Unmanned Aerial Vehicles(UAVs) have become popular and their use in agriculture monitoring is attracting more and more attention. There has emerged another class of agricultural UAVs whose normal consumer grade Red/Gr...Unmanned Aerial Vehicles(UAVs) have become popular and their use in agriculture monitoring is attracting more and more attention. There has emerged another class of agricultural UAVs whose normal consumer grade Red/Green/Blue(RBG) bands cameras have been modified to include the Near-Infrared(NIR) band by replacing one of the visible channel bands. This reduces the cost for agricultural UAVs. However, few researches have assessed the suitability of these modified UAV cameras in agricultural remote sensing. This study employed a modified UAV consumer grade camera with Blue/Green/Near Infra-red(BGNIR) bands to assess its applicability in crop remote sensing monitoring. Two experimental fields in Eastern Zimbabwe were used to assess the applicability of the modified BGNIR UAV camera in potato stress detection, maize senescence monitoring and chlorophyll concentration variations in bananas. Processed Green Normalized Vegetation Index(GNDVI) maps from the UAV imagery were compared with actual ground data of geo-tagged images taken during the UAV flights. Visual comparison between the ground and UAV imagery showed positive correlation. Highly stressed potato plants had lower GNDVI values than the healthier looking plants. Matured maize canopies also had lower GNDVI values than the late mature plants whose leaves were still green. GNDVI values in bananas from the first flight ranged from 0.094 91 to 0.334 74 and after the application of Nitrogen/Phosphorous/Potassium(NPK) fertilizer the GNDVI values ranged from 0.124 61 to 0.555 64. Increase in nitrogen also increases chlorophyll concentration in plant leaves hence the values of GNDVI increase after fertilization. We conclude that consumer grade modified UAV cameras are suitable in remote sensing of agricultural crops. Their adoption and utilization reduce the cost burden on farmers in developing countries especially in Africa, and help them to monitor their crops more efficiently.展开更多
Quantifying sugarcane production is critical for a wide range of applications, including crop management and decision making processes such as harvesting, storage, and forward selling. This study explored a novel mode...Quantifying sugarcane production is critical for a wide range of applications, including crop management and decision making processes such as harvesting, storage, and forward selling. This study explored a novel model for predicting sugarcane yield in Bundaberg region from time series Landsat data. From the freely available Landsat archive, 98 cloud free (<40%) Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper (ETM+) images, acquired between November 15th to July 31<sup>st</sup> (2001-2015) were sourced for this study. The images were masked using the field boundary layer vector files of each year and the GNDVI was calculated. An analysis of average green normalized difference vegetation index (GNDVI) values from all sugarcane crops grown within the Bundaberg region over the 15 year period identified the beginning of April as the peak growth stage and, therefore, the optimum time for satellite image based yield forecasting. As the GNDVI is an indicator of crop vigor, the model derived maximum GNDVI was regressed against historical sugarcane yield data, which showed a significant correlation with R<sup>2</sup> = 0.69 and RMSE = 4.2 t/ha. Results showed that the model derived maximum GNDVI from Landsat imagery would be a feasible and a modest technique to predict sugarcane yield in Bundaberg region.展开更多
基金Supported by Co-building Project of Jilin Province and Jilin University(No.SXGJXX2017-2)
文摘Unmanned Aerial Vehicles(UAVs) have become popular and their use in agriculture monitoring is attracting more and more attention. There has emerged another class of agricultural UAVs whose normal consumer grade Red/Green/Blue(RBG) bands cameras have been modified to include the Near-Infrared(NIR) band by replacing one of the visible channel bands. This reduces the cost for agricultural UAVs. However, few researches have assessed the suitability of these modified UAV cameras in agricultural remote sensing. This study employed a modified UAV consumer grade camera with Blue/Green/Near Infra-red(BGNIR) bands to assess its applicability in crop remote sensing monitoring. Two experimental fields in Eastern Zimbabwe were used to assess the applicability of the modified BGNIR UAV camera in potato stress detection, maize senescence monitoring and chlorophyll concentration variations in bananas. Processed Green Normalized Vegetation Index(GNDVI) maps from the UAV imagery were compared with actual ground data of geo-tagged images taken during the UAV flights. Visual comparison between the ground and UAV imagery showed positive correlation. Highly stressed potato plants had lower GNDVI values than the healthier looking plants. Matured maize canopies also had lower GNDVI values than the late mature plants whose leaves were still green. GNDVI values in bananas from the first flight ranged from 0.094 91 to 0.334 74 and after the application of Nitrogen/Phosphorous/Potassium(NPK) fertilizer the GNDVI values ranged from 0.124 61 to 0.555 64. Increase in nitrogen also increases chlorophyll concentration in plant leaves hence the values of GNDVI increase after fertilization. We conclude that consumer grade modified UAV cameras are suitable in remote sensing of agricultural crops. Their adoption and utilization reduce the cost burden on farmers in developing countries especially in Africa, and help them to monitor their crops more efficiently.
文摘Quantifying sugarcane production is critical for a wide range of applications, including crop management and decision making processes such as harvesting, storage, and forward selling. This study explored a novel model for predicting sugarcane yield in Bundaberg region from time series Landsat data. From the freely available Landsat archive, 98 cloud free (<40%) Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper (ETM+) images, acquired between November 15th to July 31<sup>st</sup> (2001-2015) were sourced for this study. The images were masked using the field boundary layer vector files of each year and the GNDVI was calculated. An analysis of average green normalized difference vegetation index (GNDVI) values from all sugarcane crops grown within the Bundaberg region over the 15 year period identified the beginning of April as the peak growth stage and, therefore, the optimum time for satellite image based yield forecasting. As the GNDVI is an indicator of crop vigor, the model derived maximum GNDVI was regressed against historical sugarcane yield data, which showed a significant correlation with R<sup>2</sup> = 0.69 and RMSE = 4.2 t/ha. Results showed that the model derived maximum GNDVI from Landsat imagery would be a feasible and a modest technique to predict sugarcane yield in Bundaberg region.
