Browsing by Subject "unmanned aerial vehicle"

Sort by: Order: Results:

Now showing items 1-5 of 5
  • Ouattara, Issouf; Hyyti, Heikki; Visala, Arto (Elsevier, 2020)
    IFAC-PapersOnLine, Proceedings of the 21th IFAC World Congress, Berlin, Germany, 12-17 July 2020
    We propose a novel method to locate spruces in a young stand with a low cost unmanned aerial vehicle. The method has three stages: 1) the forest area is mapped and a digital surface model and terrain models are generated, 2) the locations of trees are found from a canopy height model using local maximum and watershed algorithms, and 3) these locations are used in a convolution neural network architecture to detect young spruces. Our result for detecting young spruce trees among other vegetation using only color images from a single RGB camera were promising. The proposed method is able to achieve a detection accuracy of more than 91%. As low cost unmanned aerial vehicles with color cameras are versatile today, the proposed work is enabling low cost forest inventory for automating forest management.
  • Tienaho, Noora (Helsingin yliopisto, 2021)
    Structural complexity of trees is related to various ecological processes and ecosystem services. It can also improve the forests’ ability to adapt to environmental changes. In order to implement the management for complexity and to estimate its functionality, the level of structural complexity must be defined. The fractal-based box dimension (Db) provides an objective and holistic way to define the structural complexity for individual trees. The aim of this study was to compare structural complexity of Scots pine (Pinus sylvestris) trees measured by two remote sensing techniques, namely, terrestrial laser scanning (TLS) and aerial imagery acquired with unmanned aerial vehicle (UAV). Structural complexity for each Scots pine tree (n=2065) was defined by Db-values derived from the TLS and UAV measured point clouds. TLS produced the point clouds directly whereas UAV imagery was converted into point clouds with structure from motion (SfM) technology. The premise was that TLS provides the best available information on Db-values as the point density is higher in TLS than in UAV, and be-cause TLS is able to penetrate vegetation. TLS and UAV measured Db-values were found to significantly differ from each other and, thus, the techniques did not provide comparable information on structural complexity of individual Scots pine trees. On average, UAV measured Db-values were 5% bigger than TLS measured. The divergence between the TLS and UAV measured Db-values was found to be explained by the differences in the number and distribution of the points in the point clouds and by the differences in the estimated tree heights and number of boxes in the box dimension method. Forest structure (two thinning intensities, three thinning types and a control group) significantly affected the variation of both TLS and UAV measured Db-values. However, the divergence between TLS and UAV measured Db-values remained in all the treatments. In terms of the individual tree detection, the number of obtained points in the point cloud, and the distribution of these points, UAV measurements were better when the forest structure was sparser. In conclusion, while aerial imaging is a continuously developing study area and provides many advantageous attributes, at the moment, the TLS methods still dominate in accuracy when measuring the structural complexity at the tree-level. In the future, it should be studied whether TLS and UAV could be used as complementary techniques to provide more accurate and holistic view of the structural complexity in the perspective of both tree- and stand-level.
