Abstract:
© 2021 Elsevier B.V. Maintaining the massive forests of the forestry industry requires physical samples from the tree canopy to enable breeding, genetics research and monitoring of diseases. An autonomous Unmanned Aerial Vehicle (UAV) canopy sampling solution requires locating and tracking a highly unstructured, moving object against a dynamic, cluttered background. The developed algorithm utilises stereo vision techniques to reconstruct a 3D point cloud of the target branch and subsequently estimate the intercept point location. The optimal parameters are selected by quantifying the accuracy against ground truth obtained from motion capture. Since wind will likely affect the tree canopy during sampling, the branch will exhibit some sway motion which can be modelled as simple harmonic motion. Hence, a linear Kalman filter is formulated to estimate the sway parameters. With the branch 1m from the camera, the average error is 41mm for sway amplitudes between 50mm and 250mm with a plain background. When tested with a cluttered background, the reduced contrast results in higher standard deviations. Overall, the developed Kalman filter significantly reduces the intercept point error standard deviation, averaging 17% and 33% reductions for plain and cluttered backgrounds respectively. Subsequent outdoor testing verified the capability of the developed algorithm to estimate the branch trajectory to well within the maximum gripper opening of 115mm.