Abstract
The use of unmanned aerial vehicles (UAV) can allow individual tree detection for forest inventories in a cost-effective way. The scale-space filtering (SSF) algorithm is commonly used and has the capability of detecting trees of different crown sizes. In this study, we made two improvements with regard to the existing method and implementations. First, we incorporated SSF with a Lab color transformation to reduce over-detection problems associated with the original luminance image. Second, we ported four of the most time-consuming processes to the graphics processing unit (GPU) to improve computational efficiency. The proposed method was implemented using PyCUDA, which enabled access to NVIDIA’s compute unified device architecture (CUDA) through high-level scripting of the Python language. Our experiments were conducted using two images captured by the DJI Phantom 3 Professional and a most recent NVIDIA GPU GTX1080. The resulting accuracy was high, with an F-measure larger than 0.94. The speedup achieved by our parallel implementation was 44.77 and 28.54 for the first and second test image, respectively. For each 4000 × 3000 image, the total runtime was less than 1 s, which was sufficient for real-time performance and interactive application.
Highlights
Recent improvements in inertial measurement units (IMUs), cameras, and flight control systems have led to an increase in the use of unmanned aerial vehicles (UAVs) as remote sensing tools.The advantages in using UAVs are that they can capture information on a single tree basis to improve plantation inventory, reduce the number of field plots required, and fulfill the customer’s specific needs of interactive surveys, which has great potential for plantation management and yield prediction
The speedup achieved by our parallel implementation was 44.77 and 28.54 for the first and second test image, respectively
We proposed a tree detection method for UAV images based on graphics processing units (GPU)-accelerated scale-space filtering
Summary
Recent improvements in inertial measurement units (IMUs), cameras, and flight control systems have led to an increase in the use of unmanned aerial vehicles (UAVs) as remote sensing tools. Some probabilistic methods, including Markov random fields (MRF) [7] and marked point process (MPP) [8] characterize tree geometry using stochastic models. This converts tree detection into an optimization problem, which is solved using classical optimization algorithms in a simulated annealing framework. There are problems associated with this method: first, the scale-space (SS) is often constructed based on luminance grayscale images, which are sensitive to bright objects and result in over-detection; and second, some algorithm parameters are highly sensitive to image conditions that require fine tuning, such as the trial-and-error method.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
