A Semi-Automated RGB-Based Method for Wildlife Crop Damage Detection Using QGIS-Integrated UAV Workflow

Abstract

Monitoring crop damage caused by wildlife remains a significant challenge in agricultural management, particularly in the case of large-scale monocultures such as maize. The given study presents a semi-automated process for detecting wildlife-induced damage using RGB imagery acquired from unmanned aerial vehicles (UAVs). The method is designed for non-specialist users and is fully integrated within the QGIS platform. The proposed approach involves calculating three vegetation indices-Excess Green (ExG), Green Leaf Index (GLI), and Modified Green-Red Vegetation Index (MGRVI)-based on a standardized orthomosaic generated from RGB images collected via UAV. Subsequently, an unsupervised k-means clustering algorithm was applied to divide the field into five vegetation vigor classes. Within each class, 25% of the pixels with the lowest average index values were preliminarily classified as damaged. A dedicated QGIS plugin enables drone data analysts (Drone Data Analysts-DDAs) to adjust index thresholds, based on visual interpretation, interactively. The method was validated on a 50-hectare maize field, where 7 hectares of damage (15% of the area) were identified. The results indicate a high level of agreement between the automated and manual classifications, with an overall accuracy of 81%. The highest concentration of damage occurred in the "moderate" and "low" vigor zones. Final products included vigor classification maps, binary damage masks, and summary reports in HTML and DOCX formats with visualizations and statistical data. The results confirm the effectiveness and scalability of the proposed RGB-based procedure for crop damage assessment. The method offers a repeatable, cost-effective, and field-operable alternative to multispectral or AI-based approaches, making it suitable for integration with precision agriculture practices and wildlife population management.

Keywords: QGIS; RGB; UAV; crop damage; vegetation indices.

Figure 1

Method comparison—raw scores per criterion. Source: Authors’ own study, based on internal experimental trials.

Figure 2

Extended UML Diagram for Drone-Based Field Assessment Pipeline. Source: Authors’ own study, based on internal experimental trials.

Figure 3

Ortho-image with five-class vigor map: (a) Ortho-image; (b) Vigor classification map; (c) Ortho-image + vigor classification map overlay. Color interpretation for (b,c): Bright green—very good, dark green—good, yellow—moderate, orange—poor, red—very poor. Colors correspond to vegetation vigor classes, as explained in the caption. Source: Authors’ own study, based on internal experimental trials.

Figure 4

GUI interface for manipulating mask-generation indicators (tab: Parameters, Event file). Source: Authors’ own study, based on internal experimental trials.

Figure 5

Damage detection masks generated for each crop vigor class and combined result: (a) Aggregated damage mask with color-coded vegetation vigor classes; (b) Binary mask of all detected damage overlaid on the RGB orthophoto. Color interpretation for (a): Bright green—very good, dark green—good, yellow—moderate, orange—poor, red—very poor. Each color represents damaged areas identified within the corresponding vegetation vigor class. Source: Authors’ own study, based on internal experimental trials.

Figure 6

Location of the experimental area in northeastern Poland, including a detailed view of the field boundaries overlaid on high-resolution aerial imagery, and its general position within the national context. Source: Authors’ own study, based on internal experimental trials.

Figure 7

Location of control points randomly generated in QGIS. Source: Authors’ own study, based on internal experimental trials.

Figure 8

Confusion matrix for the conducted accuracy assess. Source: Authors’ own study, based on internal experimental trials.