Canadian Forest Service Publications
Detection of coniferous seedlings in UAV imagery. 2018. Feduck, C.; McDermid, G.J.; Castilla, G. Forests 9(7):432.
Year: 2018
Issued by: Northern Forestry Centre
Catalog ID: 39562
Language: English
Availability: PDF (download)
Available from the Journal's Web site. †
DOI: 10.3390/f9070432
† This site may require a fee
Abstract
Rapid assessment of forest regeneration using unmanned aerial vehicles (UAVs) is likely to decrease the cost of establishment surveys in a variety of resource industries. This research tests the feasibility of using UAVs to rapidly identify coniferous seedlings in replanted forest-harvest areas in Alberta, Canada. In developing our protocols, we gave special consideration to creating a workflow that could perform in an operational context, avoiding comprehensive wall-to-wall surveys and complex photogrammetric processing in favor of an efficient sampling-based approach, consumer-grade cameras, and straightforward image handling. Using simple spectral decision rules from a red, green, and blue (RGB) camera, we documented a seedling detection rate of 75.8 % n = 149), on the basis of independent test data. While moderate imbalances between the omission and commission errors suggest that our workflow has a tendency to underestimate the seedling density in a harvest block, the plot-level associations with ground surveys were very high (Pearson’s r = 0.98; n = 14). Our results were promising enough to suggest that UAVs can be used to detect coniferous seedlings in an operational capacity with standard RGB cameras alone, although our workflow relies on seasonal leaf-off windows where seedlings are visible and spectrally distinct from their surroundings. In addition, the differential errors between the pine seedlings and spruce seedlings suggest that operational workflows could benefit from multiple decision rules designed to handle diversity in species and other sources of spectral variability.
Plain Language Summary
In Canada, forested areas that have been replanted after harvest must be surveyed to determine if the replanting efforts have been successful. These surveys confirm whether the spacing between the seedlings is adequate, check the survival and growth of the new trees, and assess the mix of species in the regenerating area. In this study, we compared ground-based counts of conifer seedlings with counts generated automatically using drone photography in two replanted areas in Alberta. We show that the two methods largely agreed, with drones finding more than three-quarters of the seedlings counted on foot. We used a straightforward workflow that forestry practitioners could adopt in the field. Our methods do not rely on complex processing of photographs of the entire area to produce maps and measurements. Instead, we used an efficient sampling-based approach, consumer-grade cameras, and simple image handling. Our workflow works best in months when the young conifer trees are the only green vegetation around. Our technology can potentially transform the way establishment surveys are conducted, leading to cheaper, faster assessments of the survival of replanted conifer seedlings on land that has been replanted.