Identification and Counting of European Souslik Burrows from UAV Images by Pixel-Based Image Analysis and Random Forest Classification: A Simple, Semi-Automated, yet Accurate Method for Estimating Population Size

Abstract

Burrowing mammals such as European sousliks are widespread and contribute significantly to soil ecosystem services. However, they have declined across their range and the non-invasive estimation of their actual population size has remained a challenge. Results support that the number of burrow entrances is positively correlated with population abundance, and burrow locations indicate the occupied area. We present an imagery-based method to identify and count animals’ burrows semi-automatically by combining remotely recorded red, green, and blue (RGB) images, pixel-based imagery, and random forest (RF) classification. Field images were collected for four colonies, then combined and processed by histogram matching and spectral band normalization to improve the spectral distinctions among the categories BURROW, SOIL, TREE, and GRASS. The accuracy indexes of classification for BURROW kappa (κ) were 95% (precision) and 90% (sensitivity). A 10-iteration bootstrapping of the final model resulted in coefficients of variation (CV%) of BURROW κ for sensitivity and precision lower than 5%; moreover, CV% values were not significantly different between those scores. The consistency of classification and balanced precision and sensitivity confirmed the applicability of this approach. Our approach provides an accurate, user-friendly, and relatively simple approach to count the number of burrow openings, estimate population abundance, and delineate the areas of occupancy non-invasively.

A spatial tool to identify potential conflict hotspots for the European ground squirrel in agricultural land

“…While other direct sampling measures, such as trapping-requiring methods like Capture-Mark-Recapture, telemetry or GPS based tools can potentially provide a more accurate measure of density and more detail in movement patterns, they require more labour and cost intensive activities (Bean et al 2012, Byers et al 2019 and it is difficult to implement them at scale. Mapping burrow openings in large areas can also be labour intensive, but the use of non-invasive conservation drones and image processing techniques have already shown that this method could be at least semi-automated in areas not covered by vegetation (Gedeon et al 2022). The number of burrow openings can vary significantly depending on the season (Grulich 1960) and our experience indicates that habitat management can also affect the visibility of burrow openings.…”

Efficacy of remote sensing technologies for burrow count estimates of a rare kangaroo rat

“…In the former study, burrow counts were adequate to determine relative abundance of D. ingens averaged over multiple years. In Europe, Gedeon et al (2022) used an imagery‐based method to identify and count burrows of an endangered rodent in order to estimate abundance. There is evidence from our ongoing work as well as earlier studies (Packard and Roberts 1973, Goetze et al 2007, Goetze et al 2008) that TKR individuals may vary in terms of using one versus multiple burrows at a given time, or that some burrows may be occupied by other species (e.g., Chaetodipus hispidus ).…”

Semantic segmentation of rodent burrows using deep convolutional architectures

“…The best detection result (86.7% accuracy) shows the images taken from a height of 24 meters. In work [4] the authors proposed a semi-automatically approach of land cover classification of two classes are burrows and soil. The classification is performed using RGB histograms extraction and random forest classification of them.…”