Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-1/W4, 249-256, 2015
http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XL-1-W4/249/2015/
doi:10.5194/isprsarchives-XL-1-W4-249-2015
© Author(s) 2015. This work is distributed
under the Creative Commons Attribution 3.0 License.
 
26 Aug 2015
UNMANNED AERIAL VEHICLES PRODUCE HIGH-RESOLUTION, SEASONALLY-RELEVANT IMAGERY FOR CLASSIFYING WETLAND VEGETATION
J. V. Marcaccio, C. E. Markle, and P. Chow-Fraser Department of Biology, McMaster University, 1280 Main St. West, Hamilton, ON L8S 4K1, Canada
Keywords: Unmanned aerial vehicle, habitat mapping, vegetation classification, wetlands, multi-rotor, mapping Abstract. With recent advances in technology, personal aerial imagery acquired with unmanned aerial vehicles (UAVs) has transformed the way ecologists can map seasonal changes in wetland habitat. Here, we use a multi-rotor (consumer quad-copter, the DJI Phantom 2 Vision+) UAV to acquire a high-resolution (< 8 cm) composite photo of a coastal wetland in summer 2014. Using validation data collected in the field, we determine if a UAV image and SWOOP (Southwestern Ontario Orthoimagery Project) image (collected in spring 2010) differ in their classification of type of dominant vegetation type and percent cover of three plant classes: submerged aquatic vegetation, floating aquatic vegetation, and emergent vegetation. The UAV imagery was more accurate than available SWOOP imagery for mapping percent cover of submergent and floating vegetation categories, but both were able to accurately determine the dominant vegetation type and percent cover of emergent vegetation. Our results underscore the value and potential for affordable UAVs (complete quad-copter system < $3,000 CAD) to revolutionize the way ecologists obtain imagery and conduct field research. In Canada, new UAV regulations make this an easy and affordable way to obtain multiple high-resolution images of small (< 1.0 km2) wetlands, or portions of larger wetlands throughout a year.
Conference paper (PDF, 1211 KB)


Citation: Marcaccio, J. V., Markle, C. E., and Chow-Fraser, P.: UNMANNED AERIAL VEHICLES PRODUCE HIGH-RESOLUTION, SEASONALLY-RELEVANT IMAGERY FOR CLASSIFYING WETLAND VEGETATION, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-1/W4, 249-256, doi:10.5194/isprsarchives-XL-1-W4-249-2015, 2015.

BibTeX EndNote Reference Manager XML