Resumo
The management of natural and planted forests can be conducted sustainably by implementing techniques that consider the spatial and temporal variability of the plant and soil. In this context, precision silviculture through remote sensing can play a vital role, mainly when using Unmanned Aerial Vehicles (UAVs) equipped with specific sensors. In the present study, an automated computational routine (based on computer vision techniques) was developed and validated to perform forest inventory in commercial Eucalyptus grandis forests, using an orthophoto mosaic obtained with an RGB sensor built-in to a UAV. The developed routine employs computer vision techniques, including template matching to locate plants, Delaunay triangulation to create a mesh and indicate the predominant orientations of the planting rows, and an adaptation of the Hough transform to estimate the analytical parameters of each row. These parameters are refined using linear regression to generate the lines best fitting the input data. Finally, the failure segments on each row are identified by detecting the plants in each row. A simulation of regular point distribution on the segment is then used to identify the planting failure. This process allows the geolocation of each failure point for replanting to be quantified. The routine has significant potential in the forest inventory, allowing the geolocation of failures with an overall accuracy of 0.97 and 0.99, respectively, and a maximum positional error of 0.15 m and 0.20 m, respectively.
Assuntos
Agricultura Florestal , Eucalyptus , Tecnologia de Sensoriamento Remoto , Dispositivos Aéreos não TripuladosResumo
Few studies have investigated the biometric attributes of citrus orchards under formation that use RGB sensors on board unmanned aerial vehicles (UAV) and the challenges are great. This study aimed to develop and validate a method of using aerial UAV images by automated routines to evaluate the biometric attributes of a crop of 'Tahiti' acid lime under formation. We used a multirotor UAV, programmed to capture images at three different map scales, with a frontal and side overlap of 80 %. Geoprocessing was carried out both with and without ground control points on each scale. An automated routine was developed in an open-source environment, consisting of three processing phases: i) Estimation of the plant biometric attributes, ii) Statistical analysis, and iii) Statistical Report Map (SRM). The use of the developed routine allowed to delimit and estimate the crown projection area with an accuracy of more than 95 % as well as identify and quantify the plants with an accuracy of over 97 %. The use of ground control points during the processing stage does not increase accuracy in estimating the biometric attributes under evaluation. On the other hand, map scale is strongly correlated with the quality of the estimates, especially plant height. The results allowed to define a method for the acquisition and analysis of aerophotogrammetric data using a UAV, which can be used to measure the plant biometric attributes under analysis and the method can be easily adapted to perennial crops.