“…The spatial resolution of commercially available satellite and aerial images produced by passive and active technology ranges from several meters (MODIS, IKONOS, WorldView, and RapidEye) to tens of centimetres (LiDAR and aerial images) [Schowengerdt, 2007]. Previous studies have constructed canopy cover maps of large areas from mid or low spatial resolution datasets, such as Landsat Thematic Mapper (TM), NASA Multi-angle Imaging SpectroRadiometer (MISR), and Linear Imaging Self Scanning Sensor (LISS III) [Carreiras et al, 2006;Chopping et al, 2008;Yang et al, 2012] or high spatial resolution datasets, such as Compact Airborne Spectrographic Imager (CASI), Color-Infrared (CIR) orthophotos, and LiDAR [Bunting and Lucas, 2006;Kral, 2009;Mathieu et al, 2013]. The spatial resolution of most satellite remote sensing images is too low to identify many objects from their shape or spatial detail [Schowengerdt, 2007;Frohn and Chaudhary, 2008].…”