Detection of Single Standing Dead Trees From Aerial Color Infrared Imagery by Segmentation With Shape and Intensity Priors

Abstract

ABSTRACT:Standing dead trees, known as snags, are an essential factor in maintaining biodiversity in forest ecosystems. Combined with their role as carbon sinks, this makes for a compelling reason to study their spatial distribution. This paper presents an integrated method to detect and delineate individual dead tree crowns from color infrared aerial imagery. Our approach consists of two steps which incorporate statistical information about prior distributions of both the image intensities and the shapes of the target objects. In the first step, we perform a Gaussian Mixture Model clustering in the pixel color space with priors on the cluster means, obtaining up to 3 components corresponding to dead trees, living trees, and shadows. We then refine the dead tree regions using a level set segmentation method enriched with a generative model of the dead trees' shape distribution as well as a discriminative model of their pixel intensity distribution. The iterative application of the statistical shape template yields the set of delineated dead crowns. The prior information enforces the consistency of the template's shape variation with the shape manifold defined by manually labeled training examples, which makes it possible to separate crowns located in close proximity and prevents the formation of large crown clusters. Also, the statistical information built into the segmentation gives rise to an implicit detection scheme, because the shape template evolves towards an empty contour if not enough evidence for the object is present in the image. We test our method on 3 sample plots from the Bavarian Forest National Park with reference data obtained by manually marking individual dead tree polygons in the images. Our results are scenario-dependent and range from a correctness/completeness of 0.71/0.81 up to 0.77/1, with an average center-of-gravity displacement of 3-5 pixels between the detected and reference polygons.

Detecting Dead Standing Eucalypt Trees from Voxelised Full-Waveform Lidar Using Multi-Scale 3D-Windows for Tackling Height and Size Variations

“…They are, therefore, important for managing biodiversity. For detecting snags from infrared imagery, Polewski et al [60] used a two stages detections approach. At first Gaussian analysis was used to estimate locations of dead trees and they used prior knowledge about shapes and density of local areas manually labelled as snags.…”

Dead Wood Detection Based on Semantic Segmentation of VHR Aerial Cir Imagery Using Optimized FCN-Densenet

“…Another trend is to utilize the methods based on multispectral camera. For the task of dead tree detection, the Colour-Infrared camera (CIR) is widely utilized as the image pixel value in the near-infrared spectral channel obtained by the camera retains magnificent strength on identifying the tree health in forests (Polewski et al, 2015). However, most of current methods based on optical camera failed to accurately detect multi-class of dead trees and pixel-level tree segmentation is vulnerable to different factors, * Corresponding author although the benefits of pixel level detection are significant.…”

Sensing forest structure from LIDAR

“…We adapt the method of Polewski et al (2015b) which is originally designed for fallen tree segmentation, to detect the standing stems of single trees from unstructured high density ALS point clouds. The main goal is to detect linear structures in the ALS 3D point clouds which are likely to represent single tree stems.…”

“…The reconstruction of single tree stems at different canopy layers is an important factor for providing essential habitat resources for further studies (McElhinny et al, 2005;Polewski et al, 2015b;Polewski, 2017). Standard ALS sensors with a point density up to 30 points/m 2 are able to cover large areas more efficiently in terms of time and expense.…”

“…Point feature histograms (PFH): a local 3D shape descriptor of the neighborhood around the target point, based on the angular relationships between adjacent surface normals. It is useful for distinguishing between different types of surface classes based on their shape (plane, cylindrical, spherical, etc) (Rusu et al, 2008) (Rusu et al, 2008;Polewski et al, 2015b For the point classification level we chose Random Forest (Breiman, 2001) as a binary classifier due to its robust ability to estimate the class probability.…”