  • Roosjen, Peter, P.J.; Brede, Benjamin; Suomalainen, Juha, M.; Bartholomeus, Harm, M.; Kooistra, Lammert; Clevers, Jan, G.P.W. (2018)
    International Journal of Applied Earth Observation and Geoinformation
    In addition to single-angle reflectance data, multi-angular observations can be used as an additional information source for the retrieval of properties of an observed target surface. In this paper, we studied the potential of multi-angular reflectance data for the improvement of leaf area index (LAI) and leaf chlorophyll content (LCC) estimation by numerical inversion of the PROSAIL model. The potential for improvement of LAI and LCC was evaluated for both measured data and simulated data. The measured data was collected on 19 July 2016 by a frame-camera mounted on an unmanned aerial vehicle (UAV) over a potato field, where eight experimental plots of 30 × 30 m were designed with different fertilization levels. Dozens of viewing angles, covering the hemisphere up to around 30° from nadir, were obtained by a large forward and sideways overlap of collected images. Simultaneously to the UAV flight, in situ measurements of LAI and LCC were performed. Inversion of the PROSAIL model was done based on nadir data and based on multi-angular data collected by the UAV. Inversion based on the multi-angular data performed slightly better than inversion based on nadir data, indicated by the decrease in RMSE from 0.70 to 0.65 m2/m2 for the estimation of LAI, and from 17.35 to 17.29 μg/cm2 for the estimation of LCC, when nadir data were used and when multi-angular data were used, respectively. In addition to inversions based on measured data, we simulated several datasets at different multi-angular configurations and compared the accuracy of the inversions of these datasets with the inversion based on data simulated at nadir position. In general, the results based on simulated (synthetic) data indicated that when more viewing angles, more well distributed viewing angles, and viewing angles up to larger zenith angles were available for inversion, the most accurate estimations were obtained. Interestingly, when using spectra simulated at multi-angular sampling configurations as were captured by the UAV platform (view zenith angles up to 30°), already a huge improvement could be obtained when compared to solely using spectra simulated at nadir position. The results of this study show that the estimation of LAI and LCC by numerical inversion of the PROSAIL model can be improved when multi-angular observations are introduced. However, for the potato crop, PROSAIL inversion for measured data only showed moderate accuracy and slight improvements.
  • Yrttimaa, Tuomas; Saarinen, Ninni; Kankare, Ville; Viljanen, Niko; Hynynen, Jari; Huuskonen, Saija; Holopainen, Markus; Hyyppa, Juha; Honkavaara, Eija; Vastaranta, Mikko (2020)
    Terrestrial laser scanning (TLS) provides a detailed three-dimensional representation of surrounding forest structures. However, due to close-range hemispherical scanning geometry, the ability of TLS technique to comprehensively characterize all trees, and especially upper parts of forest canopy, is often limited. In this study, we investigated how much forest characterization capacity can be improved in managed Scots pine (Pinus sylvestris L.) stands if TLS point clouds are complemented with photogrammetric point clouds acquired from above the canopy using unmanned aerial vehicle (UAV). In this multisensorial (TLS+UAV) close-range sensing approach, the used UAV point cloud data were considered especially suitable for characterizing the vertical forest structure and improvements were obtained in estimation accuracy of tree height as well as plot-level basal-area weighted mean height (H-g) and mean stem volume (V-mean). Most notably, the root-mean-square-error (RMSE) in H-g improved from 0.8 to 0.58 m and the bias improved from -0.75 to -0.45 m with the multisensorial close-range sensing approach. However, in managed Scots pine stands, the mere TLS also captured the upper parts of the forest canopy rather well. Both approaches were capable of deriving stem number, basal area, V-mean, H-g, and basal area-weighted mean diameter with the relative RMSE less than 5.5% for all the sample plots. Although the multisensorial close-range sensing approach mainly enhanced the characterization of the forest vertical structure in single-species, single-layer forest conditions, representation of more complex forest structures may benefit more from point clouds collected with sensors of different measurement geometries.
  • Sandbrook, Chris; Clark, Douglas; Toivonen, Tuuli; Simlai, Trishant; O'Donnell, Stephanie; Cobbe, Jennifer; Adams, William (2021)
    Wildlife conservation and research benefits enormously from automated and interconnected monitoring tools. Some of these tools, such as drones, remote cameras, and social media, can collect data on humans, either accidentally or deliberately. They can therefore be thought of as conservation surveillance technologies (CSTs). There is increasing evidence that CSTs, and the data they yield, can have both positive and negative impacts on people, raising ethical questions about how to use them responsibly. CST use may accelerate because of the COVID-19 pandemic, adding urgency to addressing these ethical challenges. We propose a provisional set of principles for the responsible use of such tools and their data: (a) recognize and acknowledge CSTs can have social impacts; (b) deploy CSTs based on necessity and proportionality relative to the conservation problem; (c) evaluate all potential impacts of CSTs on people; (d) engage with and seek consent from people who may be observed and/or affected by CSTs; (e) build transparency and accountability into CST use; (f) respect peoples' rights and vulnerabilities; and (g) protect data in order to safeguard privacy. These principles require testing and could conceivably benefit conservation efforts, especially through inclusion of people likely to be affected by CSTs.