Illumination-Invariant Anomaly Detection for Sub-Canopy UAV Multispectral Point Clouds
2026-06-08 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method to find hidden or unusual objects under forest canopy using drone images that capture multiple wavelengths of light. They solved a tricky problem caused by shadows from trees, which usually mess up the image colors, by estimating the sun’s position and separating real shadows from dark objects without needing extra flight data. Their technique also carefully compares nearby points that share the same lighting to better tell apart natural background from targets. Tests showed their approach works better than existing methods for spotting things like camouflaged items or fallen trees in complex forests.
Unmanned Aerial Vehicle (UAV)Multispectral point cloudsIllumination heterogeneityAnomaly detectionSolar angle estimationRay-tracing modelShadow extractionSparse representationSpectral reflectanceForest canopy mapping
Authors
Likun Chen, Yanfeng Gu, Xian Li
Abstract
Unmanned Aerial Vehicle (UAV) multispectral point clouds (MPC) provide high-dimensional spatial-spectral data for sub-canopy target detection; however, their efficacy is significantly compromised by severe illumination heterogeneity caused by vegetation shadows. To address this, we propose a prior-free anomaly detection framework capable of robustly handling lighting variations. First, we formulate solar angle estimation as an inverse optimization problem. By coupling spectral indices with a ray-tracing model, this strategy achieves Prior-Free Shadow Extraction without relying on flight metadata, effectively distinguishing dark objects from true shadows. Second, to mitigate spectral distortions, we introduce an Illumination-Consistent Sparse Representation mechanism. Unlike standard reconstruction methods, we construct a background dictionary strictly from neighbors sharing the same illumination state. This constraint effectively disentangles spectral reflectance from lighting variations, ensuring that targets are represented solely by physically consistent background points. Experimental results indicate that the proposed method significantly improves the separability between anomalies and background in complex forest environments, demonstrating superior performance over state-of-the-art baselines. This framework is particularly suited for identifying camouflaged military targets, mapping fallen tree trunks, and uncovering archaeological ruins hidden beneath dense foliage.