The increasing use of unmanned aerial vehicles (UAV) and high spatial resolution imagery from associated sensors necessitates the continued advancement of efficient means of image processing to ensure these tools are utilized effectively. This is exemplified in the field of forest management, where the extraction of individual tree crown information stands to benefit operational budgets. We explored training a region-based convolutional neural network (Mask R-CNN) to automatically delineate individual tree crown (ITC) polygons in regenerating forests (14 years after harvest) using true colour red-green-blue (RGB) imagery with an average ground sampling distance (GSD) of 3 cm. We predicted ITC polygons to extract height information using canopy height models generated from digital aerial photogrammetric (DAP) point clouds. Our approach yielded an average precision of 0.98, an average recall of 0.85, and an average F1 score of 0.91 for the delineation of ITC. Remote height measurements were strongly correlated with field height measurements (r2 = 0.93, RMSE = 0.34 m). The mean difference between DAP-derived and field-collected height measurements was −0.37 m and −0.24 m for white spruce (Picea glauca) and lodgepole pine (Pinus contorta), respectively. Our results show that accurate ITC delineation in young, regenerating stands is possible with fine-spatial resolution RGB imagery and that predicted ITC can be used in combination with DAP to estimate tree height.

No abstract

No abstract

Around the globe, various types of forest machinery are employed to conduct fully mechanized ground-based timber harvesting. In the Pacific Northwest the whole-tree harvesting method remains dominant. While machine-implemented sensors provide accurate productivity information in the cut-to-length harvesting method, productivity is more complicated to determine in whole-tree harvesting. This literature review compiles and analyses the existing evidence on productivity studies of feller-bunchers and feller-directors in a systematic manner and identifies the factors influencing machine productivity. The study indicates that most of the previous research was conducted in North America particularly in Canada. It was also found that a considerable portion of the literature lacked statistical analysis. The factors piece size, slope, and silvicultural treatment were the most commonly studied amongst the results to affect productivity. Although there is already a great knowledge of the most important factors influencing the productivity of feller-bunchers and feller-directors, there is still a lack in accurate measurement and isolation of individual factors to facilitate accurate productivity prediction. Detailed information is needed for the development of systems capable of estimating machine performance in terms of productivity through specific sensors. Updated productivity models will optimize harvesting operations, identify bottlenecks, and allow the development of best practices.

A comparison of traditional and mobile wood pellet mills found that mobile systems had higher production costs. Wildfire suppression costs have consistently exceeded British Columbia's budget set for such activities. Pelletization of excess wood for bioenergy applications has been proposed as a possible method of reducing the overall costs of fighting wildfires. In this study, a traditional pellet mill produces wood pellets from new, marginal feedstocks for $182.24 ± 24.47 tonne −1 and a mobile pellet production system produces wood pellets for $402.71 ± 24.18 tonne −1 . The traditional pellet mill produces 90,000 tonnes•yr −1 with harvest residues being collected in the forest, transported to the pellet mill, dried, chipped, pelletized and then stored. The mobile system collects harvest residues from the forest, transports them to the forest landing where the trailer-mounted mobile pellet system is established and is then ground, pelletized and dried if needed. The mobile system uses a novel high moisture pelletization system and harvest residues to heat the biomass dryer used in the system. The mobile pellet system requires 22 systems to produce 90,000 tonnes•yr −1 and each system should relocate 9 times in a year to minimize production costs related to feedstock quality and scarcity. These mobile pellet systems can allow increased forest management in forest areas at high risk for wildfires and reduce the cost of suppressing wildfires in treated areas.