A Hybrid Approach of Combining Random Forest with Texture Analysis and VDVI for Desert Vegetation Mapping Based on UAV RGB Data

Desert vegetation is an important part of arid and semi-arid areas, which plays an important role in preventing wind and fixing sand, conserving water and soil, maintaining the balanced ecosystem. Therefore, mapping the vegetation accurately is necessary to conserve rare desert plants in the fragile ecosystems that are easily damaged and slow to recover. In mapping desert vegetation, there are some weaknesses by using traditional digital classification algorithms from high resolution data. The traditional approach is to use spectral features alone, without spatial information. With the rapid development of drones, cost-effective visible light data is easily available, and the data would be non-spectral but with spatial information. In this study, a method of mapping the desert rare vegetation was developed based on the pixel classifiers and use of Random Forest (RF) algorithm with the feature of VDVI and texture. The results indicated the accuracy of mapping the desert rare vegetation were different with different methods and the accuracy of the method proposed was higher than the traditional method. The most commonly used decision rule in the traditional method, named Maximum Likelihood classifier, produced overall accuracy (76.69%). The inclusion of texture and VDVI features with RGB (Red Green Blue) data could increase the separability, thus improved the precision. The overall accuracy could be up to 84.19%, and the Kappa index with 79.96%. From the perspective of features, VDVI is less important than texture features. The texture features appeared more important than spectral features in desert vegetation mapping. The RF method with the RGB+VDVI+TEXTURE would be better method for desert vegetation mapping compared with the common method. This study is the first attempt of classifying the desert vegetation based on the RGB data, which will help to inform management and conservation of Ulan Buh desert vegetation.

[1]  Ren Zhi-ming,et al.  Capture and processing of low altitude remote sensing images by UAV , 2011 .

[2]  Zhang Fengshou.  Suaeda salsa dynamic remote monitoring and biomass remote sensing inversion in Shuangtaizi River estuary , 2011 .

[3]  Guofan Shao,et al.  Object-based urban vegetation mapping with high-resolution aerial photography as a single data source , 2013 .

[4]  Johannes R. Sveinsson,et al.  Random Forests for land cover classification , 2006, Pattern Recognit. Lett..

[5]  Zhang Zhi,et al.  Land use classification of object-oriented multi-scale by UAV image , 2013 .

[6]  J. Langhammer.  UAV Monitoring of Stream Restorations , 2019, Hydrology.

[7]  Vincent G. Ambrosia,et al.  Unmanned Aircraft Systems in Remote Sensing and Scientific Research: Classification and Considerations of Use , 2012, Remote. Sens..

[8]  D. Zhuang,et al.  Multi-scale quantitative assessment of the relative roles of climate change and human activities in desertification – A case study of the Ordos Plateau, China , 2010 .

[9]  Xiaohui Yang,et al.  Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms , 2020, Global Ecology and Conservation.

[10]  Zhenhai Li,et al.  Extracting apple tree crown information from remote imagery using deep learning , 2020, Comput. Electron. Agric..

[11]  N. Coops,et al.  Application of high spatial resolution satellite imagery for riparian and forest ecosystem classification , 2007 .

[12]  The study of vegetation biomass inversion based on the HJ satellite data in Yellow River wetland , 2013 .

[13]  Faith R. Kearns,et al.  Classification of the wildland-urban interface: A comparison of pixel- and object-based classifications using high-resolution aerial photography , 2008, Comput. Environ. Urban Syst..

[14]  Statistics: A New Approach. , 1957 .

[15]  D. Roberts,et al.  Urban tree species mapping using hyperspectral and lidar data fusion , 2014 .

[16]  Zhu Zhen.  Studies on the sandy desertification in China. , 2001 .

[17]  Brendan F. Kohrn,et al.  Small unmanned aerial vehicles (micro-UAVs, drones) in plant ecology , 2016, Applications in Plant Sciences.

[18]  Amr H. Abd-Elrahman,et al.  Analyzing fine-scale wetland composition using high resolution imagery and texture features , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[19]  Hui ZHANG,et al.  Kappa coefficient: a popular measure of rater agreement , 2015, Shanghai archives of psychiatry.

[20]  Javier Lacasta,et al.  End-to-end sequence labeling via deep learning for automatic extraction of agricultural regulations , 2019, Comput. Electron. Agric..

[21]  D. He,et al.  Evaluation of textural and multipolarization radar features for crop classification , 1995, IEEE Trans. Geosci. Remote. Sens..

[22]  S. Purkis,et al.  Enhanced detection of the coral Acropora cervicornis from satellite imagery using a textural operator , 2006 .

[23]  Pingbo Tang,et al.  Augmenting a deep-learning algorithm with canal inspection knowledge for reliable water leak detection from multispectral satellite images , 2020, Adv. Eng. Informatics.

[24]  Patricia Gober,et al.  Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery , 2011, Remote Sensing of Environment.

[25]  Jalal Amini,et al.  A method for generating floodplain maps using IKONOS images and DEMs , 2010 .

[26]  Jianhua Gong,et al.  UAV Remote Sensing for Urban Vegetation Mapping Using Random Forest and Texture Analysis , 2015, Remote. Sens..

[27]  Xi Chen,et al.  [Coverage extraction and up-scaling of sparse desert vegetation in arid area]. , 2009, Ying yong sheng tai xue bao = The journal of applied ecology.

[28]  R. Hall,et al.  Incorporating texture into classification of forest species composition from airborne multispectral images , 2000 .

[29]  M. A. Aguilar,et al.  Using texture analysis to improve per-pixel classification of very high resolution images for mapping plastic greenhouses , 2008 .

[30]  N. Lam,et al.  On the Issues of Scale, Resolution, and Fractal Analysis in the Mapping Sciences* , 1992 .

[31]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[32]  Naser El-Sheimy,et al.  A New Vegetation Segmentation Approach for Cropped Fields Based on Threshold Detection from Hue Histograms , 2018, Sensors.

[33]  E. Boyer,et al.  Acceptability and perceived utility of drone technology among emergency medical service responders and incident commanders for mass casualty incident management. , 2017, American journal of disaster medicine.

[34]  Lei Zhou,et al.  Investigating natural drivers of vegetation coverage variation using MODIS imagery in Qinghai, China , 2016, Journal of Arid Land.

[35]  Andrew R. Bankert,et al.  An open-source approach to characterizing Chihuahuan Desert vegetation communities using object-based image analysis , 2020 .