdecimeter resolution unmanned aerial vehicle (UAV) imagery

Author
item LALIBERTE, ANDREA - NEW MEXICO STATE UNIV
item Rango, Albert

Submitted to: IEEE Transactions on Geoscience and Remote Sensing
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/1/2008
Publication Date: 3/1/2009
Citation: Laliberte, A., Rango, A. 2009. Texture and scale in object-based analysis of subdecimeter resolution unmanned aerial vehicle (UAV) imagery. IEEE Transactions on Geoscience and Remote Sensing. 47:761-770.

Interpretive Summary: Unmanned aerial vehicles (UAVs) have great potential for use in rangeland assessment and monitoring, because they can fly at low altitudes and acquire imagery with sub-decimeter pixel resolution. Due to low payload capabilities, inexpensive and light digital cameras are commonly used with the drawback of relatively low spectral resolution, presenting a challenge for image classification. We investigated the use of image texture measures and object-based image analysis for differentiating rangeland vegetation structure groups at multiple image segmentation scales. The inclusion of texture measures increased classification accuracies at almost all segmentation scales, and the highest accuracies in the high 90% range were found at the coarser analysis scales. Because texture calculations are computer intensive, the use of decision trees and class separability analysis offer a straightforward approach for determining optimal texture features and analysis scale. The results show that UAVs are viable platforms for rangeland monitoring with relatively inexpensive cameras, but with the recent increase in high resolution digital aerial cameras for piloted aircraft, the image analysis results have applicability in that field as well.

Technical Abstract: Imagery acquired with unmanned aerial vehicles (UAVs) has great potential for incorporation into natural resource monitoring protocols due to their ability to be deployed quickly and repeatedly and to fly at low altitudes. While the imagery may have high spatial resolution, the spectral resolution is low when lightweight, off-the-shelf digital cameras are used, and the inclusion of texture measures can potentially increase the classification accuracy. Texture measures have been used widely in pixel-based image analysis, but their use in an object-based environment has not been well documented. Our objectives were to determine the most suitable texture measures and the optimal image analysis scale for differentiating rangeland vegetation using UAV imagery segmented at multiple scales. A decision tree was used to determine the optimal texture features for each segmentation scale. The error rate of the decision tree was lower, prediction success was higher, class separability was greater, and overall accuracy was higher (high 90% range) at coarser segmentation scales, between 55 and 70 (range 10-80). The inclusion of texture measures increased classification accuracies at nearly all segmentation scales, and entropy was the texture measure with the highest score in most decision trees. The results demonstrate that UAVs are viable platforms for rangeland monitoring and that the drawbacks of low-cost off-the-shelf digital cameras can be overcome by including texture measures and using object-based image analysis highly suitable for very high resolution imagery.